A method, device and equipment for optimizing utilization of steel bars

Abstract

The application discloses a steel bar utilization optimization method and device, equipment and a readable storage medium, and relates to the technical field of steel bar utilization optimization. The method comprises the following steps: first, obtaining a blanking task of a steel bar, and digitally representing the blanking task to obtain data characteristics of the steel bar; then, standardizing and splicing all the data characteristics to obtain a characteristic vector; then, performing product calculation on the characteristic vector and a preset correlation matrix to obtain a comprehensive benefit prediction value of the blanking task on each candidate algorithm; finally, based on the comprehensive benefit prediction value, an optimal algorithm is determined from the candidate algorithms by using a decision maker. The complex engineering problem is converted into quantifiable and calculable standard data objects, precise and automatic decision-making is realized in the blanking link according to the task, and the scientificity, consistency and overall efficiency of the material optimization process are significantly improved.

Description

Technical Field

[0001] This invention relates to the field of steel reinforcement utilization optimization technology, and more specifically to a method, apparatus, equipment, and readable storage medium for optimizing steel reinforcement utilization. Background Technology

[0002] Against the backdrop of the national "dual-carbon" strategy and the transformation and upgrading of the construction industry towards lean and digitalization, steel reinforcement, as one of the most widely used and concentrated basic materials in engineering construction, has made material conservation and consumption reduction in its processing a key focus of the industry and an important technological breakthrough for achieving efficient resource utilization. Among these, steel reinforcement cutting optimization, as a crucial step in the steel reinforcement processing, has a direct impact on material utilization, production efficiency, and overall costs.

[0003] Existing steel reinforcement cutting optimization technologies mainly focus on improving the performance of single algorithms, resulting in several relatively mature technical routes. Firstly, there are classic heuristic algorithms, such as those combining greedy strategies with dynamic programming. These algorithms are fast, simple to implement, and produce stable results, making them widely used in industrial software systems. However, when the cutting task is large-scale, the process constraints are complex, or the component specifications exhibit non-standardized characteristics, these algorithms are prone to getting trapped in local optima, making it difficult to obtain a globally optimal solution. Secondly, there are metaheuristic algorithms, such as genetic algorithms and simulated annealing algorithms. These have strong global search capabilities and can adapt well to complex constraints and irregular requirements, but they typically suffer from long computation times and a certain degree of randomness in the solution results, making them difficult to meet the high requirements of drawing efficiency and response time in actual production applications. Thirdly, there are precise algorithm frameworks, such as column generation methods. These methods can theoretically approximate mathematically optimal solutions and are suitable for major engineering scenarios with extremely high material utilization requirements. However, their computational complexity is high, they are highly sensitive to hardware resources and problem scale, and their implementation cost is high, making them difficult to widely promote in conventional engineering projects.

[0004] In summary, existing technologies, regardless of the algorithmic approach employed, focus primarily on optimizing the algorithm itself, lacking the ability to dynamically match and intelligently select algorithms based on the inherent characteristics of specific material cutting tasks (such as problem size, component length distribution, and constraint complexity). Furthermore, existing solutions fail to effectively utilize the execution results of historical material cutting tasks to continuously learn and optimize algorithm selection and parameter configuration, resulting in a difficulty in balancing solution quality and computational efficiency across different application scenarios.

[0005] Therefore, there is an urgent need for a method to optimize the utilization rate of steel bars that can solve the above-mentioned defects. Summary of the Invention

[0006] The purpose of this invention is to provide a method, apparatus, equipment, and readable storage medium for optimizing rebar utilization. First, by digitally representing the material cutting task across multiple dimensions—including scale, distribution, constraints, and business processes—complex engineering problems are transformed into quantifiable and computable standard data objects, laying a solid foundation for intelligent decision-making. Second, by multiplying the standardized, concatenated feature vectors with a preset correlation matrix, the comprehensive performance of different candidate algorithms on this specific task can be predicted scientifically and efficiently, thus elevating algorithm selection from subjective experience or fixed rules to objective prediction based on a data model. Finally, the decision-maker automatically determines the optimal algorithm based on the predicted values, achieving precise and automated decision-making "tailored to the task" in the material cutting process, significantly improving the scientific rigor, consistency, and overall efficiency of the material optimization process.

