Steel member cost and carbon emission optimization method and equipment

Abstract

The invention provides a method and equipment for optimizing cost and carbon emission of a steel member, which can achieve the purpose of minimizing carbon emission and cost by reasonably planning and adjusting key working procedures and execution modes of steel member processing according to construction site conditions and construction process characteristics. Therefore, a scientific basis is provided for an enterprise to formulate a carbon emission reduction strategy and optimize a production process. According to the method, the Pareto optimal solution set is automatically generated through an intelligent algorithm, and a multi-dimensional decision scheme considering the cost effectiveness and the low-carbon requirement is provided for steel member production and processing. In addition, a dynamic adjustment mechanism and a feedback control strategy ensure that the optimization scheme can adapt to market changes and changes of production requirements. The carbon emission in the whole construction process can be effectively controlled and reduced.

Description

Technical Field

[0001] The present invention relates to a method and device for optimizing steel component cost and carbon emissions. Background Art

[0002] Reducing carbon emissions during steel structure construction will play a vital role in achieving deep carbon reduction in the construction industry. Traditional steel component production and processing process design often fails to adequately consider carbon footprints, resulting in unnecessary carbon emissions at every stage, from material production to transportation and installation. Summary of the Invention

[0003] The object of the present invention is to provide a method and device for optimizing the cost and carbon emissions of steel components.

[0004] To solve the above problems, the present invention provides a method for optimizing steel component costs and carbon emissions, comprising:

[0005] Conduct carbon emission analysis on key processes in steel component processing to identify the types of labor, equipment, and resource consumption corresponding to each key process;

[0006] Determine the objective function for calculating carbon emissions and costs of the key process based on the types of labor, equipment, and resource consumption;

[0007] Based on the objective functions of carbon emission and cost calculation for the key processes, and with the minimization of cost and carbon emission as the goals, a multi-objective optimization model of carbon emission and cost is established, wherein each key process in the multi-objective optimization model has a selection mechanism of preset execution modes;

[0008] The NSGA-II genetic algorithm is used to solve the multi-objective optimization model, and the Pareto optimal solution set of the multi-objective optimization model is generated through the operations of initializing the population, calculating the objective function value, non-dominated sorting, crowding calculation, crossover mutation and iterative population update.

[0009] The weight coefficients corresponding to cost minimization and carbon emissions are determined based on real-time data, including real-time data on energy price fluctuations and carbon trading market prices. Based on the weight coefficients and the Pareto optimal set, the solution with the best overall performance is selected.

[0010] Furthermore, in the above method, the objective function for calculating carbon emissions in the key process includes:

[0011]

[0012] Where: C i —Carbon emissions of the i-th process;

[0013] Mj —The amount of the jth material consumed in the i-th process;

[0014] EF m —Carbon emission factor of the jth material used in the i-th process;

[0015] E i —The amount of electricity consumed by the i-th process;

[0016] EF e —The carbon emission coefficient of electricity in the region where the processing plant is located;

[0017] O i —The amount of oil consumed by the i-th process;

[0018] EF o —Oil carbon emission coefficient for the region where the processing plant is located;

[0019] G i —The amount of liquefied natural gas consumed by the i-th process;

[0020] EF g —Carbon emission coefficient of liquefied natural gas;

[0021] —The amount of CO2 directly released by welding shielding gas.

[0022] Furthermore, in the above method, the objective function for calculating the cost of the key process includes:

[0023]

[0024] F i is the cost of the i-th process;

[0025] T i is the processing time of the component in the i-th process;

[0026] N pi is the number of workers required for the i-th process;

[0027] F p for the cost of daily workers;

[0028] F a The unit time usage fee of mechanical equipment;

[0029] M ij —The amount of material / energy of the jth type consumed in the i-th process;

[0030] F mj is the cost price of the jth material / energy;

[0031] T giis the usage time of the i-th mechanical equipment;

[0032] P gi is the power of the i-th mechanical equipment;

[0033] F e The unit price of electricity.

[0034] Furthermore, in the above method, the multi-objective optimization model of carbon emissions and costs includes:

[0035]

[0036] Where: n is the number of key processes; m is the number of execution modes of the i-th key process; D ij It is a decision variable with a value of 0 or 1. When the i-th process adopts the j-th execution mode, its value is 1, otherwise it is 0.

[0037] Furthermore, in the above method, the initializing the population includes:

[0038] A population of N individuals is randomly generated. Each individual is a Q-dimensional execution pattern sequence, representing the execution pattern selected by each of the Q key processes. The gene value of each individual represents the execution pattern of each key process encoded in integers.

