Deep learning-based batching model collaboration method and equipment for two-step stainless steel smelting and medium

Abstract

The invention discloses a deep learning-based batching model collaboration method and equipment for two-step stainless steel smelting and a medium. Comprising the following steps: S1, acquiring historical raw and auxiliary material usage amount data, historical energy medium usage amount, tapping molten steel components, tapping molten steel temperature, raw and auxiliary material cost and energy medium cost data, constructing a data set, and dividing the data set into a training set, a test set and a verification set; s2, obtaining calculation data of raw and auxiliary materials and an energy medium of the batching model; s3, constructing batching model collaboration based on cost optimization; s4, inputting the calibrated batching model calculation data into a batching model based on cost optimization for cooperation, and outputting predicted tapping molten steel components, tapping molten steel temperature and batching prediction cost; s5, collecting current raw and auxiliary materials, energy medium usage amount data and cost in real time; and S6, based on deep learning, realizing cost-optimal batching model cooperation, and performing operation according to the corrected calculation data of the raw and auxiliary materials and the energy medium.

Description

Technical Field

[0001] The present invention relates to a deep learning-based collaborative method, equipment and medium for realizing cost-optimal batching model for two-step stainless steel smelting. Background Art

[0002] The two-step stainless steel smelting method, in the first step, uses an electric furnace to melt nickel iron and an intermediate frequency furnace to melt chromium iron; in the second step, the molten nickel iron and chromium iron mother liquor are blended in proportion and poured into the AOD furnace, and smelted into qualified stainless steel liquid in the AOD furnace. For the stainless steel smelting industry, the steelmaking process is the link in steel production with a high proportion of raw material costs, high energy consumption, and high carbon emissions. In the process of the steel industry's transformation to green and low-carbon, solving the problem of cost-optimal batching for steelmaking and smelting has become the key to promoting the green economic operation of enterprises. By rationally planning the batching of electric furnaces, intermediate frequency furnaces, and AOD furnaces, stainless steel smelting enterprises can achieve the economic use of raw materials, auxiliary materials, and energy media to obtain the maximum cost-effectiveness. Through scientifically optimized batching plans and adjustments, stainless steel smelting enterprises can achieve environmentally friendly and low-carbon production methods. Moreover, this helps to establish a sustainable economic model and promote the steel industry to develop in a more environmentally friendly, efficient and sustainable direction.

[0003] In the existing technology, the electric furnace is equipped with an electric furnace batching model, the medium frequency furnace is equipped with an medium frequency furnace batching model, and the AOD furnace is equipped with an AOD furnace batching model. These three models operate independently and serve their respective processes. Moreover, these batching models are mainly used to smelt molten steel with qualified composition, and basically do not consider the coordination cost between processes. Summary of the invention

[0004] In order to overcome the above defects, the purpose of the present invention is to provide a method, device and medium for realizing the optimal cost-effective batching model coordination based on deep learning for two-step stainless steel smelting. In order to solve the problem that the existing electric furnace is configured with an electric furnace batching model, the medium frequency furnace is configured with an medium frequency furnace batching model, and the AOD furnace is configured with an AOD furnace batching model, and the electric furnace batching model, the medium frequency furnace batching model, and the AOD furnace batching model are all independently operated in their respective processes, and there is no cost data sharing association, so as to realize the coupling of the batching models of the electric furnace, the medium frequency furnace, and the AOD furnace based on the cost-optimal algorithm, and achieve the cost-optimal batching model coordination of the two-step stainless steel smelting.

[0005] To achieve the above object, the present invention provides a deep learning-based batching model collaboration method for two-step stainless steel smelting, wherein the method comprises the following steps:

[0006] S1: Obtain the historical raw material usage data of electric furnace, medium frequency furnace, AOD furnace, the historical energy medium usage corresponding to the historical raw material usage data, the composition of molten steel, the temperature of molten steel, the cost of raw materials, and the cost of energy medium, construct a data set, and divide the data set into a training set, a test set, and a validation set;

[0007] S2: Obtain the calculation data of raw materials and energy media of the batching models of the electric furnace, the medium frequency furnace, and the AOD furnace, and calibrate the calculation data of the batching models of raw materials and energy media through the historical raw materials and energy media usage data;

