Intelligent scheduling method for molten iron tank car and related equipment
By using intelligent scheduling methods, combined with convolutional neural networks and Q-learning algorithms, the speed of molten iron ladle cars and the ladle allocation strategy are optimized, which solves the supply and demand imbalance problem caused by traditional manual scheduling and improves the efficiency of molten iron transportation and production stability.
Patent Information
- Application Number
- CN202411241238.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-05
- Publication Date
- 2024-11-26
AI Technical Summary
The reliance on manual scheduling in traditional molten iron transportation leads to a mismatch between the production cycles of ironmaking and steelmaking processes, resulting in an imbalance between supply and demand, which affects production efficiency and energy consumption.
An intelligent scheduling method is adopted to optimize molten iron transportation by acquiring production task information, molten iron content, and tank car location, and using convolutional neural networks and Q-learning algorithms to adjust tank car speed and tank allocation strategies.
It improved transportation efficiency and production process coordination, reduced energy consumption, ensured supply and demand balance, and enhanced the continuity and stability of production.
Smart Images

Figure CN119026871A_ABST
Abstract
Description
Technical Field
[0001] The present specification relates to the field of metal smelting, and more specifically, the present application relates to an intelligent scheduling method for molten iron tank cars and related equipment. Background Art
[0002] In the traditional steel production process, the transportation of molten iron between iron mills and steel mills relies on manual scheduling, and the scheduling efficiency of molten iron tank cars is usually limited by manual experience and simple planning control. Due to the different production cycles and rhythms of ironmaking and steelmaking processes, manual scheduling methods often cannot respond to changes in production demand in a timely manner, resulting in an imbalance in the supply and demand of molten iron, which may cause the steel mill to shut down due to insufficient molten iron, or waste energy due to excessive backlog of molten iron. In addition, the adjustment of the tank car speed during the transportation of molten iron is not flexible enough, resulting in long transportation time or increased energy consumption, affecting the overall production efficiency. In order to solve at least some of the above problems, it is urgent to provide an intelligent scheduling method for molten iron tank cars. Summary of the invention
[0003] A series of simplified concepts are introduced in the Summary of the Invention section, which will be further described in detail in the Detailed Description of the Invention section. The Summary of the Invention section of this application does not mean to attempt to define the key features and essential technical features of the claimed technical solution, nor does it mean to attempt to determine the scope of protection of the claimed technical solution.
[0004] In the first aspect, the present application proposes an intelligent dispatching method for molten iron tank cars, comprising:
[0005] Obtain the current production task type information of the factory;
[0006] Determine an intermediate molten iron content range based on the above production type information, wherein the above intermediate molten iron content range is the molten iron content range on the transportation track between the ironmaking plant and the steelmaking plant;
[0007] Get the iron content information of all the ladles in the ironworks;
[0008] Get the iron content information of all the ladles in the steel mill;
[0009] The target moving speed of each of the above-mentioned molten iron ladle cars is adjusted based on the position information of all the molten iron ladle cars in transit, the current moving speed of all the molten iron ladle cars in transit, the above-mentioned intermediate molten iron content range, the molten iron content information of all the above-mentioned iron plant ladles, and the molten iron content information of all the above-mentioned steel plant ladles.
[0010] In a feasible implementation manner, the ironworks molten iron ladle and the steelworks molten iron include a pouring molten iron ladle, and the method for determining the content information of the pouring molten iron ladle specifically includes:
[0011] Obtain image information of the ladle being poured;
[0012] The above-mentioned image information of the pouring molten iron ladle is input into the intelligent recognition model to obtain the content information of the pouring molten iron ladle.
[0013] In a feasible implementation, the intelligent recognition model includes an input layer, a convolutional neural network feature extraction module, a fully connected layer, a regression module and an output layer. The convolutional neural network feature extraction module includes a first convolutional layer, a second convolutional layer, a third convolutional layer and a pooling layer. The first convolutional layer uses 32 3x3 convolution kernels, the second convolutional layer uses 64 3x3 convolution kernels, the third convolutional layer uses 128 3x3 convolution kernels, the pooling layer is a maximum pooling layer, the fully connected layer includes a first fully connected layer and a second fully connected layer, the size of the first fully connected layer is 1024, and the activation function is the ReLU function. The size of the second fully connected layer is 512, and the activation function is the ReLU activation function. The regression layer is a regression layer with a custom loss function.
[0014] In a feasible implementation manner, the target moving speed of each of the above-mentioned molten iron ladle vehicles is adjusted based on the position information of all the molten iron ladle vehicles in transit, the current moving speed of all the molten iron ladle vehicles in transit, the above-mentioned intermediate molten iron content range, the molten iron content information of all the above-mentioned iron plant ladles, and the molten iron content information of all the above-mentioned steel plant ladles, including:
[0015] Initialize a Q table, wherein the Q table is used to store the Q value of each state-action, and the dimension of the table is Q(S,A), wherein S is a state set, and A is an action set, wherein the state set includes the position information of all the molten iron ladle cars in transit, the current moving speed of all the molten iron ladle cars in transit, the intermediate molten iron content range, the molten iron content information of all the molten iron ladles of the iron plant, and the molten iron content information of all the molten iron ladles of the steel plant, and the action set includes acceleration, deceleration, and keeping the speed unchanged;
[0016] Set the learning rate, discount factor, and exploration rate;
[0017] Set the reward function;
[0018] Observe the current state S t ;
[0019] According to the current state, the target action is selected using the ε-greedy strategy:
[0020] Let the molten iron ladle perform the above target actions and observe the system's feedback;
[0021] After executing the action, get the new state S (t+1) , and calculate the reward R of the current action according to the reward function t ;
[0022] Use the Q-learning update rule to update the Q values in the Q table:
[0023]
[0024] Among them, α is the learning rate, γ is the discount factor, and A' is the new action;
[0025] Repeat the process of observing the state to update the Q value until the Q value converges or has been repeated a preset number of times, and output the target moving speed of each of the above-mentioned molten iron tank cars.
