Steelmaking continuous casting multi-layer intelligent scheduling optimization system and method based on edge calculation

Abstract

The invention provides a steelmaking continuous casting multi-layer intelligent scheduling optimization system and method based on edge calculation, and relates to the technical field of steelmaking continuous casting, and the method comprises the steps: deploying edge calculation nodes on steelmaking and continuous casting equipment, collecting the environment parameters and production parameters of a current task in real time, carrying out the non-dimensionalization processing of the environment parameters and production parameters, and carrying out the optimization of the multi-layer intelligent scheduling of the current task; generating a casting evaluation index, an energy consumption index and a cost benefit index; combining the casting evaluation index, the energy consumption index and the cost benefit index to construct a comprehensive production evaluation model, determining the weight in the model through an analytic hierarchy process, and generating a comprehensive evaluation index of the current production task by using the comprehensive production evaluation model; the comprehensive evaluation index is compared with a preset evaluation threshold value, production scheduling is adjusted in real time according to the comparison result, and intelligent upgrading of steelmaking continuous casting production is promoted.

Description

Technical Field

[0001] The present invention relates to the technical field of steelmaking continuous casting, and particularly to a multi-layer intelligent scheduling optimization system and method for steelmaking continuous casting based on edge computing. Background Art

[0002] In the traditional steelmaking continuous casting production process, the production scheduling mode mainly relies on manual experience and static scheduling plans. This method is particularly weak in the face of complex and changeable production environments. Due to the lack of real-time monitoring, the changes in environmental parameters and production parameters during the production process often cannot be reflected in the scheduling decisions in a timely manner. This results in a decline in production efficiency and unstable output quality when equipment performance fluctuates, raw material quality changes, or external environmental interference occurs. In addition, scheduling decisions based on historical data often cannot meet the actual production needs of the current situation, resulting in the lag and blindness of production scheduling, and ultimately affecting the optimization of the overall production process.

[0003] In addition, there are also obvious deficiencies in the data processing and analysis capabilities of the existing technologies. Most traditional systems adopt centralized data processing, resulting in long data response times, poor real-time performance, and difficulty in adapting to rapidly changing production requirements. In addition, existing systems usually lack the ability to comprehensively evaluate multiple production indicators, resulting in the optimization of a single indicator often at the expense of other indicators. For example, in order to reduce energy consumption, production efficiency may be reduced, and vice versa. This limitation makes it difficult for production managers to comprehensively evaluate the mutual influence between different production parameters, and thus unable to make scientific and reasonable scheduling decisions. At the same time, the data transparency and security of traditional systems are relatively low, the difficulty of data sharing is increased, and it is easy to form information islands, further restricting the optimization and improvement of the production process. Therefore, there is an urgent need for a new type of intelligent scheduling system to improve the dynamic adaptability and resource allocation efficiency of the steelmaking continuous casting process.

[0004] The above information disclosed in the background art section is only used to enhance the understanding of the background of the present disclosure, and thus it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0005] The purpose of the present invention is to provide a multi-layer intelligent scheduling optimization system and method for steelmaking continuous casting based on edge computing to solve the problems raised in the above background art.

[0006] To achieve the above purpose, the present invention provides the following technical solutions:

[0007] A multi-layer intelligent scheduling optimization system for steelmaking continuous casting based on edge computing specifically includes:

[0008] Edge computing deployment module, used to deploy edge computing nodes on steelmaking and continuous casting equipment, and collect environmental parameters and production parameters of the current task in real time. The environmental parameters include liquid metal temperature, mold pressure, and smelting time, and the production parameters include the production cost and benchmark production cost of the current task, the energy consumed in the production of the current task, and the target energy consumption.

[0009] Index generation module, used to generate a casting evaluation index after dimensionless processing of the liquid metal temperature, mold pressure, and smelting time, generate an energy consumption index after dimensionless processing of the energy consumed in the production of the current task and the target energy consumption, and generate a cost-benefit index after dimensionless processing of the production cost and benchmark production cost of the current task.

[0010] Model construction module, used to combine the casting evaluation index, energy consumption index, and cost-benefit index to construct a comprehensive production evaluation model, determine the weights within the model through the analytic hierarchy process, and generate a comprehensive evaluation index for the current production task using the comprehensive production evaluation model.

[0011] Real-time scheduling adjustment module, used to compare the comprehensive evaluation index with a preset evaluation threshold, adjust the production scheduling in real time according to the comparison result, and deploy a blockchain platform to record the production scheduling data generated by the edge computing nodes.