[0039] The calculating of the objective function value comprises:

[0040] For each individual, the corresponding carbon emissions and costs are calculated according to its gene value and the objective function of calculating carbon emissions and costs based on the key processes, and the corresponding carbon emissions and costs are recorded for each individual.

[0041] Furthermore, in the above method, the non-dominated sorting includes:

[0042] In a population of N individuals, individual A and individual B are identical if and only if C A ≤C B And F A ≤F B And at least one inequality is strictly true, then there is a dominance relationship, individual A dominates individual B;

[0043] Based on the dominance relationship, the population is divided into multiple Pareto front levels (Front 1, Front2, ...), where Front 1 contains individuals that are not dominated by any other solution, Front 2 contains individuals dominated by individuals in Front 1 but not dominated by other solutions, and so on.

[0044] Furthermore, in the above method, the congestion degree calculation includes:

[0045] For each individual in the Pareto frontier level, sort them by carbon emissions C and cost F, and calculate the crowding distance of each individual:

[0046] a. The crowding distance between the first and last individuals in the sorting of each Pareto front level is set to infinity;

[0047] b. The crowding distance of the middle individual in each Pareto frontier ranking is the sum of the objective function differences between the carbon emissions and costs of the adjacent individuals:

[0048]

[0049] Individuals with high Pareto frontier levels are given priority, and individuals with large crowding distances are selected at the same level. Through multiple selection operations, M individuals are retained as the parent population.

[0050] Furthermore, in the above method, the crossover and mutation operations include:

[0051] Randomly select two parent individuals from the parent population, randomly select a crossover point, exchange the parts of the two parent individuals after the crossover point, and generate two crossover offspring individuals; where the crossover probability is set to 0.8-0.9;

[0052] For each offspring individual after crossover, a gene position in the offspring individual is randomly selected, and the gene value of the gene position is replaced with one of the other execution modes to obtain the corresponding mutated offspring individual, where the mutation probability is set to 0.01-0.1.

[0053] Furthermore, in the above method, the iterative updating of the population includes:

[0054] The population of parent individuals of the current iteration and the population of mutated offspring individuals are merged to form a new candidate population; the candidate population is non-dominated sorted to obtain the corresponding Pareto front level; the crowding degree of the candidate population is calculated to obtain the crowding distance; the top P solutions are selected as the new population of parent individuals of the current iteration according to the Pareto front level and the crowding distance; crossover and mutation operations are performed on the new population of parent individuals of the current iteration to obtain the new population of mutated offspring individuals of the current iteration, and this step is repeated until the maximum number of iterations is reached;

[0055] The maximum number of iterations is set as T=100. When the maximum number of iterations is reached, all solutions of Pareto frontier level Front 1 in the candidate population of the current iteration are output, that is, the Pareto optimal solution set.

[0056] According to another aspect of the present invention, there is further provided a computer device, comprising:

[0057] processor; and

[0058] A memory arranged to store computer executable instructions, which when executed cause the processor to: perform any of the methods described above.

[0059] Compared with the existing technology, the construction steps will have different costs and carbon emissions under different construction conditions (such as different inputs of resources such as labor and machinery). The present invention proposes a method that can minimize carbon emissions and costs by rationally planning and adjusting the key processes and execution modes of steel component processing according to the conditions of the construction site and the characteristics of the construction process, thereby providing a scientific basis for enterprises to formulate carbon emission reduction strategies and optimize production processes. The present invention automatically generates a Pareto optimal solution set through an intelligent algorithm, providing a multi-dimensional decision-making solution for the production and processing of steel components that takes into account both cost-effectiveness and low-carbon requirements. In addition, the dynamic adjustment mechanism and feedback control strategy ensure that the optimization solution can adapt to market changes and changes in production demand. The present invention can effectively control and reduce carbon emissions throughout the construction process. The present invention incorporates potential construction economic and environmental impacts into the decision-making process during the design process, promoting a reasonable low-carbon transformation of the construction industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 4 is a flow chart of a method for optimizing steel component costs and carbon emissions according to an embodiment of the present invention. DETAILED DESCRIPTION

[0061] The present invention is further described in detail below with reference to the accompanying drawings.

[0062] In a typical configuration of the present application, the terminal, the device of the service network and the trusted party all include one or more processors (CPUs), input / output interfaces, network interfaces and memories.

[0063] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0064] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include non-transitory media such as modulated data signals and carrier waves.

[0065] like Figure 1 As shown, the present invention provides a method for optimizing steel component cost and carbon emissions, the method comprising:

[0066] Step S1: Conduct carbon emission analysis on key processes of steel component processing to identify the types of labor, equipment, and resource consumption corresponding to each key process;

[0067] Preferably, the key processes include: cutting Z1, assembly Z2, welding Z3, correction Z4, hole making Z5 and rust removal spraying Z6, a total of 6 key processes.