[0026] In a feasible implementation, it also includes:
[0027] Obtaining first remaining content information of a molten iron ladle being poured out of a molten iron ladle in a steel plant;
[0028] In the case where the first remaining content information is greater than the current capacity limit of the molten iron tank car, generating a tank transportation instruction;
[0029] Calculate the floating value of the intermediate molten iron content range based on the above tank transportation instructions;
[0030] The tank division strategy is determined based on the floating value of the above intermediate molten iron content range and the molten iron demand of different steel plant workshops.
[0031] In a feasible implementation manner, the tank division strategy is determined based on the floating value of the intermediate molten iron content range and the molten iron demand of different steel mill workshops, including:
[0032] Initialize the population and individuals, where the population has each possible tank allocation strategy, and the individual identifies the amount of molten iron allocated to each molten iron tank car;
[0033] The fitness function is defined based on the hot metal demand target of different steel mill workshops, the intermediate hot metal content balance target and the minimization of transportation time cost target;
[0034] A preset number of genetic operations are performed based on the above fitness function to obtain the above tank distribution strategy.
[0035] In a feasible implementation, the above fitness function is:
[0036] F=αF 需求 +βF 含量 +γF 运输
[0037]
[0038] F 含量 =1 / (1+|intermediate molten iron content range floating value-actual distribution content|)
[0039] F 运输 = 1 / (1+total shipping time and cost)
[0040] n is the number of workshops in the steel plant, the allocation amount i and the demand amount i represent the amount of molten iron obtained by the i-th workshop and its demand, respectively, and α, β and γ are weight coefficients used to balance the priority of demand satisfaction, intermediate molten iron content and transportation time.
[0041] In the second aspect, the present application proposes an intelligent dispatching device for a molten iron tank car, comprising:
[0042] The first acquisition unit is used to acquire the current production task type information of the factory area;
[0043] A determination unit, configured to determine an intermediate molten iron content range based on the production type information, wherein the intermediate molten iron content range is a molten iron content range on a transportation track between an ironmaking plant and a steelmaking plant;
[0044] The second acquisition unit is used to acquire the molten iron content information of all the ladles in the ironworks in the ironmaking plant;
[0045] The third acquisition unit is used to obtain the molten iron content information of all steel ladles in the steelmaking plant;
[0046] An adjustment unit is used to adjust the target moving speed of each of the above-mentioned molten iron ladle cars based on the position information of all the molten iron ladle cars in transit, the current moving speed of all the molten iron ladle cars in transit, the above-mentioned intermediate molten iron content range, the molten iron content information of all the above-mentioned iron plant ladles, and the molten iron content information of all the above-mentioned steel plant ladles.
[0047] In a third aspect, an electronic device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor is used to implement the steps of the intelligent dispatching method for molten iron tank cars as described in any one of the first aspects above when executing the computer program stored in the memory.
[0048] In a fourth aspect, the present application further proposes a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the intelligent scheduling method for molten iron tank cars of any one of the first aspects is implemented.
[0049] In summary, the intelligent scheduling method of molten iron tanker proposed in the embodiment of the present application includes: obtaining the current production task type information of the plant; determining the intermediate molten iron content range based on the above production type information, wherein the above intermediate molten iron content range is the molten iron content range on the transportation track between the ironmaking plant and the steelmaking plant; obtaining the molten iron content information of all ironworks ladles in the ironmaking plant; obtaining the molten iron content information of all steelworks ladles in the steelmaking plant; adjusting the target moving speed of each of the above molten iron tanker based on the position information of all molten iron tanker in transit, the current moving speed of all molten iron tanker in transit, the above intermediate molten iron content range, the molten iron content information of all ironworks ladles, and the molten iron content information of all steelworks ladles. By automatically obtaining the production task type information, the real-time content information of the molten iron ladle, and combining the dynamic content of the molten iron on the transportation track, the system can intelligently adjust the scheduling speed and strategy of the molten iron tanker, significantly improving the transportation efficiency and the coordination of the production process. This embodiment ensures that a reasonable amount of molten iron is maintained on the transport track by comprehensively considering the molten iron content of the ironmaking plant and the steelmaking plant, as well as the intermediate molten iron content range, to avoid insufficient supply or excessive backlog of molten iron, further optimize the balance between supply and demand, and reduce the risk of production fluctuations. By intelligently adjusting the target speed of the molten iron tank car, the system can accelerate or decelerate at the appropriate time, avoid excessive acceleration or invalid deceleration operations, reduce energy consumption during transportation, and improve the energy utilization rate of the overall system. The system can dynamically adjust the speed and scheduling strategy of the tank car according to the actual molten iron demand and the transportation status of the tank car, with rapid and flexible response, and can meet the molten iron demand of the steelmaking plant in a timely manner, improving the continuity and stability of production. BRIEF DESCRIPTION OF THE DRAWINGS
[0050] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present specification. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:
[0051] Figure 1 A schematic diagram of a process of intelligent scheduling method for molten iron tank cars provided in an embodiment of the present application;
[0052] Figure 2 A schematic diagram of the structure of an intelligent dispatching device for a molten iron tank car provided in an embodiment of the present application;
[0053] Figure 3 A schematic diagram of the structure of an intelligent dispatching electronic device for a molten iron tank car provided in an embodiment of the present application. DETAILED DESCRIPTION
[0054] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.
