Three-dimensional identification method, system and equipment for hearth erosion and storage medium

Abstract

The invention relates to the technical field of blast furnace ironmaking, and discloses a hearth erosion three-dimensional identification method, system and equipment and a storage medium. The method comprises the steps that a hearth is three-dimensionally segmented into a plurality of equal-angle block areas based on thermocouple position distribution; establishing a three-dimensional heat transfer calculation model of the hearth, and generating erosion control boundaries and measuring point temperature data sets under different erosion conditions of the partitioned regions; establishing a neural network model group for different block regions; performing offline model training on the neural network model group based on the erosion control boundary and the measuring point temperature data set to obtain a trained hearth erosion identification model group; and collecting actual temperature measurement data, inputting the actual temperature measurement data into the trained hearth erosion identification model group to output multiple groups of calculation results, and combining the multiple groups of calculation results to obtain a hearth erosion three-dimensional identification result. According to the method, the three-dimensional heat transfer calculation model of the hearth is established, the model training is completed offline by using the measuring point temperature data set in blocks, the hearth erosion identification result is rapidly given online according to the actual temperature measurement data, and the calculation rate is high.

Description

Technical Field

[0001] The present invention relates to the technical field of blast furnace ironmaking, and in particular to a three-dimensional recognition method, system, equipment and storage medium for furnace erosion. Background Art

[0002] For modern large-scale blast furnaces, the longevity of the hearth and bottom is crucial to the longevity of the entire blast furnace. In order to avoid major accidents such as hearth burnout during blast furnace production, it is particularly important to accurately monitor the erosion of the hearth brick lining.

[0003] Since the erosion of the furnace lining cannot be measured directly, it is necessary to use the temperature measurement of thermocouples buried in the brick lining and the heat flow data of the cooling system to establish an erosion identification model to identify the erosion situation. At present, the online furnace erosion calculation model generally establishes a mathematical model based on the numerical heat transfer equation under the current thermal measurement conditions. Since the reverse optimization solution of the three-dimensional heat transfer problem of furnace erosion is too large in scale and the rate is too low to be used for online identification, symmetry and boundary conditions are generally assumed, and the steady-state heat transfer in the brick lining is solved through the two-dimensional heat transfer equation. Such a two-dimensional erosion model ignores part of the heat transfer effect in space and loses calculation accuracy. Summary of the invention

[0004] The main purpose of the present invention is to provide a three-dimensional recognition method, system, device and storage medium for furnace erosion, aiming to solve at least one of the above-mentioned technical problems.

[0005] To achieve the above object, the present invention provides a three-dimensional recognition method for furnace erosion, comprising:

[0006] The furnace is three-dimensionally divided into multiple equal-angle block areas based on the distribution of thermocouple positions;

[0007] Establishing a three-dimensional heat transfer calculation model for the furnace, and generating erosion control boundaries and measurement point temperature data sets under different erosion conditions in the block area based on the three-dimensional heat transfer calculation model for the furnace;

[0008] Establishing a neural network model group for furnace erosion identification for different block areas;

[0009] Performing offline model training on the neural network model group based on the erosion control boundary and the measuring point temperature data set to obtain a trained furnace erosion recognition model group;

[0010] The actual temperature measurement data is collected and input into the trained furnace erosion recognition model group to output multiple groups of calculation results, and the multiple groups of calculation results are combined to obtain the three-dimensional recognition results of the furnace erosion.

[0011] In some embodiments, the three-dimensional cutting of the furnace cylinder into a plurality of equal-angled block areas based on the distribution of thermocouple positions includes:

[0012] The hearth is regarded as a three-dimensional solid shape symmetrical about the central axis;

[0013] Based on the three-dimensional shape and according to the positions of the thermocouples buried in the furnace, the furnace is divided into non-overlapping equal-angle sections along the radius to obtain a plurality of block areas; wherein the angle range of each block area is maximized and the positions of the thermocouples in each block area are distributed in the same manner.