[0068] Through data collection and on-site investigation, we can obtain the types of labor, resource consumption, and equipment for each process, as shown in Table 1, so that we can further calculate the cost and carbon emissions of each process.

[0069] Table 1 List of equipment and resource consumption in steel component processing

[0070]

[0071]

[0072] Step S2: determining the objective function for calculating carbon emissions and costs of the key process based on the types of labor, equipment, and resource consumption.

[0073] Step S21, calculation of carbon emissions of different key processes:

[0074] The carbon emissions generated by each key process in the production of steel components mainly come from indirect carbon emissions generated by the energy (including electricity, oil, natural gas, etc.) consumed by the various mechanical equipment used in this process during operation, implicit carbon emissions generated by material consumption (such as steel raw materials, welding flux, welding wire, carbon rods, etc.), and direct carbon emissions generated during the processing process. The specific carbon emissions can be calculated using the following formula:

[0075]

[0076] Where: C i —Carbon emissions of the i-th process;

[0077] M j —The amount of the jth material consumed in the i-th process;

[0078] EF m —Carbon emission factor of the jth material used in the i-th process;

[0079] E i —The amount of electricity consumed by the i-th process;

[0080] EF e —The carbon emission coefficient of electricity in the region where the processing plant is located;

[0081] O i —The amount of oil consumed by the i-th process;

[0082] EF o —Oil carbon emission coefficient for the region where the processing plant is located;

[0083] G i —The amount of liquefied natural gas consumed by the i-th process;

[0084] EF g —Carbon emission coefficient of liquefied natural gas;

[0085] —The amount of CO2 directly released by welding shielding gas;

[0086] Step S22, cost calculation of different key processes:

[0087] The cost model for the steel component production process only focuses on the costs incurred during actual production activities, and does not consider the costs incurred during the design and transportation stages outside of production activities. The costs incurred during actual production activities mainly include labor costs, material costs, and machinery costs. Material costs mainly refer to the purchase and transportation costs of materials consumed in different key construction processes; labor costs mainly refer to the wages of different types of workers in each process; and machinery costs refer to the rental costs of processing equipment and the cost of energy consumed by machinery. They can be calculated using the following formula:

[0088]

[0089] F i is the cost of the i-th process;

[0090] T i is the processing time of the component in the i-th process;

[0091] N pi is the number of workers required for the i-th process;

[0092] F p for the cost of daily workers;

[0093] F a The unit time usage fee of mechanical equipment;

[0094] M ij —The amount of material / energy of the jth type consumed in the i-th process;

[0095] F mj is the cost price of the jth material / energy;

[0096] T gi is the usage time of the i-th mechanical equipment;

[0097] P gi is the power of the i-th mechanical equipment;

[0098] F e The unit price of electricity.

[0099] Step S3, based on the objective functions of calculating carbon emissions and costs for the key processes, and with the goal of minimizing costs and carbon emissions, a multi-objective optimization model for carbon emissions and costs is established, taking into account process relevance and synergy effects. Each key process in the multi-objective optimization model has a preset execution mode selection mechanism;

[0100] Preferably, three execution mode selection mechanisms for six key processes can be proposed.

[0101] The optimization goal of the present invention is the multi-objective optimization of "carbon emissions C - cost F". According to the execution mode included in different processes, a multi-objective optimization model of carbon emissions and costs is established as follows:

[0102]

[0103] Where: n is the number of key processes, n = 6; m is the number of execution modes of the i-th key process, m = 3; D ij It is a decision variable with a value of 0 or 1. When the i-th process adopts the j-th execution mode, its value is 1, otherwise it is 0.

[0104] For example, this paper considers the six key construction processes in steel component production: cutting, assembly, welding, straightening, hole making, and rust removal and spraying. Each process corresponds to three different execution modes, which vary in equipment selection and usage time, significantly affecting the cost and carbon emissions of each process. See Table 2 for details.

[0105] Table 2 Carbon emissions and costs of each process under different modes

[0106]

[0107]

[0108] Considering the close interdependence and synergy between the various processes, synergy can be used to further improve production efficiency, reduce costs, and reduce carbon emissions. This paper lists examples of core equipment combinations under three different modes, as shown in Table 3. Further equipment combinations can be explored to achieve efficient collaboration between processes.

[0109] Table 3 Examples of core device combinations in different modes

[0110]

[0111] In step S4, the NSGA-II genetic algorithm is selected to solve the multi-objective optimization model, and the Pareto optimal solution set of the multi-objective optimization model is generated through operations such as initializing the population, non-dominated sorting, congestion calculation, and crossover mutation, so as to provide production plans under different cost and carbon emission trade-offs.