[0008] S3: Construct a batching model collaboration based on cost optimization for electric furnaces, medium frequency furnaces, and AOD furnaces, divide the data set into a training set, a test set, and a verification set in turn, input the data into the model collaboration, train, test, and verify the model, and determine whether the verification result meets the requirements. If so, execute step S4, if not, re-execute step S1;

[0009] S4: input the calibrated batching model calculation data of raw materials, auxiliary materials and energy media into the batching model based on cost optimization of the electric furnace, medium frequency furnace and AOD furnace, and output the predicted molten steel composition, molten steel temperature and batching prediction cost of the electric furnace, medium frequency furnace and AOD furnace;

[0010] S5: Real-time collection of the current raw and auxiliary materials, energy medium usage data and the current raw and auxiliary materials, energy medium costs of the electric furnace, medium frequency furnace, and AOD furnace, and correction of the predicted costs of raw and auxiliary materials and energy medium based on the current raw and auxiliary materials, energy medium usage data and the current raw and auxiliary materials, energy medium costs;

[0011] S6: The cost-optimal batching model for electric furnaces, medium frequency furnaces, and AOD furnaces based on deep learning works in coordination with the calculated data of corrected raw materials, auxiliary materials, and energy media.

[0012] Furthermore, the usage of raw and auxiliary materials, energy media, and model calculation data include the usage of scrap steel, ferronickel, ferrochrome, iron-containing raw materials, carbon, flux, slag-forming agents, etc., model calculation data, and the usage of energy media such as water, electricity, oxygen, nitrogen, argon, and compressed air, and the model calculation data; the raw and auxiliary materials, energy media cost data include the cost data of scrap steel, ferronickel, ferrochrome, iron-containing raw materials, carbon, flux, slag-forming agents, etc., and the cost data of energy media such as water, electricity, oxygen, nitrogen, argon, and compressed air.

[0013] Furthermore, the step S2 includes the following specific processes:

[0014] S21: Obtain the calculation data of raw materials, auxiliary materials and energy media of the batching models of the electric furnace, the medium frequency furnace and the AOD furnace within the specified period;

[0015] S22: Extract the usage data of raw materials, auxiliary materials and energy media in the same period from the historical usage data of raw materials, auxiliary materials and energy media;

[0016] S23: Based on the extracted usage data of raw materials, auxiliary materials and energy media in the same period, compensation calibration is performed on the calculated data of raw materials, auxiliary materials and energy media in the corresponding period according to the specified ratio.

[0017] Furthermore, the step S3 includes the following specific processes:

[0018] S31: Construct the coordination of batching model based on cost optimization for electric furnace, medium frequency furnace and AOD furnace;

[0019] S32: inputting the training set into the coordination of the batching model based on cost optimization of the electric furnace, the medium frequency furnace, and the AOD furnace to train the model;

[0020] S33: Input the test set into the coordination of the batching model based on cost optimization of the electric furnace, the medium frequency furnace, and the AOD furnace, test the trained model, and judge whether the corresponding indicators of the test results meet the requirements. If so, execute step S34; if not, re-input a new training set to train the model;

[0021] S34: Input the verification set into the cost-optimized batching model collaboration of the tested electric furnace, medium frequency furnace, and AOD furnace to verify the test results and determine whether the verification results meet the requirements. If so, execute step S4; if not, re-execute step S1.

[0022] Furthermore, in step S5, the process of correcting the predicted cost of raw materials and energy media by using the current raw materials and energy media usage data and the current raw materials and energy media costs is as follows:

[0023] S51: Calculate the cost of raw materials and energy media based on the calibrated calculation data of raw materials and energy media;

[0024] S52: Create a composite function of the predicted composition of the molten steel, the predicted temperature of the molten steel and the predicted cost of the batching for the electric furnace, the medium frequency furnace and the AOD furnace;

[0025] S53: Calculate the optimal solution for the composite function of the composition of the molten steel, the temperature of the molten steel and the predicted cost of the batching for the electric furnace, the medium frequency furnace and the AOD furnace;

[0026] S54: Correcting the electric furnace batching model, the medium frequency furnace batching model, and the AOD furnace batching model of the electric furnace, the medium frequency furnace, and the AOD furnace according to the specified ratio through the optimal solution.