[0014] In some embodiments, the step of establishing a three-dimensional heat transfer calculation model for a furnace includes:

[0015] Establish a furnace model based on the furnace geometry and the material types of brick linings with different structures;

[0016] Performing three-dimensional mesh division on the furnace model according to the shape of the furnace brick lining;

[0017] The mathematical model of the furnace model is set according to the energy balance principle of the shell and the three-dimensional heat transfer control differential equation in the heat transfer construction unit;

[0018] A preset numerical method is used as a solver of the furnace model, and initial conditions and boundary conditions are set in the solver to obtain a three-dimensional heat transfer calculation model of the furnace.

[0019] In some embodiments, the method further comprises:

[0020] The erosion control points at different positions of the furnace inner wall are evenly selected at reasonable intervals;

[0021] The entire furnace inner wall surface is interpolated according to the erosion control points, and is used as the boundary condition for solving the temperature field distribution of the furnace three-dimensional heat transfer calculation model.

[0022] In some embodiments, the generating of the erosion control boundary and the temperature data set of the measuring points under different erosion conditions of the block area based on the three-dimensional heat transfer calculation model of the furnace includes:

[0023] Generate erosion control boundaries based on actual blast furnace structure combined with preset erosion types;

[0024] According to the erosion control boundary, the three-dimensional temperature distribution field data in the block area is obtained through the three-dimensional heat transfer calculation model of the furnace;

[0025] A measuring point temperature data set is generated according to the three-dimensional temperature distribution field data in the block area, and the measuring point temperature data set is used as a training data set.

[0026] In some embodiments, the establishing of a neural network model group for furnace erosion identification for different block areas includes:

[0027] For each of the erosion control boundaries and the temperature data set of the measuring points in the block area, a corresponding neural network model is established; wherein the neural network model is a multi-layer feedforward neural network architecture, the temperature data set of the measuring points is used as input, and the erosion control boundary is used as output;

[0028] A neural network model group for furnace erosion identification is obtained based on the multiple neural network models.

[0029] In some embodiments, the collected actual temperature measurement data is input into the trained furnace erosion recognition model group to output multiple groups of calculation results, and the multiple groups of calculation results are combined to obtain the three-dimensional recognition results of furnace erosion, including:

[0030] Collect actual temperature measurement data;

[0031] Determine the block area corresponding to the actual temperature measurement data according to the distribution of thermocouple positions, and determine the trained furnace erosion recognition model corresponding to the block area in the trained furnace erosion recognition model group;

[0032] The actual temperature measurement data are respectively input into the corresponding trained furnace erosion recognition model to obtain the erosion control boundaries of all block areas;

[0033] The erosion control boundaries of the block areas are combined according to the angular positions of the block areas to obtain the three-dimensional recognition results of the hearth erosion.

[0034] In addition, to achieve the above-mentioned purpose, the present invention also proposes a three-dimensional recognition system for furnace erosion, comprising:

[0035] A block module is used to divide the furnace into multiple equal-angle block areas based on the distribution of thermocouple positions;

[0036] A calculation module, used to establish a three-dimensional heat transfer calculation model of the furnace, and generate erosion control boundaries and measurement point temperature data sets under different erosion conditions in the block area based on the three-dimensional heat transfer calculation model of the furnace;

[0037] A modeling module, used for establishing a neural network model group for furnace erosion identification for different block areas;

[0038] A training module, used for performing offline model training on the neural network model group based on the erosion control boundary and the measuring point temperature data set to obtain a trained furnace erosion recognition model group;

[0039] The recognition module is used to collect actual temperature measurement data and input it into the trained furnace erosion recognition model group to output multiple groups of calculation results, and merge the multiple groups of calculation results to obtain the three-dimensional recognition results of furnace erosion.

[0040] In addition, to achieve the above-mentioned purpose, the present invention also proposes an electronic device, which includes: a memory, a processor, and a three-dimensional recognition program for furnace erosion stored in the memory and executable on the processor, wherein the three-dimensional recognition program for furnace erosion is configured to implement the three-dimensional recognition method for furnace erosion as described above.

[0041] In addition, to achieve the above-mentioned purpose, the present invention also proposes a storage medium, which stores a three-dimensional recognition program for furnace erosion, and the three-dimensional recognition program for furnace erosion is used to enable the processor to implement the three-dimensional recognition method for furnace erosion as described above when executing it.