[0112] Here, the NSGA-Ⅱ genetic algorithm can be used to solve the above multi-objective optimization model, thereby obtaining the Pareto optimal solution set of the multi-objective optimization model.

[0113] Step S41, initialize the population:

[0114] A population of N individuals (N=100) is randomly generated. Each individual is a 6-dimensional execution mode sequence, representing the execution mode selected by each of the six key processes. The gene value of each individual is represented by the execution mode of each key process encoded by an integer, such as 1 / 2 / 3 corresponding to execution mode one / two / three respectively.

[0115] For example, if the 6 gene values ​​of an individual are: [2,1,3,2,1,3], it means: cutting = mode 2, assembly = mode 1, welding = mode 3, correction = mode 2, hole making = mode 1, rust removal and spraying = mode 3. Chromosome length: 6 (corresponding to 6 processes)

[0116] In this multi-objective optimization problem, the 100 randomly generated individuals represent 100 combinations of six key processes and different execution modes. Each individual is a sequence of six integers, representing the execution mode (mode 1 / 2 / 3) selected for each of the six processes (cutting, assembly, welding, straightening, hole making, and rust removal and painting).

[0117] The specific meaning of individual:

[0118] Each individual is a sequence of the form [a,b,c,d,e,f], where:

[0119] a: Execution mode of blanking and cutting process (1 / 2 / 3);

[0120] b: Execution mode of assembly process (1 / 2 / 3);

[0121] c: Execution mode of welding process (1 / 2 / 3);

[0122] d: Execution mode of the correction process (1 / 2 / 3);

[0123] e: Execution mode of hole making process (1 / 2 / 3)

[0124] f: Execution mode of rust removal spraying process (1 / 2 / 3)

[0125] For example:

[0126] The individual [2,1,3,2,1,3] means: select mode 2 for cutting, mode 1 for assembly, mode 3 for welding, and so on.

[0127] Each individual corresponds to a specific production plan, and different plans have different costs and carbon emissions.

[0128] Step S42, calculate the objective function value:

[0129] For each individual, the corresponding carbon emissions and costs are calculated based on its gene value (execution mode selection) and the objective function of carbon emissions and cost calculation based on the key process, and the objective function values ​​(C, F) of the corresponding carbon emissions and costs are recorded for each individual.

[0130] Here, the objective function values ​​(C, F) form the basis of multi-objective optimization.

[0131] Step S43: non-dominated sorting

[0132] In a population of N individuals, individual A (solution A) and individual B (solution B) are both valid if and only if C A ≤C B And F A ≤F BAnd if at least one inequality holds strictly, there is a dominance relationship, and individual A (solution A) dominates individual B (solution B); based on the dominance relationship, the population is divided into multiple Pareto front levels (Front 1, Front 2,...), where Front 1 contains individuals that are not dominated by any other solutions, and Front 2 contains individuals that are dominated by the individuals in Front 1 but not by other solutions, and so on.

[0133] Here, non-dominated sorting is one of the core steps of NSGA-II, which divides the solutions in the population into different levels according to the superiority and inferiority relationship:

[0134] Dominance relationship: Solution A dominates solution B if and only if all objectives (C and F) of A are not inferior to B, and at least one objective is strictly better than B.

[0135] Frontier division:

[0136] Front 1: All solutions that are not dominated by any other solutions (optimal solution set)

[0137] Front 2: Solutions that are dominated by the solutions in Front 1 but not by other solutions (sub-optimal)

[0138] And so on...

[0139] This hierarchical method ensures that the optimal solutions are preferentially retained.

[0140] Specifically, in the context of multi-objective optimization and the NSGA-II algorithm, A and B in solution A dominates solution B represent two different individuals (i.e., the combination of key processes and execution modes).

[0141] Specifically, the mathematical definition of the dominance relationship:

[0142] For two solutions A and B, if the following conditions are satisfied, then A is said to dominate B (denoted as A > B):

[0143] All objective values of A are not inferior to B: [[ID=۳۴]]

[0144] The cost volume of A ≤ the cost volume of B (i.e., C _A ≤ C B )

[0145] And the carbon emission of A ≤ the carbon emission of B (i.e., F A ≤ F B )

[0146] A has at least one objective value strictly better than B:

[0147] The cost volume of A < the cost volume of B (i.e., C _A < C B )

[0148] Or the carbon emission of A < the carbon emission of B (i.e., F A <F B ).