[0055] See also Figure 1 , which is a schematic diagram of a process of intelligent scheduling method for molten iron tank cars provided in an embodiment of the present application, which may specifically include:
[0056] S110, obtaining the current production task type information of the factory;
[0057] For example, the current production task type information of the plant is first obtained. This information may include the blast furnace iron production plan of the ironmaking plant and the molten iron demand plan of the steelmaking plant. Based on these production task types, the system can determine the demand for molten iron and the transportation scheduling requirements.
[0058] S120, determining an intermediate molten iron content range based on the production type information, wherein the intermediate molten iron content range is a molten iron content range on the transportation track between the ironmaking plant and the steelmaking plant;
[0059] For example, based on the production type information obtained in step S110, the system calculates the intermediate molten iron content range on the transport track between the ironmaking plant and the steelmaking plant. This range represents the minimum and maximum amount of molten iron on the transport track, ensuring that the transportation of molten iron will not lead to production stagnation or waste of resources due to imbalance between supply and demand.
[0060] S130, obtaining the molten iron content information of all the ladles in the ironworks;
[0061] For example, by monitoring the liquid level or molten iron content of all ladles in the ironmaking plant, the current molten iron storage situation of the ironmaking plant can be obtained. This information can be collected in real time by sensors to determine whether it is necessary to arrange a tank truck to transport the molten iron as soon as possible.
[0062] S140, obtaining the molten iron content information of all the ladles in the steel mill;
[0063] For example, the molten iron content information of all the ladles in the steel mill is obtained to reflect the current molten iron demand of the steel mill. If the molten iron level of the ladles is low, it means that the steel mill is in urgent need of molten iron replenishment.
[0064] S150. Adjust the target moving speed of each of the above-mentioned molten iron ladle cars based on the position information of all the molten iron ladle cars in transit, the current moving speed of all the molten iron ladle cars in transit, the above-mentioned intermediate molten iron content range, the molten iron content information of all the above-mentioned iron plant ladles, and the molten iron content information of all the above-mentioned steel plant ladles.
[0065] For example, the system integrates the location information and current moving speed of all molten iron tankers in transit, and combines the intermediate molten iron content range obtained in the previous step, the molten iron content information of the ironmaking plant and the steelmaking plant, and intelligently adjusts the target moving speed of each molten iron tanker. For example, when the amount of molten iron on the transport track approaches the upper limit, the system will reduce the speed of the molten iron tanker to prevent excessive molten iron from entering the steelmaking plant; when the liquid level of the molten iron ladle in the steelmaking plant is low, the system will speed up the transportation speed to ensure timely supply.
[0066] In summary, by automatically acquiring production task type information, real-time content information of molten iron ladle, and combining the dynamic content of molten iron on the transport track, the system can intelligently adjust the dispatching speed and strategy of molten iron tank car, significantly improving the transportation efficiency and coordination of production process. This embodiment ensures that a reasonable amount of molten iron is maintained on the transport track by comprehensively considering the molten iron content of the ironmaking plant and the steelmaking plant, as well as the intermediate molten iron content range, to avoid the shortage of molten iron or excessive backlog, further optimize the balance of supply and demand, and reduce the risk of production fluctuations. By intelligently adjusting the target speed of the molten iron tank car, the system can accelerate or decelerate at the appropriate time, avoid over-acceleration or invalid deceleration operations, reduce energy consumption during transportation, and improve the energy utilization rate of the overall system. The system can dynamically adjust the speed and dispatching strategy of the tank car according to the actual molten iron demand and the transportation status of the tank car, respond quickly and flexibly, and can meet the molten iron demand of the steelmaking plant in time, improving the continuity and stability of production.
[0067] In some examples, the ironworks molten iron ladle and the steelworks molten iron include a pouring molten iron ladle, and the method for determining the content information of the pouring molten iron ladle specifically includes:
[0068] Obtain image information of the ladle being poured;
[0069] The above-mentioned image information of the pouring molten iron ladle is input into the intelligent recognition model to obtain the content information of the pouring molten iron ladle.
[0070] For example, in an ironworks or steelworks, when the ironworks ladle or steelworks ladle is in a dumping state, the system first obtains real-time image information of the ladle being dumped. These image information are collected by a monitoring camera installed above or near the ladle. The image may include visual information such as the liquid level height and tilt angle of the molten iron in the ladle, reflecting the remaining content of the molten iron in the current ladle.
[0071] After acquiring the real-time ladle image information, the system inputs this image information into a pre-trained intelligent recognition model. Based on deep learning or other image processing technologies, the model can automatically analyze key features in the image, such as the ladle's liquid level and the flow state of the molten iron.
[0072] The core function of the intelligent recognition model is to extract features from the image and calculate the content information of the pouring ladle based on these features. The model learns how to accurately estimate the volume and liquid level of the remaining molten iron from images of molten iron ladles in different pouring states through a large amount of training data.
[0073] Based on the output of the intelligent recognition model, the system finally obtains the content information of the ladle being dumped, that is, the amount of molten iron remaining in the current ladle, which provides a key basis for the subsequent generation of tank transportation instructions and molten iron tanker dispatch.
[0074] In some examples, the intelligent recognition model includes an input layer, a convolutional neural network feature extraction module, a fully connected layer, a regression module and an output layer. The convolutional neural network feature extraction module includes a first convolutional layer, a second convolutional layer, a third convolutional layer and a pooling layer. The first convolutional layer uses 32 3x3 convolution kernels, the second convolutional layer uses 64 3x3 convolution kernels, the third convolutional layer uses 128 3x3 convolution kernels, the pooling layer is a maximum pooling layer, the fully connected layer includes a first fully connected layer and a second fully connected layer, the size of the first fully connected layer is 1024, and the activation function is the ReLU function. The size of the second fully connected layer is 512, and the activation function is the ReLU activation function. The regression layer is a regression layer with a custom loss function.