[0042] The present invention provides a three-dimensional recognition method for hearth erosion, comprising: dividing a hearth into a plurality of equal-angled block regions based on the distribution of thermocouple positions; establishing a three-dimensional heat transfer calculation model for the hearth, and generating erosion control boundaries and measuring point temperature data sets under different erosion conditions in the block regions based on the three-dimensional heat transfer calculation model for the hearth; establishing a neural network model group for hearth erosion recognition for different block regions; performing offline model training on the neural network model group based on the erosion control boundaries and measuring point temperature data sets to obtain a trained hearth erosion recognition model group; collecting actual temperature measurement data and inputting it into the trained hearth erosion recognition model group to output multiple groups of calculation results, and merging the multiple groups of calculation results to obtain a three-dimensional recognition result of hearth erosion. In the present invention, a three-dimensional heat transfer calculation model for the hearth is established, and after the training of the neural network model group is completed offline by using the three-dimensional heat transfer data of the measuring point temperature data set in blocks, the hearth erosion recognition result can be quickly given online according to the actual temperature measurement data, with a high calculation rate, thereby realizing three-dimensional heat transfer hearth erosion recognition with higher calculation efficiency, which can not only meet the rate requirements of online calculation but also achieve the accuracy of three-dimensional heat transfer solution. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 A schematic diagram of the structure of an electronic device in a hardware operating environment involved in an embodiment of the present invention;

[0044] Figure 2 It is a schematic flow chart of an embodiment of a method for three-dimensional identification of furnace erosion of the present invention;

[0045] Figure 3 It is a schematic diagram of the furnace block area involved in the embodiment of the present invention;

[0046] Figure 4 It is a schematic diagram of the distribution of thermocouple measuring points in a certain block area involved in the embodiment of the present invention;

[0047] Figure 5 A schematic diagram of erosion control points on a certain longitudinal section involved in an embodiment of the present invention;

[0048] Figure 6 It is a structural block diagram of an embodiment of a three-dimensional recognition system for furnace erosion of the present invention.

[0049] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0051] It should be noted that all directional indications in the embodiments of the present invention (such as up, down, left, right, front, back, etc.) are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0052] In addition, the descriptions of "first", "second", etc. in the present invention are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the ability of ordinary technicians in the field to implement. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by the present invention. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0053] Reference Figure 1 , Figure 1 The figure is a schematic diagram of the structure of an electronic device of the hardware operating environment involved in the embodiment of the present invention.

[0054] like Figure 1As shown, the electronic device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM memory) or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0055] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the electronic device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0056] like Figure 1 As shown, the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and a furnace erosion three-dimensional recognition program.

[0057] exist Figure 1 In the electronic device shown, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the electronic device of the present invention can be set in the electronic device, and the electronic device calls the furnace erosion three-dimensional recognition program stored in the memory 1005 through the processor 1001, and executes the furnace erosion three-dimensional recognition method provided by an embodiment of the present invention.

[0058] The present invention provides a three-dimensional recognition method, system, equipment and storage medium for furnace erosion.

[0059] The embodiment of the present invention provides a three-dimensional recognition method for furnace erosion, referring to Figure 2 , Figure 2 It is a schematic flow chart of an embodiment of a method for three-dimensional identification of furnace erosion of the present invention.

[0060] like Figure 2 As shown, the three-dimensional recognition method of furnace erosion includes:

[0061] Step S100: dividing the furnace into a plurality of equal-angle block areas based on the distribution of thermocouple positions;

[0062] Step S200: establishing a three-dimensional heat transfer calculation model for the furnace, and generating erosion control boundaries and measurement point temperature data sets under different erosion conditions in the block area based on the three-dimensional heat transfer calculation model for the furnace;

[0063] Step S300: establishing a neural network model group for furnace erosion identification for different block areas;

[0064] Step S400: performing offline model training on the neural network model group based on the erosion control boundary and the measurement point temperature data set to obtain a trained furnace erosion recognition model group;

[0065] Step S500: collecting actual temperature measurement data and inputting it into the trained furnace erosion recognition model group to output multiple groups of calculation results, and merging the multiple groups of calculation results to obtain a three-dimensional recognition result of furnace erosion.

[0066] It should be noted that the execution subject in this embodiment may be an electronic device, which may be a computer device with data processing functions, or other devices that can achieve the same or similar functions. This embodiment does not limit this. In this embodiment, a computer device is used as an example for explanation.