[0149] The following is an example. Suppose there are two solutions:

[0150] Solution A: [2, 1, 3, 2, 1, 3], and the calculated C A = 150, F A = 80;

[0151] Solution B: [1, 2, 3, 1, 2, 3], and the calculated C B = 160, F B = 90;

[0152] At this time: A dominates B because:

[0153] C A (150) ≤ C_ B (160) and F A (80) ≤ F B (90);

[0154] At the same time, C _A < C B (The total cost is more optimal).

[0155] Situations where the domination relationship is not satisfied:

[0156] If there is a solution: Solution C: [3, 1, 2, 3, 1, 2], and the calculated C C = 140, F C = 95;

[0157] At this time:

[0158] C does not dominate A because although C C (140) < C A (150), but F C (95) > F A (80);

[0159] A does not dominate C either because although F A ]](80) < F(80) < F C (95), but C A (150) > C C (140)

[0160] C and A are in a non - domination relationship, and both will be assigned to the same front rank (such as Front 1).

[0161] The role of the domination relationship in NSGA - II

[0162] Non-dominated sorting: By comparing the dominance relationship of all solutions, the population is divided into different front levels (Front1, Front 2, ...).

[0163] Step S44, congestion calculation;

[0164] For each individual in the Pareto frontier level, sort them by carbon emissions C and cost F, and calculate the crowding distance of each individual:

[0165] a. The crowding distance between the first and last individuals in the sorting of each Pareto front level is set to infinity (∞);

[0166] b. The crowding distance of the middle individual in each Pareto frontier ranking is the sum of the objective function differences between the carbon emissions and costs of the adjacent individuals:

[0167]

[0168] Individuals with high Pareto frontier levels are given priority, and individuals with large crowding distances are selected at the same level. Through multiple selection operations, M individuals are retained as the parent population.

[0169] Here, the solution choice is:

[0170] Prioritize retaining solutions with stronger dominance (such as those in Front 1).

[0171] Within the same Pareto frontier level, more evenly distributed solutions are further screened by the congestion degree to avoid the algorithm converging to a local area.

[0172] Step S45, crossover and mutation operations:

[0173] Two parent individuals are randomly selected from the parent population, a crossover point is randomly selected (the gene value position is 1 to 5), and the parts of the two parent individuals after the crossover point are exchanged to generate two crossover offspring individuals; the crossover probability is usually set to 0.8-0.9; for each crossover offspring individual, a gene position in the offspring individual is randomly selected, and the gene value of the gene position is replaced with one of the other execution modes (1→2 or 3, 2→1 or 3, 3→1 or 2) to obtain the corresponding mutated offspring individual, wherein the mutation probability is usually set to 0.01-0.1.

[0174] Here, the intersection point is the range of gene value positions:

[0175] The minimum is 1: it means starting the exchange from the second position (that is, retaining the gene value of the first position);

[0176] The maximum is 5: it means that the exchange starts from the 6th position (that is, only the gene value of the last position is exchanged).

[0177] For example, parent 1: [2,1,3,2,1,3];

[0178] Parent 2: [1,2,3,1,2,3];

[0179] Crossover point: 3 (the part after position 3 is swapped);

[0180] Child 1: [2,1,3,1,2,3] / / The first 3 digits of parent 1 + the last 3 digits of parent 2;

[0181] Child 2: [1,2,3,2,1,3] / / The first 3 digits of parent 2 + the last 3 digits of parent 1;

[0182] Mutation operation steps:

[0183] The first step is to select the mutation position: randomly select a gene position in the individual (an integer between 1 and 6).

[0184] The second step is to replace the gene value: replace the gene value at that position with one of the other two possible patterns.

[0185] Example: Assume that the randomly selected individuals and the decoded variant positions are as follows:

[0186] Individual: [2,1,3,2,1,3]

[0187] Mutation position: 4 (i.e. the 4th gene position, value 2)

[0188] New individuals generated after mutation:

[0189] The original gene value is 2 → changes to 1 or 3 (randomly selected)

[0190] The new individual may be: [2,1,3,1,1,3] or [2,1,3,3,1,3]

[0191] Step S46, iteratively update the population:

[0192] The population of parent individuals of the current iteration and the population of mutated offspring individuals are merged to form a new candidate population; a non-dominated sorting is performed on the candidate population (refer to step S43) to obtain a corresponding Pareto frontier level; and a crowding degree is calculated on the candidate population (refer to step S44) to obtain a crowding distance; the top P solutions are selected as the new population of parent individuals of the current iteration according to the Pareto frontier level and the crowding distance; a crossover and mutation operation is performed on the new population of parent individuals of the current iteration (refer to step S45) to obtain a new population of mutated offspring individuals of the current iteration, and this step is repeated until the maximum number of iterations is reached;

[0193] The maximum number of iterations is set as T=100. When the maximum number of iterations is reached, all solutions of Pareto frontier level Front 1 in the candidate population of the current iteration are output, that is, the Pareto optimal solution set.