[0075] In some examples, adjusting the target moving speed of each of the molten iron ladle cars based on the position information of all the molten iron ladle cars in transit, the current moving speed of all the molten iron ladle cars in transit, the intermediate molten iron content range, the molten iron content information of all the iron plant ladles, and the molten iron content information of all the steel plant ladles includes:
[0076] Initialize a Q table, wherein the Q table is used to store the Q value of each state-action, and the dimension of the table is Q(S,A), wherein S is a state set, and A is an action set, wherein the state set includes the position information of all the molten iron ladle cars in transit, the current moving speed of all the molten iron ladle cars in transit, the intermediate molten iron content range, the molten iron content information of all the molten iron ladles of the iron plant, and the molten iron content information of all the molten iron ladles of the steel plant, and the action set includes acceleration, deceleration, and keeping the speed unchanged;
[0077] Set the learning rate, discount factor, and exploration rate;
[0078] Set the reward function;
[0079] Observe the current state S t ;
[0080] According to the current state, the target action is selected using the ε-greedy strategy:
[0081] Let the molten iron ladle perform the above target actions and observe the system's feedback;
[0082] After executing the action, get the new state S (t+1) , and calculate the reward R of the current action according to the reward function t ;
[0083] Use the Q-learning update rule to update the Q values in the Q table:
[0084]
[0085] Among them, α is the learning rate, γ is the discount factor, and A' is the new action;
[0086] Repeat the process of observing the state to update the Q value until the Q value converges or has been repeated a preset number of times, and output the target moving speed of each of the above-mentioned molten iron tank cars.
[0087] Illustratively, the embodiment of the present application utilizes the Q-learning algorithm to intelligently schedule and adjust the target moving speed of the molten iron tank car, and continuously optimizes the scheduling strategy by dynamically observing the status information of the tank car and the corresponding feedback.
[0088] Initialize the Q table: First, the system initializes a Q table to store the Q value of each state-action pair. The dimension of the Q table is Q(S,A), where S represents the state set and A represents the action set.
[0089] State set S: includes the location information, current moving speed, intermediate molten iron content range, molten iron content information of all molten iron ladle in transit, and molten iron content information of all ironworks ladles and all steelworks ladles.
[0090] Action set A: includes three actions: acceleration, deceleration and keeping the speed constant. Through these three actions, the system can dynamically adjust the target speed of each molten iron ladle car.
[0091] Set learning rate, discount factor, and exploration rate: The system sets three key parameters for the Q-learning algorithm:
[0092] Learning rate (α): controls the degree of adoption of new information each time the Q value is updated. The larger the value, the faster the system responds to new information.
[0093] Discount factor (γ): used to measure the weight of future rewards. The larger the value, the more the system focuses on long-term returns.
[0094] Exploration rate (ε): used to balance the relationship between exploration and utilization. The ε-greedy strategy determines whether the system chooses the current optimal action or explores new actions in each state.
[0095] Set the reward function: The reward function is used to evaluate the impact of each action on the system and guide the update of the Q value:
[0096] When the molten iron tanker delivers molten iron to the steel plant in a timely and safe manner as planned, and keeps the intermediate molten iron content within a reasonable range, the system will give positive rewards.
[0097] If the speed of the molten iron tank car is adjusted too quickly or too slowly, resulting in an imbalance between supply and demand or a backlog of molten iron, the system will give a negative reward.
[0098] Observe the current state St: At each moment, the system observes the current state St, which consists of the position information of the molten iron tank car, the current moving speed, the intermediate molten iron content range, the molten iron content information of all ironworks ladles, and the molten iron content information of all steelworks ladles. These state information are the basis for the system to judge and select actions.
[0099] Use ε-greedy strategy to select target action: The system uses ε-greedy strategy to select target action based on the current state St:
[0100] Perform random exploration with probability ε and select new actions to try (such as speeding up, slowing down, or keeping the speed constant).
[0101] The action with the largest Q value in the current Q table is selected with probability 1-ε, which is the optimal action considered by the system.
[0102] Let the ladle truck perform the above target action and observe the system's feedback: After selecting the target action, the system instructs the ladle truck to perform the action (such as accelerating, decelerating, or keeping the speed unchanged). After executing the action, the system will observe the feedback of the molten iron transportation process and evaluate the effectiveness of the action.
[0103] After executing the action, the new state S(t+1) is obtained, and the reward Rt of the current action is calculated based on the reward function: After the tank car completes the target action, the system obtains the new state S(t+1), that is, the new information such as the position and speed of the molten iron tank car after the action is executed. Based on the new state and reward function, the system calculates the reward Rt of this action to guide the update of the Q table.
[0104] Use the Q-learning update rule to update the Q value in the Q table: Use the Q-learning algorithm's update rule to update the Q value in the Q table:
[0105]
[0106] Among them, α is the learning rate, γ is the discount factor, and A' is the new action, that is, the action that the tanker may take next.
[0107] After the Q table is updated, the tank truck scheduling strategy will be closer to the optimal solution.
[0108] Repeat the process of observing the state to updating the Q value until the Q value converges or has been repeated to a preset number of times: the system continues to repeat the process of observing the state, selecting actions, executing actions, and updating the Q value until the Q value in the Q table converges, that is, the tank truck scheduling strategy tends to be stable, or the preset number of training times is reached.
[0109] Output the target moving speed of each of the above-mentioned molten iron tank cars: After the Q value converges, the system outputs the target moving speed of each molten iron tank car to ensure that it is transported at the optimal speed to meet production needs while maximizing transportation efficiency and energy utilization.