[0007] To achieve the above objectives, the present invention provides the following technical solution: In a first aspect, the present invention provides a method for optimizing the utilization rate of reinforcing steel bars, the method comprising: Obtain the cutting task of steel bars and digitally represent the cutting task to obtain the data characteristics of the steel bars; the data characteristics include at least one of scale characteristics, distribution characteristics, constraint characteristics and business characteristics; Based on the mean and standard deviation of the data features in the historical task dataset, the standardized features of the data features are calculated; The standardized features are concatenated in a preset order to obtain a feature vector; The feature vector is multiplied by a preset correlation matrix to obtain the comprehensive benefit prediction value of the material feeding task for each candidate algorithm; the preset correlation matrix is ​​used to characterize the benefit response of each candidate algorithm to the material feeding task. Based on the predicted comprehensive benefits, the optimal algorithm is determined from the candidate algorithms using a decision-maker; Based on the predicted comprehensive benefits, at least one suboptimal algorithm is determined from the candidate algorithms using a decision-maker; The actual comprehensive benefit value of the material feeding task is calculated based on the optimal algorithm and the suboptimal algorithm. Based on the predicted comprehensive benefit value and the actual comprehensive benefit value, the weight vectors of each candidate algorithm in the preset correlation matrix are adjusted.

[0008] In some embodiments, scale characteristics include the total number of steel bars, the number of unique specifications, and the total required length.

[0009] In some embodiments, the distribution characteristics include the weighted average length of the reinforcing bars, the standard deviation of length, the coefficient of variation, and the entropy of the specification distribution.

[0010] In some embodiments, the constraint feature is the process requirement for the reinforcing steel; The business characteristic is the user's preference for optimizing material cutting tasks.

[0011] Secondly, the present invention also provides a steel reinforcement utilization optimization device, the device comprising: The task acquisition module is used to acquire the cutting task of steel bars and to digitally represent the cutting task to obtain the data characteristics of the steel bars; the data characteristics include at least one of scale characteristics, distribution characteristics, constraint characteristics and business characteristics; The feature concatenation module is used to calculate the standardized features of the data features based on the mean and standard deviation of the data features in the historical task dataset; and to concatenate the standardized features in a preset order to obtain a feature vector. The benefit prediction module is used to multiply the feature vector with a preset correlation matrix to obtain the comprehensive benefit prediction value of the material feeding task for each candidate algorithm; the preset correlation matrix is ​​used to characterize the benefit response of each candidate algorithm to the material feeding task. The algorithm determination module is used to determine the optimal algorithm from the candidate algorithms based on the comprehensive benefit prediction value using a decision-maker; determine at least one suboptimal algorithm from the candidate algorithms based on the comprehensive benefit prediction value using a decision-maker; calculate the actual comprehensive benefit value of the material feeding task based on the optimal algorithm and the suboptimal algorithm; and adjust the weight vector of each candidate algorithm in the preset correlation matrix based on the comprehensive benefit prediction value and the actual comprehensive benefit value.

[0012] Thirdly, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steel reinforcement utilization optimization method provided in the first aspect.

[0013] Fourthly, the present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steel reinforcement utilization optimization method provided in the first aspect.

[0014] Fifthly, the present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the steel reinforcement utilization optimization method provided in the first aspect.

[0015] The beneficial effects of this invention are as follows: The steel bar utilization optimization method of this invention first obtains the steel bar cutting task and digitally represents the cutting task to obtain the data characteristics of the steel bar; the data characteristics include at least one of scale characteristics, distribution characteristics, constraint characteristics, and business characteristics; then, all data characteristics are standardized and concatenated to obtain a feature vector; then, the feature vector is multiplied by a preset correlation matrix to obtain the comprehensive benefit prediction value of the cutting task for each candidate algorithm; the preset correlation matrix is ​​used to characterize the benefit response of each candidate algorithm to the cutting task; finally, based on the comprehensive benefit prediction value, a decision-maker is used to determine the optimal algorithm from the candidate algorithms. First, by digitally representing the cutting task in multiple dimensions covering scale, distribution, constraints, and business, complex engineering problems are transformed into quantifiable and computable standard data objects, laying a solid foundation for intelligent decision-making. Second, by multiplying the standardized and concatenated feature vector with the preset correlation matrix, the comprehensive performance of different candidate algorithms on this specific task can be predicted scientifically and efficiently, thereby elevating algorithm selection from subjective experience or fixed rules to objective prediction based on data models. Ultimately, the decision-maker automatically determines the optimal algorithm based on the predicted values, achieving precise and automated decision-making "tailored to the task" in the material feeding process, significantly improving the scientific nature, consistency, and overall efficiency of the material optimization process.