[0194] Ultimately, NSGA-II will output a set of Pareto optimal solutions (i.e., individuals in Front 1) that do not dominate each other and represent the optimal trade-off between cost and carbon emissions.

[0195] The following is a detailed explanation of the iterative population update step, illustrating how to find the Pareto optimal solution set through multiple generations of evolution:

[0196] The core logic of iterative updates is as follows:

[0197] In each generation iteration:

[0198] Merge population: Merge the current parent population (M solutions) with the child population (M solutions) to form a candidate population containing 2M solutions.

[0199] Non-dominated sorting: Perform non-dominated sorting on the candidate population and divide the solutions into different front levels (Front 1, Front 2,...).

[0200] Crowding calculation: Calculate the crowding degree of each solution within the frontier to evaluate the distribution uniformity of the solution.

[0201] Select the next generation: Select solutions from small to large according to the frontier level, and select from large to small according to the congestion degree within the same frontier, until M solutions are selected as the parents of the next generation.

[0202] Termination condition: Repeat the above process until the maximum number of iterations T (such as 100 generations) is reached, at which time all solutions in Front 1 are output as the Pareto optimal solution set.

[0203] Example demonstration (assuming M=4):

[0204] Initial parent population (P);

[0205] P = {solution 1, solution 2, solution 3, solution 4};

[0206] Crossover mutation generates offspring (O);

[0207] O = {solution 5, solution 6, solution 7, solution 8};

[0208] Merge candidate population (R):

[0209] R = P∪O = {solution 1, solution 2, solution 3, solution 4, solution 5, solution 6, solution 7, solution 8};

[0210] Non-dominated sorting results:

[0211] Front 1 = {Solution 1, Solution 5};

[0212] Front 2 = {Solution 2, Solution 6, Solution 7};

[0213] Front 3 = {Solution 3, Solution 4, Solution 8}.

[0214] Crowding calculation (simplified example):

[0215] Front 1:

[0216] -Solution 1: congestion degree = 1.2;

[0217] -Solution 5: Congestion degree = 0.8.

[0218] Front 2:

[0219] -Solution 2: congestion degree = 1.5;

[0220] -Solution 6: congestion degree = 0.7;

[0221] -Solution 7: Congestion degree = 0.9.

[0222] Select the next generation parent:

[0223] Prioritize Front 1: Solution 1, Solution 5 (2 solutions, less than N=4);

[0224] Then select Front 2: Select Solution 2 and Solution 7 in descending order of congestion (4 solutions in total, full);

[0225] The final next generation parent: {solution 1, solution 5, solution 2, solution 7}.

[0226] Optimal solution example: The NSGA-II genetic algorithm can be implemented using Python code, ultimately yielding several relatively optimal solutions, as shown in Table 4. These solutions constitute the optimal solution set for the original problem. The construction process corresponding to each feasible solution can effectively guide the steel component processing process.

[0227] Table 4 Process pattern corresponding to the optimal solution

[0228]

[0229] Step S5, determining the weight coefficients corresponding to cost minimization and carbon emissions based on real-time data, wherein the real-time data includes real-time data on energy price fluctuations and carbon trading market prices; based on the weight coefficients and the Pareto optimal set, selecting the solution with the best overall performance.

[0230] In many cases, companies need to find a balance between costs and carbon emissions. By introducing weight coefficients ω1 and ω2, they can perform a weighted summation of the two objectives to select the solution with the best overall performance:

[0231] S=ω1·F+ω2·C, ω1+ω2=1

[0232] Among them, S is the comprehensive score; ω1 is the weight coefficient of cost; ω2 is the weight coefficient of carbon emissions;

[0233] The ω1 and ω2 data settings can be dynamically adjusted based on real-time data (such as energy price fluctuations, carbon trading market prices, etc.) to determine the optimal solution.

[0234] When there are multiple groups with the same or similar comprehensive scores, further ranking and optimization can be performed based on the synergistic effects between different processes, for example:

[0235] 1) The waste heat from the laser cutting process can be effectively used to preheat the assembly process, thereby saving energy and improving overall efficiency;

[0236] 2) The combined use of CNC plasma cutting machines and band saws can flexibly meet the processing needs of materials of different thicknesses and optimize resource allocation.

[0237] Preferably, the present invention may further include: dynamically adjusting the optimization results, and designing the equipment types of each key process into independent functional modules, which can be quickly replaced or upgraded as needed.

