Blast furnace transition performance prediction method and equipment based on data driving and storage medium

By combining finite element simulation and machine learning, a blast furnace thrust performance prediction method is established, and the real-time optimization problem of blast furnace thrust performance prediction in the existing technology is solved, and the rapid and accurate prediction effect is achieved, ensuring the safety and production efficiency of the blast furnace thrust process are ensured. .

CN118917138APending Publication Date: 2024-11-08CHINA 19TH METALLURGICAL CORP
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410958509.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-17
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

The existing technology is difficult to quickly and accurately perform real-time optimization in blast furnace thrust process. The finite element method has problems such as long calculation time, difficulty in parallel computing using GPU and inability to make real-time prediction in blast furnace thrust performance prediction, and it is difficult to meet the intelligent numerical calculation model. demand.

Method used

By establishing a three-dimensional data model of the blast furnace thrust system, designing orthogonal experimental models, calculating the combined force characteristics and vibration mode characteristics of the furnace body and the thrust orbit, using finite element simulation and machine learning to generate machine learning data samples and collect them through sensors Transient response data, cross-validation method trains the optimal machine learning model, and performs blast furnace lapse performance prediction.

Benefits of technology

It realizes rapid and accurate prediction of furnace body displacement, attitude, sliding shoe friction and thrust track deformation and stress during blast furnace transfer, warning in advance and removing obstacles, ensuring the safety and smooth production of blast furnace transfer projects.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118917138A_ABST
    Figure CN118917138A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of engineering numerical calculation and analysis, in particular to a blast furnace transition performance prediction method and device based on data driving and a storage medium. The invention discloses a data-driven blast furnace displacement performance prediction method, which comprises the following steps: establishing a high-fidelity digital model, simulating a blast furnace displacement process by adopting a finite element simulation model, and generating sample data; and comparing and verifying the test data under actual transition with part of sample data, and designing an orthogonal experiment table through characteristic analysis to obtain a transition response spectrum sample of the blast furnace. Carrying out model training and testing on the sample to obtain an optimal machine learning model, and comparing the optimal machine learning model with an actual pushing working condition to obtain an intelligent prediction model of the blast furnace pushing performance; accurate prediction of the overall displacement of the blast furnace, the posture change process of the furnace body, the stress distribution of the sliding shoes at the bottom of the pushing tray and the stress distribution of the furnace body under the action of wind load in the pushing work of the blast furnace is achieved, and guarantee is provided for safe implementation of blast furnace pushing and production recovery of the blast furnace.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of engineering numerical calculation and analysis, and in particular to a prediction method, device and storage medium for blast furnace pushing performance based on data drive. Background Art

[0002] The overall movement of the blast furnace is not only a technical challenge, but also an important means to improve production efficiency, ensure safety, reduce costs and promote the development of the steel industry. The movement of the blast furnace includes the following complex engineering issues:

[0003] Precise mechanical equipment and structural design, such as hydraulic systems, support structures, slide rails and anchor points, are required to ensure the stability and alignment of the furnace body during the movement. To achieve precise control of the blast furnace body, advanced control systems and sensor technologies are required, including displacement sensors, angle sensors, pressure sensors, etc., as well as feedback control algorithms and automation software. The mechanical properties of the blast furnace body structure, including stress analysis, deformation prediction and structural integrity assessment, are required to prevent structural damage during the movement. At present, there is an urgent need for numerical technology theories and methods that can quickly and accurately optimize the movement performance in real time during the blast furnace movement process.

[0004] At present, the finite element method (FEM) is basically used in the simulation calculation of blast furnace movement under complex working conditions in actual engineering applications. The finite element method is a calculation method that discretizes specific partial differential equations (PDE) of physical objects for numerical solution. Although the above methods are widely used in various engineering fields, they have obvious limitations: for example, the Galerkin method used in the finite element method takes a long time to calculate, and it is difficult to use GPU parallel computing technology. In addition, the finite element method only has offline analysis and calculation and cannot perform real-time prediction. Once the pre-processing parameters are set, they cannot be self-optimized. In the current context of artificial intelligence combined with industrial big data, it is difficult to meet the needs of a new generation of intelligent numerical calculation models in large-scale complex engineering calculations such as blast furnace movement projects. Summary of the invention

[0005] In order to solve the above technical problems, the present invention provides a method for predicting blast furnace moving performance based on data-driven, which is characterized by comprising the following steps:

[0006] S1. Establish a three-dimensional data model of the blast furnace moving system based on the blast furnace moving site data and construction drawing data;

[0007] S2. According to the obtained three-dimensional data model, based on the parametric idea, a finite element simulation model of the blast furnace push system is established;

[0008] S3. Design an orthogonal experimental model based on the force conditions of the blast furnace, and calculate the combined force characteristics and vibration modal characteristics of the furnace body and the push track;

[0009] S4. Input the obtained force combination characteristics and vibration modal characteristics of the furnace body and the push rail into the finite element simulation model for simulation calculation to obtain a machine learning data sample;

[0010] S5. Collect transient response data of the furnace and the push track through sensors;

[0011] S6. Based on the machine learning data samples, a training data result is obtained by training through a cross-validation method, and the training data result is compared with the transient response data for data accuracy, and the result with the highest accuracy is selected as the optimal machine learning model;

[0012] S7. Based on the optimal machine learning model and combined with transient response data, the blast furnace pushing performance is predicted.