[0067] It can be understood that this embodiment is described by taking the three-dimensional recognition of hearth erosion in the field of blast furnace ironmaking as an example.

[0068] In one embodiment, the furnace body is divided into a plurality of equal-angle block areas based on the distribution of thermocouple positions, including: treating the furnace body as a three-dimensional shape symmetrical about a central axis; based on the three-dimensional shape and according to the positions of thermocouples buried in the furnace body, the furnace body is divided into non-overlapping equal-angle areas along the radius to obtain a plurality of block areas; wherein the angle range of each block area is maximized and the distribution of thermocouple positions in each block area is the same.

[0069] refer to Figure 3 and Figure 4 , Figure 3 The schematic diagram of the segmented area is shown. Figure 3 The black bold solid line and dotted line in the figure indicate a segmented area (other segmented areas are not shown). The multiple segmented areas are distributed at equal angles. Figure 4 The distribution of thermocouple measurement points in a certain block area is shown. Figure 4The temperature value is indicated as 0, indicating that the temperature value is not used as an actual reference. Specifically, the furnace cylinder is divided into multiple equal-angle block areas according to the distribution of thermocouple positions: the furnace cylinder is regarded as a three-dimensional shape symmetrical about the central axis, and according to the positions of the thermocouples buried in the furnace cylinder, the furnace cylinder is divided into non-overlapping equal-angle areas along the radius, so that the angle range of each area is maximized while making the distribution of thermocouple positions in the obtained divided area as similar as possible to the distribution of other block areas. In this way, using the above-mentioned furnace cylinder three-dimensional cutting method, as few block areas as possible can represent the entire furnace cylinder, and the angular range of each block area can be determined, wherein as few block areas as possible represent the entire furnace cylinder, which means that the block areas with the same thermocouple position arrangement are equivalent to each other, and one block area can be used to equivalently represent multiple block angle ranges of the furnace cylinder.

[0070] In one embodiment, a three-dimensional heat transfer calculation model for a furnace is established, including: establishing a furnace model according to the geometric dimensions of the furnace and the material types of brick linings of different structures; performing three-dimensional meshing on the furnace model according to the shape of the furnace brick lining; setting a mathematical model of the furnace model according to the energy balance principle of the shell and the three-dimensional heat transfer control differential equation in the heat transfer construction unit; using a preset numerical method as a solver for the furnace model, and setting initial conditions and boundary conditions in the solver to obtain a three-dimensional heat transfer calculation model for the furnace.

[0071] In one embodiment, the method further includes: uniformly selecting erosion control points at different positions of the furnace inner wall at reasonable intervals; interpolating the entire furnace inner wall surface based on the erosion control points as boundary conditions for solving the temperature field distribution of the furnace three-dimensional heat transfer calculation model.

[0072] Specifically, for the three-dimensional steady-state heat transfer problem in the furnace, firstly, the three-dimensional grid is divided according to the specific shape of the furnace brick lining, and the material type of the brick lining with different structures is considered. According to the energy balance principle of the shell and the three-dimensional heat transfer control differential equation in the heat transfer construction unit, the temperature field distribution under the specific erosion condition of the furnace can be calculated by numerical method. This process completes the establishment of the three-dimensional heat transfer calculation model of the furnace. The input of the three-dimensional heat transfer calculation model of the furnace is the three-dimensional erosion boundary point data inside the furnace, and the output is the three-dimensional temperature distribution field data in the furnace. Among them, the three-dimensional erosion boundary point data is the erosion control points at different positions of the furnace inner wall uniformly selected at reasonable intervals. Through these control points, the entire furnace inner wall surface can be interpolated as the boundary condition for solving the temperature field distribution; the three-dimensional temperature distribution field data in the furnace is the temperature data set of each position point arranged at uniform intervals in the three-dimensional space of the furnace lining brick.

[0073] In one example, specific methods of three-dimensional mesh division include but are not limited to hexahedral unit division method, etc.; numerical methods that can be used for solving using numerical methods include but are not limited to finite element method and finite volume method, etc.