[0012] Further, place a thermocouple in the area where the metal is melted in the furnace to collect the liquid metal temperature, and record the liquid metal temperature as T liquid ; Use a pressure sensor to monitor the pressure in the mold in real time, and record the mold pressure as P mold ; Use a timer to record the duration of the smelting process, and record the smelting time as t furnace ;

[0013] Obtain the production cost and benchmark production cost of the current task. The production cost of the current task is the total cost consumed during the production process, including raw materials, energy, and labor costs. The benchmark production cost is the estimated cost under normal production conditions, and record the production cost of the current task as C prod , and record the benchmark production cost as C baseline ;

[0014] Obtain the energy consumed in the production of the current task and the target energy consumption. The target energy consumption is the expected energy consumption value to achieve the production target under the set production conditions, and record the energy consumed in the production of the current task as E consumed , and record the target energy consumption as E target .

[0015] Further, the formula for generating the casting evaluation index is as follows:

[0016]

[0017] Cas is the casting evaluation index, T liquid is the liquid metal temperature, T ref is the reference value of the liquid metal temperature, P mold is the mold pressure, P ref is the reference value of the mold pressure, t furnace is the smelting time, t ref is the reference value of the smelting time, α, β, and γ are preset proportionality coefficients, α > β > γ > 0, and satisfy α + β + γ = 1;

[0018] The energy consumption index is generated according to the following formula:

[0019]

[0020] In the formula, Eef is the energy consumption index, E target is the target energy consumption, E consumed is the energy consumed in the production of the current task;

[0021] The cost - benefit index is generated according to the following formula:

[0022]

[0023] In the formula, Ben is the cost - benefit index, C baseline is the benchmark production cost, C prod represents the production cost of the current task.

[0024] Furthermore, the casting evaluation index, energy consumption index, and cost - benefit index are combined to construct a comprehensive production evaluation model. The model expression is as follows:

[0025]

[0026] In the formula, QS is the comprehensive evaluation index, Cas is the casting evaluation index, Eef is the energy consumption index, Ben is the cost - benefit index, and ω1, ω2, and ω3 are the weights of the casting evaluation index, energy consumption index, and cost - benefit index respectively, which are determined by the analytic hierarchy process;

[0027] Furthermore, the specific logic for determining the weights by the analytic hierarchy process is as follows:

[0028] The three indicators of the casting evaluation index, energy consumption index, and cost - benefit index are marked. The relative importance values between each pair are determined by the nine - scale method to construct a judgment matrix. Among them, the casting evaluation index is marked as 1, the energy consumption index is marked as 2, and the cost - benefit index is marked as 3. The constructed judgment matrix is:

[0029]

[0030] Among them, both f and v represent the indices of exponents, and f ∈ [1, 3], v ∈ [1, 3], b fv represents the importance degree of the exponent with index f relative to the exponent with index v. The importance degree adopts a 1 - 9 scale method, and b fv The larger the value of b, the greater the importance degree of the exponent with index f compared to the exponent with index v, and b ff = 1,

[0031] Divide each element value in the judgment matrix by the sum of its column to obtain a normalized judgment matrix. Calculate the mean value of each row element value in the normalized judgment matrix, and take the mean value of the first row element value as the weight of the casting evaluation index, the mean value of the second row element value as the weight of the energy consumption index, and the mean value of the third row element value as the weight of the cost - benefit index. With the constraint that the sum of the scaled - down values equals 1, scale the three weights proportionally, and take the scaled - down weights as the proportional coefficients of the corresponding indices.

[0032] Furthermore, compare the comprehensive evaluation index with a preset evaluation threshold. The specific logic is as follows:

[0033] When QS ≥ QY, continue with the current scheduling plan, check the operating status of the equipment, and perform necessary maintenance to ensure the long - term efficient operation of the equipment;

[0034] When QS < QY, adjust the production parameters, specifically including: adjusting the heating settings of the melting furnace, increasing the output power, raising or lowering the temperature of the liquid metal according to the temperature reference threshold to ensure good fluidity of the metal during casting; checking and adjusting the hydraulic system of the casting equipment, raising or lowering the mold pressure to ensure that the metal can fully fill the mold and reduce casting defects; extending or shortening the smelting time according to the actual production situation and metal composition requirements to ensure that the quality and performance of the metal meet the standards; adjusting the production operation, using energy - saving equipment to reduce energy consumption while meeting production requirements; re - evaluating raw material suppliers and selecting materials with high cost - performance to reduce production costs;

[0035] In the formula, QS is the comprehensive evaluation index, and QY is the preset evaluation threshold.

[0036] Furthermore, deploy a blockchain platform to record the production scheduling data generated by edge computing nodes. The production scheduling data includes the casting evaluation index, the energy consumption index, and the cost - benefit index to ensure the transparency and immutability of data sharing. The blockchain uses Hyperledger Fabric technology for data recording and sharing.