[0027] Furthermore, the formula for creating a composite function in step S52 to ensure that the composition and temperature of the molten steel are qualified and the operating cost is optimal is:

[0028] f(x)=f 1EF (x)+f 1MF (x)+f 1AOD (x)+f 2EF (x)+f 2MF (x)+f 2AOD (x)+f 3EF (x)+f 3MF (x)+f 3AOD (x)

[0029] Among them, f 1EF (x) is the composition function of the steel produced by the electric furnace, f 1MF (x) is the steel composition function of the medium frequency furnace, f 1AOD (x) is the composition function of the steel produced by the AOD furnace, f 2EF (x) is the function of the steel-out temperature of the electric furnace, f 2MF (x) is the tapping temperature function of the medium frequency furnace, f 2AOD (x) is the tapping temperature function of the AOD furnace, f 3EF (x) is the cost function of the electric furnace, f 3MF (x) is the cost function of the medium frequency furnace, f 3AOD (x) is the AOD furnace cost function.

[0030] To achieve the above objectives, the terminal device of the present invention includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor. When the processor loads and executes the computer program, the above-mentioned two-step stainless steel smelting based deep learning batching model collaborative method is adopted.

[0031] To achieve the above-mentioned purpose, the present invention provides a computer-readable storage medium, in which a computer program is stored. When the computer program is loaded and executed by a processor, the above-mentioned deep learning-based batching model collaborative method for two-step stainless steel smelting is adopted.

[0032] The present invention provides a deep learning-based batching model collaboration for two-step stainless steel smelting to achieve optimal cost. The data of historical raw and auxiliary material usage, energy medium usage, molten steel composition, molten steel temperature, raw and auxiliary material cost, energy medium cost, etc. of electric furnace, medium frequency furnace, AOD furnace are obtained to construct a data set; the calculation data of raw and auxiliary materials and energy medium of each batching model of the electric furnace, medium frequency furnace, and AOD furnace are obtained, and the calculation data of raw and auxiliary materials and energy medium are calibrated according to the historical raw and auxiliary materials and energy medium usage; the batching model collaboration based on cost optimization of the electric furnace, medium frequency furnace, and AOD furnace is constructed, and the data sets are input into the model in turn. The model is trained, tested and verified, and it is determined whether the verification result meets the requirements. If so, the calibrated raw and auxiliary materials, energy medium batching model calculation data are input into the cost-optimized batching model of the electric furnace, medium frequency furnace and AOD furnace to output the predicted molten steel composition, molten steel temperature and batching prediction cost of the electric furnace, medium frequency furnace and AOD furnace; the current raw and auxiliary materials, energy medium usage data and the current raw and auxiliary materials, energy medium costs of the electric furnace, medium frequency furnace and AOD furnace are collected in real time, and the cost-optimized batching model of the electric furnace, medium frequency furnace and AOD furnace based on deep learning is coordinated with the corrected calculation data of raw and auxiliary materials and energy medium.

[0033] On the one hand, the above-mentioned deep learning-based cost-optimized batching model collaboration enables the batching models of the electric furnace, medium frequency furnace, and AOD furnace to complement each other and achieve stable molten steel composition and molten steel temperature output. On the other hand, the cost-effectiveness of two-step stainless steel smelting is improved, the smelting cost is effectively reduced, and the economic benefits are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 The figure is a flow chart of the collaborative method of implementing the cost-optimal batching model based on deep learning for two-step stainless steel smelting of the present invention. DETAILED DESCRIPTION

[0035] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0036] In the description of the present invention, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship are based on the orientation or position relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention.

[0037] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "plurality" means two or more.

[0038] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a direct connection, or an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0039] The two-step stainless steel smelting of the present invention means that, in the first step, an electric furnace is used to melt nickel iron and an intermediate frequency furnace is used to melt chromium iron; in the second step, the molten nickel iron and chromium iron mother liquors are blended in proportion and poured into an AOD furnace to smelt qualified stainless steel liquid. Depending on the raw materials, the electric furnace can independently provide molten steel mother liquor to the AOD furnace, and the intermediate frequency furnace can also independently provide molten steel mother liquor to the AOD furnace, that is, the first step can only have an electric furnace, or only have an intermediate frequency furnace, or both an electric furnace and an intermediate frequency furnace.