[0238] According to another aspect of the present invention, there is further provided a computer device, comprising:

[0239] processor; and

[0240] A memory arranged to store computer executable instructions, which when executed cause the processor to: perform any of the methods described above.

[0241] Here, the equipment types in each key process are designed as independent functional modules, which can be quickly replaced or upgraded according to the needs of different production tasks. As production scales up, more automated equipment or intelligent control systems can be added to the existing ones to facilitate the addition of new functional modules or integration with other systems. These functional modules are equipped with a carbon efficiency labeling system that displays their carbon emissions per unit of production time, costs, and carbon efficiency level. Through the digital twin simulation system, intelligent combination optimization can be carried out to calculate the carbon emissions and costs of the entire steel component process.

[0242] In summary, construction steps will have different costs and carbon emissions under different construction conditions (such as different inputs of resources such as labor and machinery). The present invention proposes a method that can minimize carbon emissions and costs by rationally planning and adjusting key processes and execution modes of steel component processing according to construction site conditions and construction process characteristics, thereby providing a scientific basis for enterprises to formulate carbon emission reduction strategies and optimize production processes. The present invention automatically generates a Pareto optimal solution set through an intelligent algorithm, providing a multi-dimensional decision-making solution for the production and processing of steel components that takes into account both cost-effectiveness and low-carbon requirements. In addition, the dynamic adjustment mechanism and feedback control strategy ensure that the optimization solution can adapt to market changes and changes in production demand. The present invention can effectively control and reduce carbon emissions throughout the construction process. The present invention incorporates potential construction economic and environmental impacts into the decision-making process during the design process, promoting a reasonable low-carbon transformation of the construction industry.

[0243] The detailed contents of the various device embodiments of the present invention can be found in the corresponding parts of the various method embodiments, which will not be repeated here.

[0244] Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is intended to include these modifications and variations.

[0245] It should be noted that the present invention can be implemented in software and / or a combination of software and hardware, for example, can be implemented using an application specific integrated circuit (ASIC), a general purpose computer or any other similar hardware device. In one embodiment, the software program of the present invention can be executed by a processor to implement the steps or functions described above. Similarly, the software program of the present invention (including related data structures) can be stored in a computer-readable recording medium, for example, a RAM memory, a magnetic or optical drive or a floppy disk and similar devices. In addition, some steps or functions of the present invention can be implemented using hardware, for example, as a circuit that cooperates with a processor to perform each step or function.

[0246] In addition, a portion of the present invention may be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. The program instructions for calling the method of the present invention may be stored in a fixed or removable recording medium, and / or transmitted through a data stream in a broadcast or other signal-carrying medium, and / or stored in a working memory of a computer device that operates according to the program instructions. Here, according to one embodiment of the present invention, a device is included, which includes a memory for storing computer program instructions and a processor for executing the program instructions, wherein, when the computer program instructions are executed by the processor, the device is triggered to operate based on the aforementioned methods and / or technical solutions according to multiple embodiments of the present invention.

[0247] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-restrictive, and the scope of the invention is defined by the appended claims rather than the above description, and it is intended that all changes that fall within the meaning and scope of the equivalents of the claims be encompassed within the present invention. Any figure marks in the claims should not be regarded as limiting the claims involved. In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the device claim may also be implemented by one unit or device through software or hardware. Words such as first and second are used to indicate names and do not indicate any particular order.

Claims

1. A method for optimizing steel component costs and carbon emissions, characterized in that: include: Conduct carbon emission analysis on key processes in steel component processing to identify the types of labor, equipment, and resource consumption corresponding to each key process; Determine the objective function for calculating carbon emissions and costs of the key process based on the types of labor, equipment, and resource consumption; Based on the objective functions of carbon emission and cost calculation for the key processes, and with the minimization of cost and carbon emission as the goals, a multi-objective optimization model of carbon emission and cost is established, wherein each key process in the multi-objective optimization model has a selection mechanism of preset execution modes; The NSGA-II genetic algorithm is used to solve the multi-objective optimization model, and the Pareto optimal solution set of the multi-objective optimization model is generated through the operations of initializing the population, calculating the objective function value, non-dominated sorting, crowding calculation, crossover mutation and iterative population update. Determining weight coefficients corresponding to cost minimization and carbon emissions based on real-time data, including real-time data on energy price fluctuations and carbon trading market prices; Based on the weight coefficient and the Pareto optimal set, the solution with the best overall performance is selected.