[0016] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, the preferred embodiments of the present invention are described in detail below with reference to the accompanying drawings. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating a method for optimizing the utilization rate of reinforcing bars according to an embodiment of the present invention; Figure 2 This is a schematic diagram of a steel bar utilization optimization device according to an embodiment of the present invention; Figure 3 This is a schematic diagram of an electronic device structure provided in an embodiment of this application. Detailed Implementation

[0018] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention. It should be noted that references to "an embodiment," "embodiment," "example embodiment," etc., in this specification refer to the described embodiment including specific features, structures, or characteristics; however, not every embodiment must include these specific features, structures, or characteristics. Furthermore, such expressions do not refer to the same embodiment. Moreover, when describing specific features, structures, or characteristics in conjunction with embodiments, whether or not explicitly described, it indicates that incorporating such features, structures, or characteristics into other embodiments is within the knowledge scope of those skilled in the art.

[0019] Furthermore, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0020] In some embodiments, such as Figure 1 As shown, a method for optimizing the utilization rate of reinforcing steel is provided, the specific method including: S101: Obtain the cutting task of the steel bars and digitally represent the cutting task to obtain the data characteristics of the steel bars.

[0021] The data characteristics include at least one of the following: scale characteristics, distribution characteristics, constraint characteristics, and business characteristics. Scale characteristics include the total number of rebar parts, the number of unique specifications, and the total required length. Distribution characteristics include the weighted average length of the rebar, the standard deviation of length, the coefficient of variation, and the specification distribution entropy. Constraint characteristics are the technological requirements for the rebar; business characteristics are the user's optimization preferences for the material cutting task.

[0022] For example, a material unloading task Includes the following raw data: : List of lengths for different parts. : List of required quantities for the corresponding parts . : Set of process constraints (e.g., kerf width) Minimum usable scrap length (Whether specific connectors are allowed, etc.). Business preference parameters (e.g., optimization mode is "extreme material saving" or "quick drawing").

[0023] The scale feature describes the basic size of the task and directly affects the computational complexity, such as the total number of parts: Unique specification number: Total required length: .

[0024] Distribution characteristics describe the degree of dispersion and concentration of part lengths, affecting the difficulty of combinatorial optimization and the effectiveness of algorithms. For example, weighted average length: Length standard deviation: Coefficient of variation: Specification distribution entropy: ,in .

[0025] Constraint features are used to encode specific process requirements. For example... ,in It is an indicator function; it returns 1 if the condition is met, and 0 otherwise.

[0026] Business characteristics can quantify users' optimization goals and preferences, which can be used to adjust benefit assessments. For example, time cost weighting: From business parameters The mapping is obtained (e.g., 0.9 corresponds to "Quick Drawing"). Material cost weight: .

[0027] The process of expressing the material cutting task with numbers is the process of digitally representing the material cutting task, and the representation result is the data characteristics of the steel bars.

[0028] S102, calculate the standardized features of the data features based on the mean and standard deviation of the data features in the historical task dataset.

[0029] Specifically, each data feature is standardized to ensure it has equal importance in the association matrix learning process. The Z-Score method is used to standardize the values. for: in, and These are the mean and standard deviation of the feature calculated on the historical task dataset or the current task pool. For binary constrained features, they are usually kept unchanged at 0 / 1 or scaled in the range of [0,1]. x is the data feature.

[0030] S103: Concatenate the standardized features in a preset order to obtain the feature vector.

[0031] All the standardized features are concatenated in a predetermined order to form the final feature vector. : ; S104, perform product calculation on the feature vector and the preset correlation matrix to obtain the comprehensive benefit prediction value of the material feeding task for each candidate algorithm.

[0032] The preset correlation matrix is ​​used to characterize the benefit response of each candidate algorithm to the material feeding task.

[0033] For example, an association matrix It can be: ; Where d is the dimension of the task feature vector, and k is the number of candidate algorithms; the i-th row of the matrix is ​​the representation vector of algorithm i, and each element... The contribution weight (positive or negative correlation) of the j-th task feature to the expected comprehensive benefit of algorithm i is quantified; the j-th column of the matrix roughly reflects the sensitivity distribution of all algorithms to the j-th task feature.

[0034] Comprehensive benefit forecast ; Right now .

[0035] S105, based on the comprehensive benefit prediction value, uses a decision maker to determine the optimal algorithm from the candidate algorithms.

[0036] Specifically, the comprehensive benefit prediction value includes the benefit prediction values ​​of each candidate algorithm. The candidate algorithm with the highest benefit prediction value is selected as the optimal algorithm, and the steel bar cutting task is executed according to the optimal algorithm, thereby optimizing the steel bar utilization rate.