[0110] Through the embodiment of the present application, the system dynamically adjusts the target moving speed of the molten iron tank car based on the Q-learning algorithm. This process gradually optimizes the tank car scheduling strategy through repeated learning and updating, so that the molten iron transportation can efficiently and balancedly meet the needs of the steel plant, avoid resource waste, and maximize production efficiency.
[0111] In some examples, this also includes:
[0112] Obtaining first remaining content information of a molten iron ladle being poured out of a molten iron ladle in a steel plant;
[0113] In the case where the first remaining content information is greater than the current capacity limit of the molten iron tank car, generating a tank transportation instruction;
[0114] Calculate the floating value of the intermediate molten iron content range based on the above tank transportation instructions;
[0115] The tank division strategy is determined based on the floating value of the above intermediate molten iron content range and the molten iron demand of different steel plant workshops.
[0116] Exemplarily, the system first obtains the first remaining content information of the molten iron ladle being dumped in the ironmaking plant. This information is obtained through real-time monitoring equipment (such as a sensor or an image recognition system), indicating the volume or liquid level of the remaining molten iron in the molten iron ladle. This information is directly related to whether the system needs to perform tank separation operation later.
[0117] When the system detects that the first remaining content information is greater than the capacity limit of the current molten iron ladle, it means that a single molten iron ladle cannot fully carry the molten iron in the ladle. In this case, the system automatically generates a tank transportation instruction. This instruction determines that the molten iron will be distributed to multiple molten iron ladle cars to avoid overload transportation.
[0118] For example, if the molten iron currently being dumped contains 70 tons of molten iron, and the maximum carrying capacity of the current tank truck is 50 tons, the system will generate a tank transportation instruction to allocate the remaining molten iron to other available tank trucks.
[0119] After generating the tank-by-tank transport instruction, the system needs to update the intermediate molten iron content range between the ironworks and the steelworks. Tank-by-tank transport means that the total amount of molten iron on the transport track will change, so a floating value needs to be calculated to reflect this change.
[0120] The floating value can be dynamically calculated based on the amount of molten iron after tank separation, the real-time transportation status of the tank car, and the molten iron content on the existing transportation track. The larger the floating value, the higher the molten iron content in the middle, and the system may need to slow down the transportation rhythm; the smaller the floating value, the insufficient supply of molten iron, and the system should speed up transportation to meet demand.
[0121] After calculating the floating value of the intermediate molten iron content range, the system determines the final tank allocation strategy based on the molten iron demand of different steel mill workshops. The tank allocation strategy aims to ensure that each steel mill workshop can obtain the required molten iron in a timely manner by reasonably allocating the molten iron in the ladles.
[0122] The system will give priority to workshops with higher molten iron demand and allocate more molten iron according to their demand.
[0123] At the same time, combined with the floating value of the intermediate molten iron content, the system will adjust the transportation order and speed of the tank trucks to ensure the rational distribution of molten iron among different workshops and the balance of transportation rhythm.
[0124] Example applications:
[0125] For example, a ladle in an ironmaking plant is being dumped, and the current remaining molten iron is 80 tons, while the available molten iron tankers A and B can only carry 50 tons and 30 tons respectively. The system will first obtain the first remaining content information of the ladle, and generate a tank transportation instruction to distribute the molten iron to tankers A and B respectively.
[0126] Subsequently, the system recalculates the floating value of the intermediate molten iron content range based on the generated tank division instructions. If the floating value is large, it means that the intermediate molten iron content is close to the upper limit, and the tank truck transportation speed may be reduced; if the floating value is small, it means that the molten iron supply is insufficient, and the system will speed up the transportation.
[0127] Finally, the system determines the tank distribution strategy based on the molten iron demand of different steel mill workshops. For example, if workshop 1 urgently needs to replenish 50 tons of molten iron and workshop 2 needs 30 tons of molten iron, the system will distribute it according to the workshop needs and adjust the transportation route and scheduling strategy of the tank truck to ensure the balance between supply and demand.
[0128] The embodiment of the present application performs real-time monitoring of the molten iron ladle being dumped, combines the capacity limitation of the current molten iron tank truck, intelligently generates tank division transportation instructions, and determines the tank division strategy according to the floating value of the intermediate molten iron content range and the molten iron demand of the steel plant workshop, thereby optimizing the molten iron distribution and transportation process and improving the efficiency and flexibility of the entire production system.
[0129] In some examples, the tank division strategy is determined based on the floating value of the intermediate molten iron content range and the molten iron demand of different steel mill workshops, including:
[0130] Initialize the population and individuals, where the population has each possible tank allocation strategy, and the individual identifies the amount of molten iron allocated to each molten iron tank car;
[0131] The fitness function is defined based on the hot metal demand target of different steel mill workshops, the intermediate hot metal content balance target and the minimization of transportation time cost target;
[0132] A preset number of genetic operations are performed based on the above fitness function to obtain the above tank distribution strategy.
[0133] In some examples, the fitness function is:
[0134] F=αF 需求 +βF 含量 +γF 运输
[0135]
[0136] F 含量 =1 / (1+|intermediate molten iron content range floating value-actual distribution content|)
[0137] F 运输 = 1 / (1+total shipping time and cost)
[0138] n is the number of workshops in the steel plant, the allocation amount i and the demand amount i represent the amount of molten iron obtained by the i-th workshop and its demand, respectively, and α, β and γ are weight coefficients used to balance the priority of demand satisfaction, intermediate molten iron content and transportation time.
[0139] For example, first, the system initializes a population, where each individual represents a possible tank allocation strategy. In this process:
[0140] The population is a collection of multiple possible tank distribution schemes, and each individual represents the way in which the molten iron in the ladle is distributed to each molten iron tank car under specific circumstances.