[0074] For example, generally, in a Cartesian coordinate system, the three-dimensional heat transfer control differential equation in the heat transfer construction unit is:

[0075]

[0076] Wherein, k is the thermal conductivity of the heat transfer building unit, T is the temperature of the heat transfer building unit, x, y, and z are the positions of a certain point in the heat transfer building unit on the x-axis, y-axis, and z-axis of the Cartesian coordinate system, respectively; here, the heat transfer building unit is a unit divided by the grid.

[0077] It should be noted that establishing a three-dimensional heat transfer calculation model for a furnace usually requires comprehensive consideration of multiple factors such as the furnace's geometric structure, material properties, and operating conditions. In one example, the following steps can be used to establish a three-dimensional heat transfer calculation model for the furnace: determine the research target of the model, i.e., the temperature distribution inside the furnace, and clarify the boundary conditions of the model, including initial conditions (such as initial temperature distribution) and boundary conditions (such as heat flux input, ambient temperature, convection conditions, etc.); establish a three-dimensional geometric model of the furnace according to the actual size, and set corresponding physical parameters such as thermal conductivity, specific heat capacity, density, etc. according to the material properties of the furnace, such as the material type of brick linings of different structures; use meshing software (such as Fluent's Meshing module) to mesh the furnace model, for example, the mesh can be encrypted in key areas of the furnace (such as heat flux inlet, furnace wall, etc.) to improve the calculation accuracy; select a suitable mathematical model according to the actual situation of heat transfer in the furnace, such as a three-dimensional heat transfer control differential equation, a steady-state or unsteady-state heat transfer model, a convection heat exchange model, etc., and select an appropriate solver for calculation; set initial conditions and boundary conditions in the solver, and in addition, set the convergence criterion of iterative solution, the calculation time step, etc., to obtain a three-dimensional heat transfer calculation model for the furnace. For example, the model parameters or mesh division of the furnace three-dimensional heat transfer calculation model can be adjusted through numerical simulation calculations, and the model can be optimized and adjusted according to the result analysis and verification feedback to improve the prediction ability and accuracy of the model.

[0078] In one embodiment, erosion control boundaries and measuring point temperature data sets under different erosion conditions in the block area are generated based on the three-dimensional heat transfer calculation model of the furnace, including: generating an erosion control boundary according to the actual blast furnace structure in combination with a preset erosion type; obtaining three-dimensional temperature distribution field data in the block area through the three-dimensional heat transfer calculation model of the furnace according to the erosion control boundary; generating a measuring point temperature data set according to the three-dimensional temperature distribution field data in the block area, and using the measuring point temperature data set as a training data set.

[0079] Specifically, the erosion control boundaries and measuring point temperature data sets under different erosion conditions in each block area are generated through the three-dimensional heat transfer calculation model of the furnace: assuming a large number of possible erosion conditions, the erosion control boundaries are generated, and the corresponding temperature distribution is calculated through the three-dimensional heat transfer calculation model of the furnace, and organized into a training data set (i.e., the measuring point temperature data set).

[0080] Exemplarily, assuming that a large number of possible erosion situations need to be targeted at the actual blast furnace structure, considering the various erosion types that may occur in actual experience, design specific rules to generate erosion control boundary data of different erosion degrees corresponding to various erosion types within the radius range of the furnace on the two-dimensional longitudinal section of the furnace. Among them, the actual erosion types include but are not limited to pot bottom shape, elephant foot shape, garlic shape, etc.; the two-dimensional longitudinal section of the furnace is to regard the furnace as a three-dimensional solid shape symmetrical about the central axis, and cut the furnace solid along the radius at uniform angles in the longitudinal direction perpendicular to the horizontal plane to obtain two-dimensional longitudinal sections at different angles. The erosion situation of the furnace on each section corresponds to the erosion control points at different angles of the inner wall of the furnace in the process of establishing the three-dimensional heat transfer calculation model of the furnace; such as Figure 5 As shown, the erosion control boundary refers to a set of erosion control points within the two-dimensional longitudinal section of the furnace.

[0081] Specifically, in each block area, all possible reasonable erosion situations are considered, and the erosion control boundaries in all longitudinal sections in the block area are combined together and input into the established three-dimensional heat transfer calculation model of the furnace as input data, so that the three-dimensional temperature distribution field data in the block area can be obtained. It should be noted that it is necessary to limit the difference in erosion control boundaries of adjacent longitudinal sections, fully consider the continuity of erosion, and avoid sudden boundary jumps on adjacent longitudinal sections. Use the continuity principle to adjust the erosion control boundary to ensure that it is consistent with the actual erosion situation.