[0037] S106, based on the comprehensive benefit prediction value, use the decision-maker to determine at least one suboptimal algorithm from the candidate algorithms.

[0038] Specifically, at least one suboptimal algorithm can be selected, whose comprehensive benefit prediction value is second only to the left and right algorithms.

[0039] S107, calculates the actual value of the comprehensive benefits of the material feeding task based on the optimal algorithm and the suboptimal algorithm.

[0040] Specifically, the average of the benefit values ​​corresponding to the optimal algorithm and the suboptimal algorithm can be used as the actual value of the comprehensive benefit.

[0041] S108, based on the predicted and actual comprehensive benefits, adjust the weight vectors of each candidate algorithm in the preset correlation matrix.

[0042] For example, the way to adjust the weight vectors of each candidate algorithm in the preset correlation matrix can be: ; in, For real benefits, To predict benefits, This is the learning rate.

[0043] The steel reinforcement utilization optimization method in the above embodiments first obtains the steel reinforcement cutting task and digitally represents the task to obtain the data features of the steel reinforcement. These data features include at least one of scale features, distribution features, constraint features, and business features. Then, all data features are standardized and concatenated to obtain a feature vector. Next, the feature vector is multiplied by a preset correlation matrix to obtain the comprehensive benefit prediction value of the cutting task for each candidate algorithm. The preset correlation matrix is ​​used to characterize the benefit response of each candidate algorithm to the cutting task. Finally, based on the comprehensive benefit prediction value, a decision-maker is used to determine the optimal algorithm from the candidate algorithms. Firstly, by digitally representing the cutting task across multiple dimensions including scale, distribution, constraints, and business, complex engineering problems are transformed into quantifiable and computable standard data objects, laying a solid foundation for intelligent decision-making. Secondly, by multiplying the standardized and concatenated feature vector with the preset correlation matrix, the comprehensive performance of different candidate algorithms on this specific task can be predicted scientifically and efficiently, thereby elevating algorithm selection from subjective experience or fixed rules to objective prediction based on a data model. Ultimately, the decision-maker automatically determines the optimal algorithm based on the predicted values, achieving precise and automated decision-making "tailored to the task" in the material feeding process, significantly improving the scientific nature, consistency, and overall efficiency of the material optimization process.

[0044] Based on the same inventive concept, this application also provides a rebar utilization optimization device for implementing the above-mentioned rebar utilization optimization method. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more rebar utilization optimization device embodiments provided below can be found in the limitations of the rebar utilization optimization method above, and will not be repeated here.

[0045] In one embodiment, such as Figure 2 As shown, a device for optimizing the utilization rate of reinforcing steel is provided, the device comprising: The task acquisition module 30 is used to acquire the cutting task of steel bars and to digitally represent the cutting task to obtain the data characteristics of the steel bars; the data characteristics include at least one of scale characteristics, distribution characteristics, constraint characteristics and business characteristics; The feature concatenation module 31 is used to calculate the standardized features of the data features based on the mean and standard deviation of the data features in the historical task dataset; and to concatenate the standardized features in a preset order to obtain a feature vector. The benefit prediction module 32 is used to perform a product calculation on the feature vector and the preset correlation matrix to obtain the comprehensive benefit prediction value of the material feeding task for each candidate algorithm; the preset correlation matrix is ​​used to characterize the benefit response of each candidate algorithm to the material feeding task; The algorithm determination module 33 is used to determine the optimal algorithm from the candidate algorithms based on the comprehensive benefit prediction value using a decision-maker; determine at least one suboptimal algorithm from the candidate algorithms based on the comprehensive benefit prediction value using a decision-maker; calculate the actual comprehensive benefit value of the material feeding task based on the optimal algorithm and the suboptimal algorithm; and adjust the weight vector of each candidate algorithm in the preset correlation matrix based on the comprehensive benefit prediction value and the actual comprehensive benefit value.

[0046] In another embodiment, the scale characteristics include the total number of steel reinforcement parts, the number of unique specifications, and the total required length.

[0047] In another embodiment, the distribution characteristics include the weighted average length of the reinforcing bars, the standard deviation of the length, the coefficient of variation, and the entropy of the specification distribution.

[0048] In another embodiment, the constraint feature is the process requirements for the reinforcing bars; the business feature is the user's optimization preferences for the material cutting task.

[0049] This application also provides an electronic device, in some embodiments, referring to... Figure 3 As shown, the electronic device 700 includes an input unit 710, a memory 720, a processor 730, and an output unit 740. The memory 720 stores program instructions that can be executed on the processor 730. The processor 730 can execute the rebar utilization optimization method and / or technical solution based on the foregoing embodiments by calling the program instructions. The electronic device 700 can be a mobile terminal device such as a mobile phone or computer.