[0037] The present invention also provides a multi-layer intelligent scheduling optimization method for steelmaking continuous casting based on edge computing. The multi-layer intelligent scheduling optimization method for steelmaking continuous casting based on edge computing is obtained by executing the above-mentioned multi-layer intelligent scheduling optimization system for steelmaking continuous casting based on edge computing, and specifically includes:

[0038] Step 1: Deploy edge computing nodes on steelmaking and continuous casting equipment to collect the environmental parameters and production parameters of the current task in real time. The environmental parameters include liquid metal temperature, mold pressure, and smelting time, and the production parameters include the production cost and benchmark production cost of the current task, the energy consumed in the production of the current task, and the target energy consumption.

[0039] Step 2: After dimensionless processing of the liquid metal temperature, mold pressure, and smelting time, a casting evaluation index is generated. After dimensionless processing of the energy consumed in the production of the current task and the target energy consumption, an energy consumption index is generated. After dimensionless processing of the production cost and benchmark production cost of the current task, a cost-benefit index is generated.

[0040] Step 3: Combine the casting evaluation index, energy consumption index, and cost-benefit index to construct a comprehensive production evaluation model. Determine the weights within the model through the analytic hierarchy process, and use the comprehensive production evaluation model to generate a comprehensive evaluation index for the current production task.

[0041] Step 4: Compare the comprehensive evaluation index with a preset evaluation threshold. According to the comparison result, adjust the production scheduling in real time, and at the same time deploy a blockchain platform to record the production scheduling data generated by the edge computing nodes.

[0042] Compared with the prior art, the beneficial effects of the present invention are:

[0043] By deploying edge computing on steelmaking and continuous casting equipment, the present invention realizes the real-time monitoring and analysis of environmental parameters and production parameters during the production process. This system can collect environmental parameters and production parameters in a timely manner, thus providing an accurate data basis for scheduling decisions. The ability to collect and process real-time data enables scheduling strategies to flexibly respond to various changes in production, optimize the production process, and significantly improve production efficiency. In addition, the system adopts a dimensionless processing technology to generate a casting evaluation index, an energy consumption index, and a cost-benefit index for comprehensive evaluation of different indicators. This comprehensive evaluation model combines the analytic hierarchy process to scientifically determine the weights of various indicators, making production scheduling decisions more accurate and reasonable. By comparing the comprehensive evaluation index with a preset evaluation threshold, the system can adjust production parameters in real time, optimize the heating settings of the melting furnace, the mold pressure, and the smelting time, thereby ensuring the high efficiency of the production process and the stability of product quality. At the same time, the application of blockchain technology ensures the transparency and immutability of production scheduling data, improves the credibility of data sharing, and helps to achieve information management of the entire process and efficient utilization of resources. These effects jointly promote the intelligent upgrade of steelmaking continuous casting production and achieve the dual goals of energy conservation and consumption reduction and cost control. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a schematic diagram of the system module of the present invention;

[0045] Figure 2 It is a schematic diagram of the overall method flow of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0046] To make the objectives, technical solutions, and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below in conjunction with specific embodiments.

[0047] It should be noted that unless otherwise defined, the technical terms or scientific terms used in the present invention should have the ordinary meanings understood by those of ordinary skill in the field to which the present invention belongs. The "first", "second", and similar terms used in the present invention do not indicate any order, quantity, or importance, but are only used to distinguish different components. The terms such as "including" or "comprising" mean that the elements or objects appearing before this word cover the elements or objects listed after this word and their equivalents, without excluding other elements or objects. The terms such as "connected" or "coupled" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The terms such as "upper", "lower", "left", and "right" are only used to represent relative positional relationships, and when the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0048] Example:

[0049] Please refer to Figure 1 , the present invention provides a multi-layer intelligent scheduling optimization system for steelmaking continuous casting based on edge computing, specifically including:

[0050] An edge computing deployment module, used to deploy edge computing nodes on steelmaking and continuous casting equipment, and collect environmental parameters and production parameters of the current task in real time. The environmental parameters include liquid metal temperature, mold pressure, and smelting time, and the production parameters include the production cost and benchmark production cost of the current task, the energy consumed in the production of the current task, and the target energy consumption;

[0051] In this embodiment, a thermocouple is placed in the area where the metal is melted in the furnace to collect the liquid metal temperature, and the liquid metal temperature is denoted as T liquid ; a pressure sensor is used to monitor the pressure in the mold in real time, and the mold pressure is denoted as P mold ; a timer is used to record the duration of the smelting process, and the smelting time is denoted as t furnace ;

[0052] Obtain the production cost and benchmark production cost of the current task. The production cost of the current task is the total cost consumed during the production process, including raw materials, energy, and labor costs. The benchmark production cost is the estimated cost under normal production conditions, and the production cost of the current task is denoted as C prod , and the benchmark production cost is denoted as C baseline ;

[0053] Obtain the energy consumed in the production of the current task and the target energy consumption. The target energy consumption is the expected energy consumption value to achieve the production target under the set production conditions, and the energy consumed in the production of the current task is denoted as E consumed , and the target energy consumption is denoted as E target .