2. The method for optimizing steel component cost and carbon emissions according to claim 1, wherein: The objective function for calculating carbon emissions of the key process includes: Where: C i —Carbon emissions of the i-th process; M j —The amount of the jth material consumed in the i-th process; EF m —Carbon emission factor of the jth material used in the i-th process; E i —The amount of electricity consumed by the i-th process; EF e —The carbon emission coefficient of electricity in the region where the processing plant is located; O i —The amount of oil consumed by the i-th process; EF o —Oil carbon emission coefficient for the region where the processing plant is located; G i —The amount of liquefied natural gas consumed by the i-th process; EF g —Carbon emission coefficient of liquefied natural gas; —The amount of CO2 directly released by welding shielding gas.

3. The method for optimizing steel component cost and carbon emissions according to claim 2, wherein: The objective function for cost calculation of key processes includes: F i is the cost of the i-th process; T i is the processing time of the component in the i-th process; N pi is the number of workers required for the i-th process; F p for the cost of daily workers; F a The unit time usage fee of mechanical equipment; M ij —The amount of material / energy of the jth type consumed in the i-th process; F mj is the cost price of the jth material / energy; T gi is the usage time of the i-th mechanical equipment; P gi is the power of the i-th mechanical equipment; F e The unit price of electricity.

4. The method for optimizing steel component cost and carbon emissions according to claim 3, wherein: The multi-objective optimization model of carbon emissions and costs includes: Where: n is the number of key processes; m is the number of execution modes of the i-th key process; D ij It is a decision variable with a value of 0 or 1. When the i-th process adopts the j-th execution mode, its value is 1, otherwise it is 0.

5. The method for optimizing steel component cost and carbon emissions according to claim 4, wherein: The initialization population includes: A population of N individuals is randomly generated. Each individual is a Q-dimensional execution pattern sequence, representing the execution pattern selected by each of the Q key processes. The gene value of each individual represents the execution pattern of each key process encoded in integers. The calculating of the objective function value comprises: For each individual, the corresponding carbon emissions and costs are calculated according to its gene value and the objective function of calculating carbon emissions and costs based on the key processes, and the corresponding carbon emissions and costs are recorded for each individual.

6. The method for optimizing steel component cost and carbon emissions according to claim 5, wherein: The non-dominated sorting includes: In a population of N individuals, individual A and individual B are identical if and only if C A ≤C B And F A ≤F B , and at least one inequality is strictly true, then there is a dominance relationship, individual A dominates individual B; Based on the dominance relationship, the population is divided into multiple Pareto front levels (Front 1, Front 2, ...), where Front 1 contains individuals that are not dominated by any other solution, Front 2 contains individuals dominated by individuals in Front 1 but not dominated by other solutions, and so on.

7. The method for optimizing steel component cost and carbon emissions according to claim 6, wherein: The congestion degree calculation includes: For each individual in the Pareto frontier level, sort them by carbon emissions C and cost F, and calculate the crowding distance of each individual: a. The crowding distance between the first and last individuals in the sorting of each Pareto front level is set to infinity; b. The crowding distance of the middle individual in each Pareto frontier ranking is the sum of the objective function differences between the carbon emissions and costs of the adjacent individuals: Individuals with high Pareto frontier levels are given priority, and individuals with large crowding distances are selected at the same level. Through multiple selection operations, M individuals are retained as the parent population.

8. The method for optimizing steel component cost and carbon emissions according to claim 7, wherein: The crossover and mutation operations include: Randomly select two parent individuals from the parent population, randomly select a crossover point, exchange the parts of the two parent individuals after the crossover point, and generate two crossover offspring individuals; where the crossover probability is set to 0.8-0.9; For each offspring individual after crossover, a gene position in the offspring individual is randomly selected, and the gene value of the gene position is replaced with one of the other execution modes to obtain the corresponding mutated offspring individual, where the mutation probability is set to 0.01-0.

1.

9. The method for optimizing steel component cost and carbon emissions according to claim 7, wherein: The iterative updating of the population includes: The population of parent individuals of the current iteration and the population of mutated offspring individuals are merged to form a new candidate population; the candidate population is non-dominated sorted to obtain the corresponding Pareto front level; the crowding degree of the candidate population is calculated to obtain the crowding distance; the top P solutions are selected as the new population of parent individuals of the current iteration according to the Pareto front level and the crowding distance; crossover and mutation operations are performed on the new population of parent individuals of the current iteration to obtain the new population of mutated offspring individuals of the current iteration, and this step is repeated until the maximum number of iterations is reached; The maximum number of iterations is set as T=100. When the maximum number of iterations is reached, all solutions of Pareto frontier level Front 1 in the candidate population of the current iteration are output, that is, the Pareto optimal solution set.

10. A computer device, wherein: include: processor; as well as A memory arranged to store computer executable instructions which, when executed, cause the processor to: perform the method according to any one of claims 1 to 9.

Images