[0141] The individual identifies the amount of molten iron allocated to each ladle car. Each individual represents a ladle allocation scheme. For example, if there is a ladle that needs to be allocated to 3 ladle cars, an individual can be represented as [40, 30, 20], where 40 tons, 30 tons, and 20 tons of molten iron are allocated to the three ladle cars respectively.
[0142] Next, the system defines a fitness function for each individual (i.e., each tank allocation strategy) to evaluate the quality of its tank allocation strategy. The design of the fitness function is based on the following three main goals:
[0143] Steel Plant Workshop Hot Metal Demand Objective: The fitness function first considers the hot metal demand of each steel plant workshop. Each workshop has a specific hot metal demand, and the tank splitting strategy should try to meet these demands. If the demand of a workshop is not met, the fitness value will decrease.
[0144]
[0145] Among them, n is the number of workshops in the steel plant, allocation quantity i is the allocated molten iron quantity of the i-th workshop, and demand quantity i is its corresponding demand quantity.
[0146] Intermediate iron content balance objective: The fitness function also considers the iron content on the transport track between the ironmaking plant and the steelmaking plant. The tank splitting strategy should ensure that the intermediate iron content remains within a reasonable range. If the tank splitting strategy causes the iron content to exceed or fall below the reasonable range, the fitness value will be reduced.
[0147] F 含量 =1 / (1+|intermediate molten iron content range floating value-actual distribution content|)
[0148] Among them, the floating value represents the reasonable range of molten iron content on the current transportation track, and the actual distributed molten iron amount is the molten iron amount distributed through the tank division strategy.
[0149] Minimize transportation time and cost objective: The fitness function considers both transportation time and cost. The tank splitting strategy should minimize the total transportation time and transportation cost of the molten iron tank car. The transportation distance, tank car speed, and route selection all affect the fitness value.
[0150] F 运输 = 1 / (1+total shipping time and cost)
[0151] The total transportation time and transportation cost are determined by the tank car's travel speed, route selection and the amount of molten iron.
[0152] The final fitness function combines the above three objectives:
[0153] F=αF 需求 +βF 含量 +γF 运输
[0154] Among them, α, β, and γ are weight coefficients of different objectives, which are used to balance the relative importance of each objective.
[0155] Based on the fitness function, a preset number of genetic operations are performed to obtain the above tank division strategy: the system optimizes the tank division strategy through selection, crossover and mutation operations in the genetic algorithm. The specific process is as follows:
[0156] Selection: Based on the fitness value, individuals with higher fitness in the population are selected as parents. Common selection methods include roulette wheel selection or tournament selection to ensure that good genes are passed on to the next generation.
[0157] Crossover: Perform a crossover operation on the selected parent generation to generate new offspring. The crossover process simulates genetic recombination in nature and generates a tank-dividing strategy with mixed characteristics. Single-point crossover or multi-point crossover is often used to generate new tank-dividing schemes. For example, two parent individuals [40, 30, 20] and [30, 40, 20] can generate two new individuals [40, 40, 20] and [30, 30, 20] through single-point crossover.
[0158] Mutation: After the generation of offspring individuals, random mutations are performed on the individuals to introduce population diversity and avoid falling into local optimal solutions. The mutation operation randomly changes some molten iron distribution amounts, for example, mutating the individual [40, 30, 20] to [35, 35, 20].
[0159] Termination condition: The system performs a preset number of genetic operations (such as 500 iterations). When the number of iterations reaches the set threshold or the fitness value converges, the genetic operation terminates.
[0160] In a specific scenario, the ironmaking plant has a ladle with 90 tons of molten iron remaining that needs to be distributed to three molten iron tank cars, while the molten iron requirements of each steel plant workshop are 30 tons, 25 tons, and 35 tons respectively. The system initializes a population, and each individual represents a tank distribution strategy. For example, the individual [40, 30, 20] represents the distribution of molten iron to three tank cars. Through the fitness function, the system evaluates whether each tank distribution strategy can meet the needs of the steel plant workshop, maintain a reasonable intermediate molten iron content, and minimize the transportation time.
[0161] After multiple genetic operations, the system finally selects a tank distribution strategy with the highest fitness value, such as [35,25,30]. This strategy can better meet the needs of the workshop and keep the intermediate molten iron content within a reasonable range, while reducing transportation time and cost.
[0162] The embodiment of the present application uses genetic algorithms to continuously optimize the tank division strategy by initializing populations and individuals, combining the molten iron demand targets of different steel mill workshops, the intermediate molten iron content balance target, and the minimization of transportation time cost targets. The tank division strategy finally output can not only meet production needs, but also optimize transportation efficiency and improve the intelligence level of the entire molten iron scheduling system.
[0163] like Figure 2 As shown, this application proposes an intelligent dispatching device for a molten iron tank car, comprising:
[0164] The first acquisition unit is used to acquire the current production task type information of the factory area;
[0165] A determination unit, configured to determine an intermediate molten iron content range based on the production type information, wherein the intermediate molten iron content range is a molten iron content range on a transportation track between an ironmaking plant and a steelmaking plant;
[0166] The second acquisition unit is used to acquire the molten iron content information of all the ladles in the ironworks in the ironmaking plant;
[0167] The third acquisition unit is used to obtain the molten iron content information of all steel ladles in the steelmaking plant;
[0168] An adjustment unit is used to adjust the target moving speed of each of the above-mentioned molten iron ladle cars based on the position information of all the molten iron ladle cars in transit, the current moving speed of all the molten iron ladle cars in transit, the above-mentioned intermediate molten iron content range, the molten iron content information of all the above-mentioned iron plant ladles, and the molten iron content information of all the above-mentioned steel plant ladles.