[0054] The advantage of the edge computing deployment module is that it can perform data processing and analysis at the proximal end of steelmaking and continuous casting equipment, significantly improving the real-time performance and response speed of data collection. Compared with the prior art, this module reduces data transmission delay, making it possible to monitor the production site in real time, and can quickly reflect the changes in various environmental and production parameters during the production process, thus providing timely and accurate data support for scheduling decisions. This real-time performance is particularly important in complex production environments, which can effectively avoid production decision-making mistakes caused by information lag, thereby improving the overall production efficiency and product quality.

[0055] In this solution, the adoption of the edge computing deployment module can significantly enhance the overall performance of the intelligent scheduling optimization system. By collecting and analyzing key parameters in real time, the system can dynamically adjust production scheduling based on the latest data, optimize resource allocation, and reduce energy consumption and production costs. In addition, the introduction of this module provides a solid data foundation for the subsequent construction of the comprehensive evaluation model and real-time scheduling adjustment, making the production process more flexible and adaptable, and ultimately achieving the goal of intelligent production management. This not only enhances the transparency of the production process but also provides practical guarantees for achieving efficient and low-consumption production.

[0056] An index generation module is used to generate a casting evaluation index after dimensionless processing of the liquid metal temperature, mold pressure, and smelting time, generate an energy consumption index after dimensionless processing of the energy consumed by the current task production and the target energy consumption, and generate a cost-benefit index after dimensionless processing of the production cost of the current task and the benchmark production cost.

[0057] In this embodiment, the formula for generating the casting evaluation index is as follows:

[0058]

[0059] Cas is the casting evaluation index, T liquid is the liquid metal temperature, T ref is the reference value of the liquid metal temperature, P mold is the mold pressure, P ref is the reference value of the mold pressure, t furnace is the smelting time, t ref is the reference value of the smelting time, and α, β, and γ are preset proportionality coefficients, where α > β > γ > 0 and satisfy α + β + γ = 1. This is because in the steelmaking and continuous casting processes, the liquid metal temperature is generally considered the most critical parameter as it directly affects the fluidity of the metal, the pouring quality, and the properties of the final product. The mold pressure and smelting time are also important, but relatively speaking, their direct impact on the casting process is usually lower than that of the liquid metal temperature. Therefore, it is reasonable to assign the highest weight to the liquid metal temperature. The mold pressure directly affects the filling effect of the metal in the mold, the integrity and surface quality of the casting. The smelting time mainly affects the composition and quality of the metal, but its immediate effect on the casting process is relatively small. Therefore, setting β to be greater than γ reflects the higher impact of the mold pressure on the casting quality.

[0060] Cas comprehensively considers the deviations of the liquid metal temperature, mold pressure, and smelting time and their impact on the casting quality. A higher Cas value usually indicates that the parameters of the casting process are closer to the ideal state, thus reflecting a higher casting quality. When |T liquid -T refWhen it increases, it indicates that the gap between the temperature of the liquid metal and the reference temperature increases. Excessive or too low temperature may cause uneven cooling of the metal during solidification, increasing the internal stress of the casting and possibly leading to deformation or cracking. Therefore, Cas will decrease; when|P mold -P ref When it increases, it indicates that the difference between the mold pressure and the reference pressure increases. If the mold pressure is too low, it may cause the liquid metal to not fully fill the mold, resulting in casting defects such as pores and inclusions. Excessive mold pressure may cause the casting to deform or crack, especially stress concentration may occur during solidification, reducing the quality of the casting. Therefore, Cas will decrease accordingly; when|t furnace -t ref When it increases, it indicates that the difference between the smelting time and the reference time increases. If the smelting time is too long, it may cause changes in the metal composition, affecting the uniformity and performance of the alloy. Too short smelting time may cause the alloying elements not to dissolve fully, resulting in uneven metal composition. Therefore, Cas will decrease; that is to say,|T liquid -T ref |,|P mold -P ref |,|t furnace -t ref | and Cas are negatively correlated.