[0082] For example, for the current segmentation method of the furnace cylinder, the spatial linear interpolation method can be used to determine the temperature of the measuring points corresponding to all types of thermocouple position arrangement types in the block area from the three-dimensional temperature distribution field data. Various erosion control boundary data and corresponding measuring point temperature data under different thermocouple position distributions are sorted into data sets, and the data sets are grouped according to different thermocouple position distributions. For each group of erosion control boundaries and measuring point temperature data sets after grouping, the position distribution and data length of the measuring point temperature data sets are unique.

[0083] In one embodiment, a neural network model group for furnace erosion identification is established for different block areas, including: establishing a corresponding neural network model for the erosion control boundary and measuring point temperature data set of each block area; wherein the neural network model is a multi-layer feedforward neural network architecture, with the measuring point temperature data set as input and the erosion control boundary as output; and obtaining a neural network model group for furnace erosion identification based on multiple neural network models.

[0084] Specifically, a neural network model group for furnace erosion identification is established for different block areas to complete offline model training: the grouped erosion control boundaries and measuring point temperature data sets are obtained, and for each group of erosion control boundaries and measuring point temperature data sets, a specific furnace erosion identification neural network model is established, in which the temperature data of the measuring point temperature data set is used as input and the erosion control boundary is used as output.

[0085] It can be understood that for each set of data sets (erosion control boundary and measurement point temperature data sets), the input and output layers, the number of network layers and the number of nodes in each layer of the appropriate neural network model are designed. Using each set of data sets, the training of each neural network model is completed, and a neural network model group that can be used for furnace erosion identification is obtained.

[0086] Exemplarily, the neural network model can adopt a multi-layer feedforward neural network architecture. In this embodiment, other network architectures can also be used, such as convolutional neural network (CNN), recurrent neural network (RNN), long short-term memory network (LSTM), gated recurrent unit (GRU), self-attention mechanism and Transformer model, generative adversarial network (GAN) and reinforcement learning network, etc.

[0087] In one embodiment, actual temperature measurement data is collected and input into a trained furnace erosion recognition model group to output multiple groups of calculation results, and the multiple groups of calculation results are combined to obtain a three-dimensional recognition result of furnace erosion, including: collecting actual temperature measurement data; determining the block area corresponding to the actual temperature measurement data according to the distribution of thermocouple positions, and determining the trained furnace erosion recognition model corresponding to the block area in the trained furnace erosion recognition model group; inputting the actual temperature measurement data into the corresponding trained furnace erosion recognition model respectively to obtain the erosion control boundaries of all block areas; combining the erosion control boundaries of the block areas according to the angular positions of the block areas to obtain the three-dimensional recognition result of furnace erosion.

[0088] Specifically, the actual temperature measurement data is input into the furnace erosion recognition model group, and the calculation results of each group are merged to obtain the three-dimensional recognition result of the furnace erosion: according to the position distribution of the thermocouples, the actual temperature measurement data of the thermocouples in each block area are respectively input into the corresponding trained neural network model, and the erosion control boundaries of all block areas can be obtained in turn; all the erosion control boundaries are combined according to the angular position of the blocks, and the erosion control point data of the longitudinal section of the furnace at all angles (the three-dimensional recognition result of the furnace erosion) is obtained. This result characterizes the erosion situation in the current furnace. In this way, the three-dimensional recognition of the furnace erosion is completed by the above method of this embodiment.