[0169] In some examples, the ironworks molten iron ladle and the steelworks molten iron include a pouring molten iron ladle, and the method for determining the content information of the pouring molten iron ladle specifically includes:
[0170] Obtain image information of the ladle being poured;
[0171] The above-mentioned image information of the pouring molten iron ladle is input into the intelligent recognition model to obtain the content information of the pouring molten iron ladle.
[0172] In some examples, the intelligent recognition model includes an input layer, a convolutional neural network feature extraction module, a fully connected layer, a regression module and an output layer. The convolutional neural network feature extraction module includes a first convolutional layer, a second convolutional layer, a third convolutional layer and a pooling layer. The first convolutional layer uses 32 3x3 convolution kernels, the second convolutional layer uses 64 3x3 convolution kernels, the third convolutional layer uses 128 3x3 convolution kernels, the pooling layer is a maximum pooling layer, the fully connected layer includes a first fully connected layer and a second fully connected layer, the size of the first fully connected layer is 1024, and the activation function is the ReLU function. The size of the second fully connected layer is 512, and the activation function is the ReLU activation function. The regression layer is a regression layer with a custom loss function.
[0173] In some examples, adjusting the target moving speed of each of the molten iron ladle cars based on the position information of all the molten iron ladle cars in transit, the current moving speed of all the molten iron ladle cars in transit, the intermediate molten iron content range, the molten iron content information of all the iron plant ladles, and the molten iron content information of all the steel plant ladles includes:
[0174] Initialize a Q table, wherein the Q table is used to store the Q value of each state-action, and the dimension of the table is Q(S,A), wherein S is a state set, and A is an action set, wherein the state set includes the position information of all the molten iron ladle cars in transit, the current moving speed of all the molten iron ladle cars in transit, the intermediate molten iron content range, the molten iron content information of all the molten iron ladles of the iron plant, and the molten iron content information of all the molten iron ladles of the steel plant, and the action set includes acceleration, deceleration, and keeping the speed unchanged;
[0175] Set the learning rate, discount factor, and exploration rate;
[0176] Set the reward function;
[0177] Observe the current state S t ;
[0178] According to the current state, the target action is selected using the ε-greedy strategy:
[0179] Let the molten iron ladle perform the above target actions and observe the system's feedback;
[0180] After executing the action, get the new state S (t+1) , and calculate the reward R of the current action according to the reward function t ;
[0181] Use the Q-learning update rule to update the Q values in the Q table:
[0182]
[0183] Among them, α is the learning rate, γ is the discount factor, and A′ is the new action;
[0184] Repeat the process of observing the state to update the Q value until the Q value converges or has been repeated a preset number of times, and output the target moving speed of each of the above-mentioned molten iron tank cars.
[0185] In some examples, this also includes:
[0186] Obtaining first remaining content information of a molten iron ladle being poured out of a molten iron ladle in a steel plant;
[0187] In the case where the first remaining content information is greater than the current capacity limit of the molten iron tank car, generating a tank transportation instruction;
[0188] Calculate the floating value of the intermediate molten iron content range based on the above tank transportation instructions;
[0189] The tank division strategy is determined based on the floating value of the above intermediate molten iron content range and the molten iron demand of different steel plant workshops.
[0190] In some examples, the tank division strategy is determined based on the floating value of the intermediate molten iron content range and the molten iron demand of different steel mill workshops, including:
[0191] Initialize the population and individuals, where the population has each possible tank allocation strategy, and the individual identifies the amount of molten iron allocated to each molten iron tank car;
[0192] The fitness function is defined based on the hot metal demand target of different steel mill workshops, the intermediate hot metal content balance target and the minimization of transportation time cost target;
[0193] A preset number of genetic operations are performed based on the above fitness function to obtain the above tank distribution strategy.
[0194] In some examples, the fitness function is:
[0195] F=αF 需求 +βF 含量 +γF 运输
[0196]
[0197] F 含量 =1 / (1+|intermediate molten iron content range floating value-actual distribution content|)
[0198] F 运输= 1 / (1+total shipping time and cost)
[0199] n is the number of workshops in the steel plant, the allocation amount i and the demand amount i represent the amount of molten iron obtained by the i-th workshop and its demand, respectively, and α, β and γ are weight coefficients used to balance the priority of demand satisfaction, intermediate molten iron content and transportation time.
[0200] like Figure 3 As shown, an embodiment of the present application also provides an electronic device 300, including a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor. When the processor 320 executes the computer program 311, the steps of any of the above-mentioned methods for intelligent scheduling of molten iron tank cars are implemented.
[0201] Since the electronic device introduced in this embodiment is a device used to implement an intelligent dispatching device of a molten iron tank car in the embodiment of the present application, based on the method introduced in the embodiment of the present application, technical personnel in this field can understand the specific implementation mode of the electronic device of this embodiment and its various variations. Therefore, how the electronic device implements the method in the embodiment of the present application is not introduced in detail here. As long as the equipment used by technical personnel in this field to implement the method in the embodiment of the present application falls within the scope of protection of this application.
[0202] In the specific implementation process, when the computer program 311 is executed by the processor, it can achieve Figure 1 Any implementation manner in the corresponding embodiments.
[0203] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0204] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.
[0205] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0206] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0207] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0208] An embodiment of the present application also provides a computer program product, which includes computer software instructions. When the computer software instructions are executed on a processing device, the processing device executes the process of intelligent scheduling of molten iron tank cars in the corresponding embodiment.
[0209] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a server or a data center that includes one or more available media integration. The available medium can be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state drive (SSD)), etc.
[0210] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0211] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.
[0212] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0213] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0214] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program codes.