[0061] The energy consumption index is generated according to the following formula:

[0062]

[0063] In the formula, Eef is the energy consumption index, E target is the target energy consumption, E consumed is the energy consumed in the production of the current task;

[0064] Eef measures the ratio of the actual energy consumption to the target energy consumption. A higher energy consumption index indicates that the enterprise can effectively control the energy consumption during the production process and achieve good energy utilization efficiency. When E consumed increases, it reflects a decrease in the energy utilization efficiency. Therefore, Eef will decrease; that is to say, E consumed and Eef are negatively correlated.

[0065] The cost-benefit index is generated according to the following formula:

[0066]

[0067] In the formula, Ben is the cost-benefit index, C baseline is the benchmark production cost, C prod represents the production cost of the current task.

[0068] Ben reflects the gap between the current production cost and the benchmark production cost. A higher Ben value indicates that the current production cost is lower than the benchmark cost, indicating that the enterprise has achieved cost savings in actual production; when C prod increases, it means that the production cost increases and the Ben value decreases, that is, it shows that C prod is negatively correlated with Ben.

[0069] The advantage of the index generation module is that it can convert different types of production parameters into an index form that is easy to compare and analyze through dimensionless processing. This enables the comprehensive evaluation of the casting evaluation index, energy consumption index, and cost-benefit index within the same framework, thereby eliminating the dimensional influence between different data dimensions. The introduction of this module effectively improves the efficiency and accuracy of data processing, enabling scheduling decisions to be based on more scientific indicators and being able to promptly reflect changes in the production process.

[0070] Compared with the prior art, the index generation module reduces the dependence on manual intervention and subjective judgment through automated dimensionless processing, reducing potential errors and biases in the data processing process. This not only improves the objectivity of the evaluation but also enables real-time scheduling adjustments to be based on more accurate evaluation results, ensuring the flexibility and efficiency of the production process. In this solution, the adoption of the index generation module can greatly promote the intelligent development of the overall solution. Through the generated casting evaluation index, energy consumption index, and cost-benefit index, the system can more effectively identify and optimize key links in production, thereby supporting the decision-making of the real-time scheduling adjustment module. The introduction of this module makes the entire scheduling optimization system more scientific and systematic, improves production efficiency, reduces resource waste, and lays the foundation for achieving the goal of an intelligent factory.

[0071] The model construction module is used to combine the casting evaluation index, energy consumption index, and cost-benefit index to construct a comprehensive production evaluation model, determine the weights within the model through the analytic hierarchy process, and generate a comprehensive evaluation index for the current production task using the comprehensive production evaluation model;

[0072] In this embodiment, the casting evaluation index, energy consumption index, and cost-benefit index are combined to construct a comprehensive production evaluation model, and the model expression is as follows:

[0073]

[0074] In the formula, QS is the comprehensive evaluation index, Cas is the casting evaluation index, Eef is the energy consumption index, Ben is the cost-benefit index, and ω1, ω2, and ω3 are the weights of the casting evaluation index, energy consumption index, and cost-benefit index respectively, determined according to the analytic hierarchy process;

[0075] When Cas increases, it means that the product quality, qualification rate, or process flow in the casting process has been optimized, which may also have a positive impact on production efficiency and energy consumption. Therefore, QS will increase accordingly. When Eef increases, it means that the enterprise's efficiency in terms of energy consumption increases, and QS will also increase. When Ben increases, it means that the effective control of costs in the production process will enhance the enterprise's competitiveness in the market, which also leads to an increase in QS. That is to say, Cas, Eef, and Ben are positively correlated with QS.

[0076] The specific logic for determining weights through the Analytic Hierarchy Process is as follows:

[0077] Mark the three indicators of the casting evaluation index, energy consumption index, and cost-benefit index, and determine the relative importance values between each pair through the nine-scale method to construct a judgment matrix. Among them, mark the casting evaluation index as 1, the energy consumption index as 2, and the cost-benefit index as 3. The constructed judgment matrix is:

[0078]

[0079] Among them, both f and v represent the indices of the indices, and f ∈ [1, 3], v ∈ [1, 3], b fv represents the importance degree of the index with index f relative to the index with index v. The importance degree uses the 1-9 scale method, and b fv The larger the value, the greater the importance degree of the index with index f compared to the index with index v, and b ff = 1,

[0080] Divide each element value in the judgment matrix by the sum of its columns to obtain the normalized judgment matrix. Calculate the mean value of each row element value in the normalized judgment matrix, and take the mean value of the first row element value as the weight of the casting evaluation index, the mean value of the second row element value as the weight of the energy consumption index, and the mean value of the third row element value as the weight of the cost-benefit index. With the constraint that the sum of the scaled values is equal to 1, scale the three weights proportionally, and take the scaled weights as the proportional coefficients of the corresponding indices.