[0040] The present invention realizes the coordination of the batching model with the best cost, and uses deep learning technology to realize the coordination of the batching model with the best cost for the electric furnace batching model currently configured in the electric furnace, the medium frequency furnace batching model currently configured in the medium frequency furnace, and the AOD furnace batching model currently configured in the AOD furnace, so as to form a cost data sharing association, thereby realizing the coupling of the batching models of the electric furnace, the medium frequency furnace, and the AOD furnace based on the cost-optimal algorithm, and achieving the batching model with the best cost for two-step stainless steel smelting. The aforementioned electric furnace batching model and medium frequency furnace batching model are both optional.

[0041] The following is combined with Figure 1 The present invention is further described in detail:

[0042] See attached Figure 1 As shown, the deep learning-based collaborative method for achieving cost-optimal batching model for two-step stainless steel smelting includes the following steps:

[0043] S1: Obtain the historical raw material usage data of electric furnace, medium frequency furnace, AOD furnace, the historical energy medium usage corresponding to the historical raw material usage data, the composition of molten steel, the temperature of molten steel, the cost of raw materials, the cost of energy medium, etc., construct a data set, and divide the data set into a training set, a test set, and a validation set;

[0044] S2: Obtain the calculation data of raw materials and energy media of the batching models of the electric furnace, the medium frequency furnace, and the AOD furnace, and calibrate the calculation data of the batching models of raw materials and energy media through the historical raw materials and energy media usage data;

[0045] S3: Construct a batching model collaboration based on cost optimization for electric furnace, medium frequency furnace and AOD furnace, divide the data set into training set, test set and verification set in turn and input the data set into the model, train, test and verify the model, and judge whether the verification result meets the requirements. If yes, execute step S4, if not, execute step S1 again;

[0046] S4: input the calibrated batching model calculation data of raw materials, auxiliary materials and energy media into the batching model based on cost optimization of the electric furnace, medium frequency furnace and AOD furnace, and output the predicted molten steel composition, molten steel temperature and batching prediction cost of the electric furnace, medium frequency furnace and AOD furnace;

[0047] S5: Real-time collection of the current raw and auxiliary materials, energy medium usage data and the current raw and auxiliary materials, energy medium costs of the electric furnace, medium frequency furnace, and AOD furnace, and correction of the predicted costs of raw and auxiliary materials and energy medium based on the current raw and auxiliary materials, energy medium usage data and the current raw and auxiliary materials, energy medium costs;

[0048] S6: The cost-optimal batching model for electric furnaces, medium frequency furnaces, and AOD furnaces based on deep learning works in coordination with the calculated data of corrected raw materials, auxiliary materials, and energy media.

[0049] Step S1 is mainly to provide a data basis for subsequent model training, testing and verification, so that the model has the learning ability to meet the corresponding requirements. In the process of data preparation, it is necessary to obtain comprehensive data on the historical raw and auxiliary material usage of electric furnaces, medium frequency furnaces, and AOD furnaces in various periods, the historical energy medium usage corresponding to the historical raw and auxiliary material usage data, the composition of molten steel, the temperature of molten steel, the cost of raw and auxiliary materials, the cost of energy media and other data. After obtaining the relevant data, it is necessary to pre-process the acquired data, and the pre-processing process includes data cleaning, data conversion and data normalization. The process of data cleaning is mainly to remove invalid data, abnormal data, duplicate data or noise data in the data. The purpose of data conversion is to convert the data that is not easy to analyze into data that is more convenient to analyze. The purpose of data normalization is to limit the processed data to a certain range and summarize the statistical distribution of unified data samples.