[0089] The present embodiment provides a three-dimensional recognition method for hearth erosion, including: dividing the hearth into multiple equal-angle block areas based on the distribution of thermocouple positions; establishing a three-dimensional heat transfer calculation model for the hearth, and generating erosion control boundaries and measuring point temperature data sets under different erosion conditions in the block areas based on the three-dimensional heat transfer calculation model for the hearth; establishing a neural network model group for hearth erosion recognition for different block areas; performing offline model training on the neural network model group based on the erosion control boundaries of the measuring point temperature data set to obtain a trained hearth erosion recognition model group; collecting actual temperature measurement data and inputting it into the trained hearth erosion recognition model group to output multiple groups of calculation results, and merging the multiple groups of calculation results to obtain a three-dimensional recognition result of hearth erosion. In the present embodiment, a three-dimensional heat transfer calculation model for the hearth is established, and after the training of the neural network model group is completed offline by using the three-dimensional heat transfer data of the measuring point temperature data set in blocks, the hearth erosion recognition result can be quickly given online according to the actual temperature measurement data, with a high calculation rate, thereby realizing three-dimensional heat transfer hearth erosion recognition with higher calculation efficiency, which can not only meet the rate requirements of online calculation but also achieve the accuracy of three-dimensional heat transfer solution.

[0090] In addition, an embodiment of the present invention further proposes a storage medium, on which a three-dimensional recognition program for furnace erosion is stored. When the three-dimensional recognition program for furnace erosion is executed by a processor, the steps of the three-dimensional recognition method for furnace erosion described above are implemented.

[0091] Reference Figure 6 , Figure 6 It is a structural block diagram of an embodiment of a three-dimensional recognition system for furnace erosion of the present invention.

[0092] like Figure 6 As shown, the furnace erosion three-dimensional identification system comprises:

[0093] A block division module 10 is used to divide the furnace into a plurality of block areas with equal angles based on the distribution of thermocouple positions;

[0094] The calculation module 20 is used to establish a three-dimensional heat transfer calculation model of the furnace, and generate erosion control boundaries and measurement point temperature data sets under different erosion conditions in the block area based on the three-dimensional heat transfer calculation model of the furnace;

[0095] A modeling module 30, used for establishing a neural network model group for furnace erosion identification for different block areas;

[0096] A training module 40 is used to perform offline model training on the neural network model group based on the erosion control boundary and the measurement point temperature data set to obtain a trained furnace erosion recognition model group;

[0097] The recognition module 50 is used to collect actual temperature measurement data and input it into the trained furnace erosion recognition model group to output multiple groups of calculation results, and merge the multiple groups of calculation results to obtain the three-dimensional recognition results of furnace erosion.

[0098] In this embodiment, a three-dimensional heat transfer calculation model for the furnace is established, and after the training of the neural network model group is completed offline by using the three-dimensional heat transfer data of the measuring point temperature data set in blocks, the furnace erosion identification result can be quickly given online based on the actual temperature measurement data, with a high calculation rate, thereby achieving three-dimensional heat transfer furnace erosion identification with higher calculation efficiency, which can not only meet the rate requirements of online calculation but also achieve the accuracy of three-dimensional heat transfer solution.

[0099] It should be noted that the technical details that are not described in detail in the embodiment of the hearth erosion three-dimensional identification system can be found in the hearth erosion three-dimensional identification method as described above provided in any embodiment of the present invention, and will not be repeated here.

[0100] It should be understood that the above is only an example and does not constitute any limitation on the technical solution of the present invention. In specific applications, technicians in this field can make settings as needed, and the present invention does not limit this.

[0101] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of them according to actual needs to achieve the purpose of the present embodiment, and no limitation is made here.

[0102] In addition, it should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0103] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0104] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory (ROM) / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0105] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A three-dimensional identification method for furnace erosion, characterized in that: include: The furnace is three-dimensionally divided into multiple equal-angle block areas based on the distribution of thermocouple positions; Establishing a three-dimensional heat transfer calculation model for the furnace, and generating erosion control boundaries and measurement point temperature data sets under different erosion conditions in the block area based on the three-dimensional heat transfer calculation model for the furnace; Establishing a neural network model group for furnace erosion identification for different block areas; Performing offline model training on the neural network model group based on the erosion control boundary and the measuring point temperature data set to obtain a trained furnace erosion recognition model group; The actual temperature measurement data is collected and input into the trained furnace erosion recognition model group to output multiple groups of calculation results, and the multiple groups of calculation results are combined to obtain the three-dimensional recognition results of the furnace erosion.

2. The method according to claim 1, characterized in that The method of dividing the furnace into a plurality of equal-angle block areas based on the distribution of thermocouple positions includes: The hearth is regarded as a three-dimensional solid shape symmetrical about the central axis; Based on the three-dimensional shape and according to the positions of the thermocouples buried in the furnace, the furnace is divided into non-overlapping equal-angle sections along the radius to obtain a plurality of block areas; wherein the angle range of each block area is maximized and the positions of the thermocouples in each block area are distributed in the same manner.