[0081] The advantage of the model construction module is that it can systematically integrate the casting evaluation index, energy consumption index, and cost-benefit index into a comprehensive production evaluation model. This integration not only facilitates a comprehensive evaluation of each indicator but also can scientifically determine the weights of each indicator through the Analytic Hierarchy Process to ensure the rationality and accuracy of decision-making. In this way, the one-sidedness that may be caused by a single indicator is effectively eliminated, enabling the production scheduling decision to more comprehensively and objectively reflect the actual situation.

[0082] Compared with the prior art, the model construction module determines weights by introducing the analytic hierarchy process, enabling the relative importance of various indicators to be scientifically quantified. This method is more rigorous than traditional empirical judgment or simple averaging methods and can better adapt to complex production environments, improving the credibility and practicality of the evaluation model. This scientific way of weight allocation enables production scheduling decisions to be flexibly adjusted in the face of different production conditions, enhancing the overall system's response ability. In this solution, the adoption of the model construction module can significantly promote the intelligent and systematic development of the overall solution. By establishing a comprehensive production evaluation model, the system can monitor and evaluate key indicators in the production process in real time, thus providing a solid data foundation and decision-making support for the real-time scheduling adjustment module. This comprehensive evaluation method not only improves production efficiency but also reduces resource waste, promotes the realization of intelligent manufacturing, and lays a foundation for the sustainable development of enterprises.

[0083] The real-time scheduling adjustment module is used to compare the comprehensive evaluation index with a preset evaluation threshold, and according to the comparison result, adjust the production scheduling in real time. At the same time, a blockchain platform is deployed to record the production scheduling data generated by the edge computing nodes;

[0084] In this embodiment, the specific logic for comparing the comprehensive evaluation index with the preset evaluation threshold is as follows:

[0085] When QS≥QY, continue with the current scheduling plan, check the operating status of the equipment, and perform necessary maintenance to ensure the long-term efficient operation of the equipment;

[0086] When QS < QY, adjust the production parameters, specifically including: adjusting the heating settings of the melting furnace, increasing the output power, raising or lowering the temperature of the liquid metal according to the temperature reference threshold to ensure good metal fluidity during the casting process; checking and adjusting the hydraulic system of the casting equipment, raising or lowering the mold pressure to ensure that the metal can completely fill the mold and reduce casting defects; extending or shortening the smelting time according to the actual production situation and metal composition requirements to ensure that the quality and performance of the metal meet the standards; adjusting production operations, using energy-saving equipment to ensure that energy consumption is reduced while meeting production requirements; re-evaluating raw material suppliers and selecting materials with high cost performance to reduce production costs;

[0087] Where QS is the comprehensive evaluation index and QY is the preset evaluation threshold.

[0088] Deploy a blockchain platform to record the production scheduling data generated by the edge computing nodes. The production scheduling data includes casting evaluation index, energy consumption index, and cost-benefit index to ensure the transparency and immutability of data sharing. The blockchain uses Hyperledger Fabric technology for data recording and sharing.

[0089] The advantage of the real-time scheduling adjustment module is that it can achieve dynamic optimization and adjustment of production scheduling by comparing the comprehensive evaluation index with the preset evaluation threshold in real time. This real-time nature enables the system to respond quickly to changes in production conditions, thus achieving a better balance among production efficiency, product quality, and resource utilization. At the same time, by deploying blockchain technology, the recording and tracking of real-time scheduling data are tamper-proof and highly transparent, ensuring the reliability of the production process and the credibility of the data.

[0090] Compared with the prior art, the real-time scheduling adjustment module significantly improves the flexibility and accuracy of scheduling decisions. Traditional systems usually rely on preset fixed parameters or post-event analysis and cannot quickly respond to sudden changes in the production process. However, this module can effectively avoid resource waste and production problems caused by delayed or inaccurate decisions through real-time perception and adjustment. In addition, the introduction of blockchain technology ensures the security and transparency of data sharing, reducing the risk of data tampering and disputes compared with traditional centralized data management methods. In this solution, the real-time scheduling adjustment module is an important execution link for intelligent production scheduling. Through real-time evaluation and adjustment measures, it ensures that the production plan can dynamically adapt to changes in actual production conditions. It provides direct guarantee for the efficient operation of the system and forms a closed-loop feedback mechanism with the edge computing module, index generation module, and model construction module, comprehensively improving the intelligent level and execution efficiency of the entire solution. The introduction of this module makes the steelmaking and continuous casting production processes more flexible and precise, laying a foundation for the enterprise to achieve high-quality and low-cost production goals.

[0091] Please refer to Figure 2 , a multi-layer intelligent scheduling optimization method for steelmaking continuous casting based on edge computing, the specific steps include:

[0092] Step 1: Deploy edge computing nodes on the steelmaking and continuous casting equipment to collect the environmental parameters and production parameters of the current task in real time. The environmental parameters include liquid metal temperature, mold pressure, and smelting time, and the production parameters include the production cost and benchmark production cost of the current task, the energy consumed by the current task production, and the target energy consumption.