[0050] In step S2, the calculation data of raw materials and energy media of each batching model of the electric furnace, the medium frequency furnace, and the AOD furnace are obtained, because the calculation data is crucial to the smelting system. The smelting system performs smelting according to the calculation data of the aforementioned batching model, so that the smelting system can operate stably and produce molten steel with qualified composition and qualified temperature. However, the calculation data is not completely accurate, and the batching data of the same workshop in the same cycle over a long period of time has a certain regularity. Therefore, it is of great significance to correct the calculation data of the batching model by obtaining the historical raw materials and energy medium usage.

[0051] In steps S3 and S4, a machine learning model that is coordinated with a cost-optimized batching model is constructed, and the constructed model is trained, tested, and verified by obtaining relevant historical data. This allows the model to have a learning ability that meets certain requirements, to be able to achieve the production of qualified products at a lower operating cost based on cost optimization, and to have lower operating costs and higher economic benefits.

[0052] The cost-optimized batching model constructed above works together as a convolutional neural network model. The process of building a convolutional neural network model includes building a convolutional layer, a pooling layer, and a fully connected layer. At the same time, corresponding parameters are set for each constructed layer, including the size and step size of the convolution kernel. At the same time, the activation function and loss function must be selected, and the optimizer must be set.

[0053] In one embodiment, the first convolution layer has 4 input channels, 8 output channels, a filter / kernel sliding step size of 1 in the convolution layer, and 0 is added to the edge of the input data during the convolution operation, and the maximum pooling size is 5. The second convolution layer has 8 input channels, 18 output channels, a filter / kernel sliding step size of 1 in the convolution layer, and 0 is added to the edge of the input data during the convolution operation, and the maximum pooling size is 5. The third fully connected layer has 324 input channels and 135 output channels. The fourth fully connected layer has 135 input channels and 96 output channels, and the output layer has 96 fully connected channels and 12 output channels. The activation function uses the Sigmoid activation function, and the loss function uses the Manhattan distance loss function.

[0054] During the training of the convolutional neural network model, the output of the model is calculated through forward propagation, and the error between the predicted value and the true value is calculated based on the loss function. Then, the gradient is calculated through the backpropagation algorithm, and the network parameters are updated using the optimizer to minimize the loss function. This process will be iterated many times until the preset number of iterations is reached or the loss function reaches a lower value. At the same time, hyperparameters such as the learning rate need to be adjusted during the training process to balance the training speed and generalization ability of the model. The optimizer selects the Adam optimization algorithm to update the model parameters.

[0055] Step S2 includes the following specific processes:

[0056] S21: Obtain the calculation data of raw materials, auxiliary materials and energy media of the batching models of the electric furnace, the medium frequency furnace and the AOD furnace within the specified period;

[0057] S22: Extract the usage data of raw materials, auxiliary materials and energy media in the same period from the historical usage data of raw materials, auxiliary materials and energy media;

[0058] S23: Based on the extracted usage data of raw materials, auxiliary materials and energy media in the same period, compensation calibration is performed on the calculated data of raw materials, auxiliary materials and energy media in the corresponding period according to the specified ratio.

[0059] Step S3 includes the following specific processes:

[0060] S31: Construct the coordination of batching model based on cost optimization for electric furnace, medium frequency furnace and AOD furnace;

[0061] S32: inputting the training set into the coordination of the batching model based on cost optimization of the electric furnace, the medium frequency furnace, and the AOD furnace to train the model;

[0062] S33: Input the test set into the coordination of the batching model based on cost optimization of the electric furnace, the medium frequency furnace, and the AOD furnace, test the trained model, and judge whether the corresponding indicators of the test results meet the requirements. If so, execute step S34; if not, re-input a new training set to train the model;

[0063] S34: Input the verification set into the cost-optimized batching model collaboration of the tested electric furnace, medium frequency furnace, and AOD furnace to verify the test results and determine whether the verification results meet the requirements. If so, execute step S4; if not, re-execute step S1.