3. The method according to claim 1, characterized in that The establishment of a three-dimensional heat transfer calculation model for the furnace includes: Establish a furnace model based on the furnace geometry and the material types of brick linings with different structures; Performing three-dimensional mesh division on the furnace model according to the shape of the furnace brick lining; The mathematical model of the furnace model is set according to the energy balance principle of the shell and the three-dimensional heat transfer control differential equation in the heat transfer construction unit; A preset numerical method is used as a solver of the furnace model, and initial conditions and boundary conditions are set in the solver to obtain a three-dimensional heat transfer calculation model of the furnace.

4. The method according to claim 3, characterized in that The method further comprises: The erosion control points at different positions of the furnace inner wall are evenly selected at reasonable intervals; The entire furnace inner wall surface is interpolated according to the erosion control points, and is used as the boundary condition for solving the temperature field distribution of the furnace three-dimensional heat transfer calculation model.

5. The method according to claim 1, characterized in that The generating of the erosion control boundary and the temperature data set of the measuring points under different erosion conditions of the block area based on the three-dimensional heat transfer calculation model of the furnace includes: Generate erosion control boundaries based on actual blast furnace structure combined with preset erosion types; According to the erosion control boundary, the three-dimensional temperature distribution field data in the block area is obtained through the three-dimensional heat transfer calculation model of the furnace; A measuring point temperature data set is generated according to the three-dimensional temperature distribution field data in the block area, and the measuring point temperature data set is used as a training data set.

6. The method according to claim 1, characterized in that The neural network model group for furnace erosion identification is established for different block areas, including: For each of the erosion control boundaries and the temperature data set of the measuring points in the block area, a corresponding neural network model is established; wherein the neural network model is a multi-layer feedforward neural network architecture, the temperature data set of the measuring points is used as input, and the erosion control boundary is used as output; A neural network model group for furnace erosion identification is obtained based on the multiple neural network models.

7. The method according to any one of claims 1 to 6, characterized in that The collected actual temperature measurement data is input into the trained furnace erosion recognition model group to output multiple groups of calculation results, and the multiple groups of calculation results are combined to obtain the three-dimensional recognition results of furnace erosion, including: Collect actual temperature measurement data; Determine the block area corresponding to the actual temperature measurement data according to the thermocouple position distribution, and determine the trained furnace erosion recognition model corresponding to the block area in the trained furnace erosion recognition model group; The actual temperature measurement data are respectively input into the corresponding trained furnace erosion recognition model to obtain the erosion control boundaries of all block areas; The erosion control boundaries of the block areas are combined according to the angular positions of the block areas to obtain the three-dimensional recognition results of the hearth erosion.

8. A three-dimensional recognition system for furnace erosion, characterized in that: include: A block module is used to divide the furnace into multiple equal-angle block areas based on the distribution of thermocouple positions; A calculation module, used to establish a three-dimensional heat transfer calculation model of the furnace, and generate erosion control boundaries and measurement point temperature data sets under different erosion conditions in the block area based on the three-dimensional heat transfer calculation model of the furnace; A modeling module, used for establishing a neural network model group for furnace erosion identification for different block areas; A training module, used for performing offline model training on the neural network model group based on the erosion control boundary and the measuring point temperature data set to obtain a trained furnace erosion recognition model group; The recognition module is used to collect actual temperature measurement data and input it into the trained furnace erosion recognition model group to output multiple groups of calculation results, and merge the multiple groups of calculation results to obtain the three-dimensional recognition results of furnace erosion.

9. An electronic device, characterized in that: The electronic device comprises: a memory, a processor and a three-dimensional recognition program for furnace erosion stored in the memory and executable on the processor, wherein the three-dimensional recognition program for furnace erosion is configured to implement a three-dimensional recognition method for furnace erosion as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores a three-dimensional recognition program for hearth erosion, and the three-dimensional recognition program for hearth erosion is used to enable the processor to implement the three-dimensional recognition method for hearth erosion as described in any one of claims 1 to 7 when executing the program.

Images