[0093] Step 2: After dimensionless processing of the liquid metal temperature, mold pressure, and smelting time, generate a casting evaluation index. After dimensionless processing of the energy consumed by the current task production and the target energy consumption, generate an energy consumption index. After dimensionless processing of the production cost and benchmark production cost of the current task, generate a cost-benefit index.

[0094] Step 3: Combine the casting evaluation index, energy consumption index, and cost-benefit index to construct a comprehensive production evaluation model. Determine the weights within the model through the analytic hierarchy process, and use the comprehensive production evaluation model to generate the comprehensive evaluation index for the current production task;

[0095] Step 4: Compare the comprehensive evaluation index with the preset evaluation threshold. According to the comparison results, adjust the production schedule in real time, and at the same time deploy a blockchain platform to record the production schedule data generated by the edge computing nodes.

[0096] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to obtain a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0097] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. Those skilled in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in this article can be implemented by electronic hardware, or by the combination of computer software and electronic hardware. Whether these functions are executed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0098] The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units. They can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0099] The above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in this application, and all should be covered by the protection scope of this application.

Claims

1. A multi-layer intelligent scheduling optimization system for steelmaking and continuous casting based on edge computing, characterized in that: Specifically include: The edge computing deployment module is used to deploy edge computing nodes on steelmaking and continuous casting equipment to collect the environmental parameters and production parameters of the current task in real time. The environmental parameters include liquid metal temperature, mold pressure and smelting time. The production parameters include the production cost and benchmark production cost of the current task, the energy consumed by the current task production and the target energy consumption. An index generation module is used to generate a casting evaluation index after dimensionally processing the liquid metal temperature, mold pressure and smelting time, generate an energy consumption index after dimensionally processing the energy consumed by the current task production and the target energy consumption, and generate a cost-effectiveness index after dimensionally processing the production cost of the current task and the benchmark production cost; The model building module is used to combine the casting evaluation index, energy consumption index and cost-effectiveness index to build a comprehensive production evaluation model, determine the weights in the model through the hierarchical analysis method, and use the comprehensive production evaluation model to generate a comprehensive evaluation index for the current production task; The real-time scheduling adjustment module is used to compare the comprehensive evaluation index with the preset evaluation threshold, and adjust the production scheduling in real time according to the comparison results. At the same time, the blockchain platform is deployed to record the production scheduling data generated by the edge computing nodes.

2. The steelmaking and continuous casting multi-layer intelligent scheduling optimization system based on edge computing according to claim 1 is characterized in that: Place the thermocouple in the area of ​​​​the molten metal in the furnace to collect the temperature of the liquid metal and record the liquid metal temperature as T liquid ; Use a pressure sensor to monitor the pressure in the mold in real time, and record the mold pressure as P mold ; Use a timer to record the duration of the smelting process and record the smelting time as t furnace ; Obtain the production cost and benchmark production cost of the current task. The production cost of the current task is the total cost consumed in the production process, including raw materials, energy and labor costs. The benchmark production cost refers to the estimated cost under normal production conditions. The production cost of the current task is recorded as C prod , let the base production cost be C baseline ; Obtain the energy consumed by the current task production and the target energy consumption. The target energy consumption refers to the expected energy consumption value in order to achieve the production target under the set production conditions, and the energy consumed by the current task production is recorded as E consumed , the target energy consumption is recorded as E target .

3. The steelmaking and continuous casting multi-layer intelligent scheduling optimization system based on edge computing according to claim 2 is characterized in that: The casting evaluation index is generated based on the following formula: Cas is the casting assessment index, T liquid is the liquid metal temperature, T ref is the reference value of liquid metal temperature, P mold is the mold pressure, P ref is the reference value of mold pressure, t furnace is the smelting time, t ref is the reference value of smelting time, α, β and γ are preset proportional coefficients, α>β>γ>0, and α+β+γ=1; The energy consumption index is generated based on the following formula: Where, Eef is the energy consumption index, E target is the target energy consumption, E consumed The energy consumed to produce the current task; The cost-effectiveness index is generated based on the following formula: In the formula, Ben is the cost-effectiveness index, C baseline is the base production cost, C prod Represents the production cost of the current task.