[0064] In step S5, the process of correcting the predicted cost of raw materials and energy media by using the current raw materials and energy media usage data and the current raw materials and energy media costs is as follows:

[0065] S51: Calculate the cost of raw materials and energy media based on the calibrated calculation data of raw materials and energy media;

[0066] S52: Create a composite function of the predicted composition of the molten steel, the predicted temperature of the molten steel and the predicted cost of the batching for the electric furnace, the medium frequency furnace and the AOD furnace;

[0067] S53: Calculate the optimal solution for the composite function of the composition of the molten steel, the temperature of the molten steel and the predicted cost of the batching for the electric furnace, the medium frequency furnace and the AOD furnace;

[0068] S54: Correcting the electric furnace batching model, the medium frequency furnace batching model, and the AOD furnace batching model of the electric furnace, the medium frequency furnace, and the AOD furnace according to the specified ratio through the optimal solution.

[0069] Preferably, the formula for creating a composite function in step S52 to ensure that the composition and temperature of the molten steel are qualified and the operating cost is optimal is:

[0070] f(x)=f 1EF (x)+f 1MF (x)+f 1AOD (x)+f 2EF (x)+f 2MF (x)+f 2AOD (x)+f 3EF (x)+f 3MF (x)+f 3AOD (x)

[0071] Among them, f 1EF (x) is the composition function of the steel produced by the electric furnace, f 1MF (x) is the steel composition function of the medium frequency furnace, f 1AOD (x) is the composition function of the steel produced by the AOD furnace, f 2EF (x) is the function of the steel-out temperature of the electric furnace, f 2MF (x) is the tapping temperature function of the medium frequency furnace, f 2AOD (x) is the tapping temperature function of the AOD furnace, f 3EF (x) is the cost function of the electric furnace, f 3MF (x) is the cost function of the medium frequency furnace, f 3AOD (x) is the AOD furnace cost function.

[0072] In summary, the present invention provides a deep learning-based collaborative method for achieving cost-optimal batching model for two-step stainless steel smelting, which obtains data such as historical raw and auxiliary material usage, energy medium usage, molten steel composition, molten steel temperature, raw and auxiliary material costs, and energy medium costs of electric furnaces, medium frequency furnaces, and AOD furnaces to construct a data set; obtains the calculation data of raw and auxiliary materials and energy media of the batching models of the electric furnace, medium frequency furnace, and AOD furnace, and calibrates the calculation data of raw and auxiliary materials and energy media through the historical raw and auxiliary materials and energy medium usage; constructs a batching model collaboration based on cost optimization for the electric furnace, medium frequency furnace, and AOD furnace, and inputs the data sets into the batching model in turn. Model, train, test and verify the model, and determine whether the verification result meets the requirements. If so, input the calibrated raw and auxiliary materials, energy medium batching model calculation data into the cost-optimized batching model of the electric furnace, medium frequency furnace and AOD furnace to output the predicted molten steel composition, molten steel temperature and batching prediction cost of the electric furnace, medium frequency furnace and AOD furnace; collect the current raw and auxiliary materials, energy medium usage data and the current raw and auxiliary materials, energy medium costs of the electric furnace, medium frequency furnace and AOD furnace in real time, and run the batching model based on deep learning to achieve the optimal cost with the corrected calculation data of raw and auxiliary materials and energy medium.

[0073] An embodiment of the present application also discloses a terminal device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the processor adopts the deep learning-based batching model collaborative method for the two-step stainless steel smelting of the above-mentioned embodiment when executing the computer program.

[0074] The terminal device may be a computer device such as a desktop computer, a laptop computer or a cloud server, and the terminal device includes but is not limited to a processor and a memory. For example, the terminal device may also include input and output devices, a network access device and a bus.

[0075] Among them, the processor can adopt a central processing unit (CPU). Of course, according to actual usage, other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. can also be adopted. The general-purpose processor can adopt a microprocessor or any conventional processor, etc., and this application does not impose any restrictions on this.

[0076] Among them, the memory can be an internal storage unit of the terminal device, such as a hard disk or memory of the terminal device, or it can be an external storage device of the terminal device, such as a plug-in hard disk, a smart memory card (SMC), a secure digital card (SD) or a flash memory card (FC) equipped on the terminal device, etc., and the memory can also be a combination of an internal storage unit and an external storage device of the terminal device. The memory is used to store computer programs and other programs and data required by the terminal device. The memory can also be used to temporarily store data that has been output or is to be output, and this application does not impose any restrictions on this.