[0215] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims
1. An intelligent dispatching method for molten iron tank cars, characterized in that: include: Obtain the current production task type information of the factory; Determine an intermediate molten iron content range based on the production type information, wherein the intermediate molten iron content range is the molten iron content range on the transportation track between the ironmaking plant and the steelmaking plant; Get the iron content information of all the ladles in the ironworks; Get the iron content information of all the ladles in the steel mill; The target moving speed of each molten iron ladle is adjusted based on the position information of all molten iron ladle cars in transit, the current moving speed of all molten iron ladle cars in transit, the intermediate molten iron content range, the molten iron content information of all iron plant ladles and the molten iron content information of all steel plant ladles.
2. The method according to claim 1, characterized in that The ironworks molten iron ladle and the steelworks molten iron include a pouring molten iron ladle, and the method for determining the content information of the pouring molten iron ladle specifically includes: Obtain image information of the molten iron ladle being poured; The image information of the pouring molten iron ladle is input into an intelligent recognition model to obtain content information of the pouring molten iron ladle.
3. The method according to claim 2, characterized in that The intelligent recognition model includes an input layer, a convolutional neural network feature extraction module, a fully connected layer, a regression module and an output layer. The convolutional neural network feature extraction module includes a first convolutional layer, a second convolutional layer, a third convolutional layer and a pooling layer. The first convolutional layer uses 32 3x3 convolution kernels, the second convolutional layer uses 64 3x3 convolution kernels, and the third convolutional layer uses 128 3x3 convolution kernels. The pooling layer is a maximum pooling layer. The fully connected layer includes a first fully connected layer and a second fully connected layer. The size of the first fully connected layer is 1024, and the activation function is the ReLU function. The size of the second fully connected layer is 512, and the activation function is the ReLU activation function. The regression layer is a regression layer with a custom loss function.
4. The method according to claim 1, characterized in that: The step of adjusting the target moving speed of each molten iron ladle based on the position information of all molten iron ladle in transit, the current moving speed of all molten iron ladle in transit, the intermediate molten iron content range, the molten iron content information of all ironworks ladles, and the molten iron content information of all steelworks ladles includes: Initialize a Q table, wherein the Q table is used to store the Q value of each state-action, and the dimension of the table is Q(S, A), wherein S is a state set, and A is an action set, wherein the state set includes the position information of all molten iron ladle cars in transit, the current moving speed of all molten iron ladle cars in transit, the intermediate molten iron content range, the molten iron content information of all ironworks ladles, and the molten iron content information of all steelworks ladles, and the action set includes acceleration, deceleration, and keeping the speed unchanged; Set the learning rate, discount factor, and exploration rate; Set the reward function; Observe the current state S t ; According to the current state, the target action is selected using the ε-greedy strategy: Let the molten iron ladle car perform the target action and observe the feedback of the system; After executing the action, get the new state S (t+1) , and calculate the reward R of the current action according to the reward function t ; Use the Q-learning update rule to update the Q values in the Q table: Among them, α is the learning rate, γ is the discount factor, and A' is the new action; Repeat the process of observing the state to updating the Q value until the Q value converges or has been repeated a preset number of times, and output the target moving speed of each of the molten iron ladle cars.
5. The method according to claim 1, characterized in that: Also includes: Obtaining first remaining content information of a molten iron ladle being poured out of a molten iron ladle in a steel plant; When the first remaining content information is greater than the current capacity limit of the molten iron tank car, generating a tank transportation instruction; Calculate the floating value of the intermediate molten iron content range based on the tank transportation instruction; The tank division strategy is determined based on the floating value of the intermediate molten iron content range and the molten iron demand of different steel plant workshops.
6. The method according to claim 1, characterized in that The tank division strategy is determined based on the floating value of the intermediate molten iron content range and the molten iron demand of different steel mill workshops, including: Initialize the population and individuals, where the population has each possible tank allocation strategy, and the individual identifies the amount of molten iron allocated to each molten iron tank car; The fitness function is defined based on the hot metal demand target of different steel mill workshops, the intermediate hot metal content balance target and the minimization of transportation time cost target; A preset number of genetic operations are performed based on the fitness function to obtain the tank distribution strategy.
7. The method according to claim 1, characterized in that The fitness function is: F=αF 需求 +βF 含量 +γF 运输 F 含量 =1(1+|intermediate molten iron content range floating value-actual distribution content|) F 运输 = 1 / (1+total shipping time and cost) n is the number of workshops in the steel plant, the allocation i and demand i They represent the amount of molten iron obtained by the i-th workshop and its demand, respectively. α, β and γ are weight coefficients used to balance the priority of demand satisfaction, intermediate molten iron content and transportation time.
8. An intelligent dispatching device for a molten iron tank car, characterized in that: include: The first acquisition unit is used to acquire the current production task type information of the factory area; A determination unit, configured to determine an intermediate molten iron content range based on the production type information, wherein the intermediate molten iron content range is a molten iron content range on a transportation track between an ironmaking plant and a steelmaking plant; The second acquisition unit is used to acquire the molten iron content information of all the ladles in the ironworks in the ironmaking plant; The third acquisition unit is used to obtain the molten iron content information of all steel ladles in the steelmaking plant; An adjustment unit is used to adjust the target moving speed of each of the molten iron ladle cars based on the position information of all the molten iron ladle cars in transit, the current moving speed of all the molten iron ladle cars in transit, the intermediate molten iron content range, the molten iron content information of all the iron plant ladles, and the molten iron content information of all the steel plant ladles.
9. An electronic device, comprising: A memory and a processor, wherein the processor is used to implement the steps of the intelligent scheduling method for molten iron tank cars as described in any one of claims 1 to 7 when executing the computer program stored in the memory.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, the steps of the intelligent scheduling method for molten iron tank cars according to any one of claims 1 to 7 are implemented.