4. The steelmaking and continuous casting multi-layer intelligent scheduling optimization system based on edge computing according to claim 1 is characterized in that: The casting evaluation index, energy consumption index and cost-effectiveness index are combined to construct a comprehensive production evaluation model. The model expression is as follows: Where QS is the comprehensive evaluation index, Cas is the casting evaluation index, Eef is the energy consumption index, Ben is the cost-effectiveness index, ω1, ω2 and ω3 are the weights of the casting evaluation index, energy consumption index and cost-effectiveness index, respectively, which are determined according to the hierarchical analysis method.

5. The steelmaking and continuous casting multi-layer intelligent scheduling optimization system based on edge computing according to claim 4 is characterized in that: The specific logic of determining weights through the hierarchical analysis method is: The three indicators of casting evaluation index, energy consumption index and cost-effectiveness index are marked, and the relative importance between them is determined by the nine-scale method to construct a judgment matrix, in which the casting evaluation index is marked as 1, the energy consumption index is marked as 2, and the cost-effectiveness index is marked as 3. The constructed judgment matrix is: Where f and v both represent indexes of the exponent, and f∈[1,3], v∈[1,3], b fv Indicates the importance of the index with index f relative to the index with index v. The importance is scaled from 1 to 9, and b fv The larger the value, the more important the index with index f is compared to the index with index v, and Each element value in the judgment matrix is ​​divided by the sum of its columns to obtain a normalized judgment matrix. The mean of the element values ​​in each row of the normalized judgment matrix is ​​calculated, and the mean of the element values ​​in the first row is used as the weight of the casting evaluation index, the mean of the element values ​​in the second row is used as the weight of the energy consumption index, and the mean of the element values ​​in the third row is used as the weight of the cost-effectiveness index. With the constraint that the sum of the scaled values ​​is equal to 1, the three weights are scaled in equal proportions, and the scaled weights are used as the proportional coefficients of the corresponding indexes.

6. The steelmaking and continuous casting multi-layer intelligent scheduling optimization system based on edge computing according to claim 1 is characterized in that: The comprehensive evaluation index is compared with the preset evaluation threshold, based on the following specific logic: When QS ≥ QY, continue the current scheduling plan, check the operating status of the equipment, and perform necessary maintenance to ensure long-term and efficient operation of the equipment; When QS < QY, adjust the production parameters, specifically including: adjusting the heating settings of the smelting furnace to increase the output power, increasing or decreasing the temperature of the liquid metal according to the temperature reference threshold to ensure good metal fluidity during the casting process; checking and adjusting the hydraulic system of the casting equipment to increase or decrease the mold pressure to ensure that the metal can completely fill the mold and reduce casting defects; extending or shortening the smelting time according to the actual production situation and metal composition requirements to ensure that the quality and performance of the metal meet the standards; adjusting the production operation and using energy-saving equipment to reduce energy consumption while meeting the production requirements; re-evaluating the raw material suppliers and selecting materials with high cost performance to reduce the production cost; In the formula, QS is the comprehensive evaluation index, and QY is the preset evaluation threshold.

7. The steelmaking and continuous casting multi-layer intelligent scheduling optimization system based on edge computing according to claim 1 is characterized in that: Deploy a blockchain platform to record the production scheduling data generated by the edge computing nodes. The production scheduling data includes the casting evaluation index, energy consumption index, and cost-benefit index to ensure the transparency and immutability of data sharing. The blockchain uses Hyperledger Fabric technology for data recording and sharing.

8. A multi-layer intelligent scheduling optimization method for steelmaking and continuous casting based on edge computing, characterized by: The above-mentioned multi-layer intelligent scheduling optimization method for steelmaking continuous casting based on edge computing is obtained by executing the multi-layer intelligent scheduling optimization system for steelmaking continuous casting based on edge computing described in any one of claims 1-7, specifically including: Step 1: Deploy edge computing nodes on the steelmaking and continuous casting equipment to collect the environmental parameters and production parameters of the current task in real time. The environmental parameters include the liquid metal temperature, mold pressure, and smelting time, and the production parameters include the production cost and benchmark production cost of the current task, the energy consumed by the current task production, and the target energy consumption; Step 2: After dimensionless processing of the liquid metal temperature, mold pressure, and smelting time, generate a casting evaluation index. After dimensionless processing of the energy consumed by the current task production and the target energy consumption, generate an energy consumption index. After dimensionless processing of the production cost and benchmark production cost of the current task, generate a cost-benefit index; Step 3: Combine the casting evaluation index, energy consumption index, and cost-benefit index to construct a comprehensive production evaluation model. Determine the weights within the model through the analytic hierarchy process, and use the comprehensive production evaluation model to generate the comprehensive evaluation index of the current production task; Step 4: Compare the comprehensive evaluation index with the preset evaluation threshold. According to the comparison results, adjust the production scheduling in real time, and at the same time deploy a blockchain platform to record the production scheduling data generated by the edge computing nodes.

Images