[0077] Among them, through this terminal device, the deep learning-based batching model collaborative method for the two-step stainless steel smelting of the above-mentioned embodiment is stored in the memory of the terminal device, and is loaded and executed on the processor of the terminal device for user convenience.

[0078] An embodiment of the present application further discloses a computer-readable storage medium, and the computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the deep learning-based batching model collaborative method for the two-step stainless steel smelting of the above embodiment is adopted.

[0079] Among them, the computer program can be stored in a computer-readable medium, the computer program includes computer program code, the computer program code can be in the form of source code, object code, executable file or certain middleware, etc. The computer-readable medium includes any entity or device that can carry the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the computer-readable medium includes but is not limited to the above-mentioned components.

[0080] Among them, through the computer-readable storage medium, the deep learning-based batching model collaborative method for the two-step stainless steel smelting of the above-mentioned embodiment is stored in the computer-readable storage medium, and is loaded and executed on the processor to facilitate the storage and application of the deep learning-based batching model collaborative method for the two-step stainless steel smelting.

[0081] The present invention is described in detail above in conjunction with the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge of ordinary technicians in the field without departing from the purpose of the present invention. Many other changes and modifications that do not depart from the concept and scope of the present invention should be regarded as the protection scope of the present invention.

[0082] In the description of this specification, specific features, structures, materials or characteristics may be combined in an appropriate manner in any one or more embodiments or examples.

[0083] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A deep learning-based batching model collaborative method for two-step stainless steel smelting, characterized by: The method comprises the following steps: S1: Obtain the historical raw material usage data of electric furnace, medium frequency furnace, AOD furnace, the historical energy medium usage corresponding to the historical raw material usage data, the composition of molten steel, the temperature of molten steel, the cost of raw materials, and the cost of energy medium, construct a data set, and divide the data set into a training set, a test set, and a validation set; S2: Obtain the calculation data of raw materials and energy media of the batching models of the electric furnace, the medium frequency furnace, and the AOD furnace, and calibrate the calculation data of the batching models of raw materials and energy media through the historical raw materials and energy media usage data; S3: Construct a batching model collaboration based on cost optimization for electric furnaces, medium frequency furnaces, and AOD furnaces, divide the data set into a training set, a test set, and a verification set in turn, input the data into the model collaboration, train, test, and verify the model, and determine whether the verification result meets the requirements. If so, execute step S4, if not, re-execute step S1; S4: input the calibrated batching model calculation data of raw materials, auxiliary materials and energy media into the batching model based on cost optimization of the electric furnace, medium frequency furnace and AOD furnace, and output the predicted molten steel composition, molten steel temperature and batching prediction cost of the electric furnace, medium frequency furnace and AOD furnace; S5: Real-time collection of the current raw and auxiliary materials, energy medium usage data and the current raw and auxiliary materials, energy medium costs of the electric furnace, medium frequency furnace, and AOD furnace, and correction of the predicted costs of raw and auxiliary materials and energy medium based on the current raw and auxiliary materials, energy medium usage data and the current raw and auxiliary materials, energy medium costs; S6: The cost-optimal batching model for electric furnaces, medium frequency furnaces, and AOD furnaces based on deep learning works in coordination with the calculated data of corrected raw materials, auxiliary materials, and energy media.

2. The deep learning-based batching model collaborative method for two-step stainless steel smelting according to claim 1 is characterized in that: The raw and auxiliary materials, energy medium usage, and model calculation data include the usage, model calculation data of scrap steel, ferronickel, ferrochrome, iron-containing raw materials, carbon, flux, slag-forming agent, and the energy medium usage, model calculation data of water, electricity, oxygen, nitrogen, argon, and compressed air.

3. The deep learning-based batching model collaborative method for two-step stainless steel smelting according to claim 1 is characterized in that: The cost data of raw materials, auxiliary materials and energy media include the cost data of scrap steel, ferronickel, ferrochrome, iron-containing raw materials, carbon, flux, slag-forming agents and the cost data of energy media such as water, electricity, oxygen, nitrogen, argon and compressed air.