[0050] Furthermore, embodiments of this application also provide a computer-readable storage medium for storing a computer program that executes a method for optimizing rebar utilization. For example, computer program instructions, when executed by a computer, can invoke or provide the methods and / or technical solutions according to this application through the operation of the computer. The program instructions that invoke the methods of this application may be stored in a fixed or removable storage medium, and / or transmitted via data streams in broadcast or other signal carrying media, and / or stored in a storage medium that operates according to the program instructions.

[0051] Obviously, those skilled in the art should understand that the modules or steps of this application described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby storing them in a storage device for execution by a computing device, or fabricating them separately as individual integrated circuit modules, or fabricating multiple modules or steps as a single integrated circuit module. Thus, this application is not limited to any particular combination of hardware and software.

[0052] The technical features of the above embodiments can be arbitrarily integrated. For the sake of brevity, not all possible integrations of the technical features in the above embodiments are described. However, as long as the integration of these technical features does not contradict each other, they should be considered to be within the scope of this specification.

[0053] The above embodiments merely illustrate several implementation methods of the present invention, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of this invention patent should be determined by the appended claims.

Claims

1. A method for optimizing the utilization rate of reinforcing steel bars, characterized in that, The method includes: Obtain the cutting task of steel bars and digitally represent the cutting task to obtain the data characteristics of the steel bars; the data characteristics include at least one of scale characteristics, distribution characteristics, constraint characteristics and business characteristics; Based on the mean and standard deviation of the data features in the historical task dataset, the standardized features of the data features are calculated; The standardized features are concatenated in a preset order to obtain a feature vector; The feature vector is multiplied by a preset correlation matrix to obtain the comprehensive benefit prediction value of the material feeding task for each candidate algorithm; the preset correlation matrix is ​​used to characterize the benefit response of each candidate algorithm to the material feeding task. Based on the predicted comprehensive benefits, the optimal algorithm is determined from the candidate algorithms using a decision-maker; Based on the predicted comprehensive benefits, at least one suboptimal algorithm is determined from the candidate algorithms using a decision-maker; The actual comprehensive benefit value of the material feeding task is calculated based on the optimal algorithm and the suboptimal algorithm. Based on the predicted comprehensive benefit value and the actual comprehensive benefit value, the weight vectors of each candidate algorithm in the preset correlation matrix are adjusted.

2. The method for optimizing steel reinforcement utilization as described in claim 1, characterized in that, The scale characteristics include the total number of steel bars, the number of unique specifications, and the total required length.

3. The method for optimizing steel reinforcement utilization as described in claim 1, characterized in that, The distribution characteristics include the weighted average length, length standard deviation, coefficient of variation, and specification distribution entropy of the reinforcing bars.

4. The method for optimizing steel reinforcement utilization as described in claim 1, characterized in that, The constraint feature is the process requirement for the reinforcing steel; The business feature refers to the user's optimization preferences for the material unloading task.

5. A device for optimizing the utilization rate of reinforcing steel bars, characterized in that, The device includes: The task acquisition module is used to acquire the cutting task of steel bars and to digitally represent the cutting task to obtain the data characteristics of the steel bars; the data characteristics include at least one of scale characteristics, distribution characteristics, constraint characteristics and business characteristics; The feature concatenation module is used to calculate the standardized features of the data features based on the mean and standard deviation of the data features in the historical task dataset; and to concatenate the standardized features in a preset order to obtain a feature vector. The benefit prediction module is used to multiply the feature vector with a preset correlation matrix to obtain the comprehensive benefit prediction value of the material feeding task for each candidate algorithm; the preset correlation matrix is ​​used to characterize the benefit response of each candidate algorithm to the material feeding task. The algorithm determination module is used to determine the optimal algorithm from the candidate algorithms based on the comprehensive benefit prediction value using a decision-maker; determine at least one suboptimal algorithm from the candidate algorithms based on the comprehensive benefit prediction value using a decision-maker; calculate the actual comprehensive benefit value of the material feeding task based on the optimal algorithm and the suboptimal algorithm; and adjust the weight vector of each candidate algorithm in the preset correlation matrix based on the comprehensive benefit prediction value and the actual comprehensive benefit value.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steel reinforcement utilization optimization method as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steel reinforcement utilization optimization method according to any one of claims 1 to 4.

8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steel reinforcement utilization optimization method as described in any one of claims 1 to 4.

Images