4. The deep learning-based batching model collaborative method for two-step stainless steel smelting according to claim 1 is characterized in that: The step S2 includes the following specific process: S21: Obtain the calculation data of raw materials, auxiliary materials and energy media of the batching models of the electric furnace, the medium frequency furnace and the AOD furnace within the specified period; S22: Extract the usage data of raw materials, auxiliary materials and energy media in the same period from the historical usage data of raw materials, auxiliary materials and energy media; S23: Based on the extracted usage data of raw materials, auxiliary materials and energy media in the same period, compensation calibration is performed on the calculated data of raw materials, auxiliary materials and energy media in the corresponding period according to the specified ratio.

5. The deep learning-based batching model collaborative method for two-step stainless steel smelting according to claim 1 is characterized in that: The step S3 includes the following specific process: S31: Construct the coordination of batching model based on cost optimization for electric furnace, medium frequency furnace and AOD furnace; S32: inputting the training set into the coordination of the batching model based on cost optimization of the electric furnace, the medium frequency furnace, and the AOD furnace to train the model; S33: Input the test set into the coordination of the batching model based on cost optimization of the electric furnace, the medium frequency furnace, and the AOD furnace, test the trained model, and judge whether the corresponding indicators of the test results meet the requirements. If so, execute step S34; if not, re-input a new training set to train the model; S34: Input the verification set into the cost-optimized batching model collaboration of the tested electric furnace, medium frequency furnace, and AOD furnace to verify the test results and determine whether the verification results meet the requirements. If so, execute step S4; if not, re-execute step S1.

6. The deep learning-based batching model collaborative method for two-step stainless steel smelting according to claim 1 is characterized in that: In step S5, the process of correcting the predicted cost of raw materials and energy medium by using the current raw materials and energy medium usage data and the current raw materials and energy medium costs is as follows: S51: Calculate the cost of raw materials and energy media based on the calibrated calculation data of raw materials and energy media; S52: Create a composite function of the predicted composition of the molten steel, the predicted temperature of the molten steel and the predicted cost of the batching for the electric furnace, the medium frequency furnace and the AOD furnace; S53: Calculate the optimal solution for the composite function of the composition of the molten steel, the temperature of the molten steel and the predicted cost of the batching for the electric furnace, the medium frequency furnace and the AOD furnace; S54: Correcting the electric furnace batching model, the medium frequency furnace batching model, and the AOD furnace batching model of the electric furnace, the medium frequency furnace, and the AOD furnace according to the specified ratio through the optimal solution.

7. The deep learning-based batching model collaborative method for two-step stainless steel smelting according to claim 6 is characterized in that: The formula for creating a composite function in step S52 to ensure that the composition and temperature of the molten steel are qualified and the operating cost is optimal is: f(x)=f 1EF (x)+f 1MF (x)+f 1AOD (x)+f 2EF (x)+f 2MF (x)+f 2AOD (x)+f 3EF (x)+f 3MF (x)+f 3AOD (x) Among them, f 1EF (x) is the composition function of the steel produced by the electric furnace, f 1MF (x) is the steel composition function of the medium frequency furnace, f 1AOD (x) is the composition function of the steel produced by the AOD furnace, f 2EF (x) is the temperature function of the electric furnace, f 2MF (x) is the tapping temperature function of the medium frequency furnace, f 2AOD (x) is the tapping temperature function of the AOD furnace, f 3EF (x) is the cost function of the electric furnace, f 3MF (x) is the cost function of the medium frequency furnace, f 3AOD (x) is the AOD furnace cost function.

8. The deep learning-based batching model collaborative method for two-step stainless steel smelting according to claim 1, characterized in that: The two-step stainless steel smelting method comprises: the first step of melting ferronickel in an electric furnace and melting ferrochrome in a medium frequency furnace; the second step of blending the molten ferronickel and ferrochrome mother liquors in proportion and pouring them into an AOD furnace to smelt qualified stainless steel liquid.

9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that: When the processor loads and executes the computer program, the deep learning-based batching model collaborative method for two-step stainless steel smelting described in claim 1 is adopted.

10. A computer-readable storage medium having a computer program stored therein, characterized in that: When the computer program is loaded and executed by the processor, the deep learning-based batching model collaborative method for two-step stainless steel smelting described in claim 1 is adopted.

Images