[0013] Furthermore, the three-dimensional data model includes a three-dimensional data model of a blast furnace body, a three-dimensional data model of a sliding tray and a three-dimensional data model of a sliding track.

[0014] Further, step S2 includes the following steps:

[0015] S401. Set the material properties, boundary conditions and load parameters of the blast furnace push system in the three-dimensional data model;

[0016] S402. Meshing the three-dimensional data model using finite element analysis software to generate a finite element network model;

[0017] S403. According to the material properties, boundary conditions and load data, the finite element network model is respectively verified to obtain a finite element simulation model.

[0018] Furthermore, the sensors described in step S5 include a wind speed sensor, an acceleration sensor, an inclination sensor, a laser displacement sensor and a strain force sensor, which are respectively used to collect wind speed data of the blast furnace body, acceleration data of the blast furnace body, inclination data of the blast furnace body, displacement transient response data of the blast furnace body and stress transient response data of the blast furnace push track.

[0019] Furthermore, the cross-validation method described in step S6 uses 12-fold cross-validation, in which the machine learning data sample is divided into 12 equal parts, 11 parts of the machine learning data sample are selected as training samples for training, and the remaining part is tested. This process is repeated 12 times, and a different part is selected as the training data result each time.

[0020] Furthermore, the training algorithm is a composite neural network, which integrates at least a CNN neural network, an RNN neural network, and a DBN neural network based on a generation model of restricted Boltzmann machines (RBMs). The training algorithm supports vector machines (SVMs) and is combined with a BP neural network algorithm, namely a back propagation algorithm.

[0021] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the data-driven prediction method for blast furnace movement performance as described in any one of claims 1 to 6 when executing the computer program.

[0022] A storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the data-driven prediction method for blast furnace movement performance as described in any one of claims 1 to 6.

[0023] The beneficial effects of the present invention are:

[0024] Combining data-driven machine learning, finite element simulation and blast furnace pushing dynamics testing can quickly and accurately predict the displacement and posture of the furnace body during the blast furnace pushing process, the friction between the sliding shoe and the pushing, the deformation and stress of the pushing track, and provide early warning of dangerous points that may appear during the blast furnace pushing process. All obstacles in the blast furnace pushing process can be eliminated in advance, providing effective guarantees for the safe implementation of the blast furnace pushing project and the smooth resumption of blast furnace production. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 , a flow chart of the data-driven prediction method for blast furnace movement performance of the present invention.

[0026] Figure 2 , schematic diagram of the arrangement of measurement points of the blast furnace pushing furnace body according to an embodiment of the present invention.

[0027] Figure 3 , schematic diagram of the arrangement of measurement points of the blast furnace push track according to an embodiment of the present invention.

[0028] Figure 4 , a schematic diagram of the structure of the machine learning model of an embodiment of the present invention.

[0029] Figure 5 , a schematic diagram of the internal structure of a computer device of the present invention.

[0030] Figure 6 , a schematic diagram of a storage medium of the present invention. DETAILED DESCRIPTION

[0031] In order to enable those skilled in the art to better understand the content of the present invention and make the purpose, technical solution and advantages of the present invention clearer, the present invention is further described in detail below in conjunction with the embodiments and the accompanying drawings. The illustrative embodiments of the present invention and their description are only used to explain the present invention and are not intended to further limit the present invention.

[0032] like Figure 1 As shown, the embodiment of the present invention provides a method for predicting blast furnace movement performance based on data-driven, comprising the following steps:

[0033] S1: Establish a high-precision 3D geometric model of blast furnace movement;

[0034] Firstly, the site data of blast furnace pushing is measured, and a high-fidelity digital model of blast furnace pushing is established in combination with the actual blast furnace pushing construction drawing data, including blast furnace body, heat-bearing refractory materials inside the blast furnace, concrete foundation at the bottom of the blast furnace, blast furnace pushing tray, and blast furnace pushing track. The high-fidelity digital model of blast furnace pushing is accurately modeled by using commercial CAD modeling software.

[0035] S2: Establish a finite element model for blast furnace movement simulation;

[0036] Based on the parametric concept, a finite element simulation model of the blast furnace sliding system was established, and the pre-processing work including material parameter setting, contact definition, and mesh discretization was completed.

[0037] Specifically, the furnace body and the main body and concrete foundation of the bottom push tray of the blast furnace are simulated by thin-walled shell elements; the bottom sliding shoe of the push tray and the rack of the upper part of the push track are simulated by solid elements, and the push track, the bottom sliding shoe and the blast furnace body are numbered in sections. The blast furnace push track is numbered in sequence for a total of 4, the blast furnace body is divided into 14 sections along the height, and the bottom sliding shoe is numbered in sequence for a total of 22; combined with the field measurement of wind speed, an appropriate conservative wind speed is selected. The Von-Karman wind spectrum is used to simulate the actual wind conditions during the blast furnace push process.

[0038] S3: Design orthogonal experimental scheme;

[0039] According to the actual situation, the thrust applied at the contact point between the blast furnace pushing tray and the toothed pushing track and the piston connecting rod is divided into j level values. According to the orthogonal experimental method, an orthogonal experimental table with k factor levels is designed. The orthogonal experimental table can characterize the force combination characteristics of the blast furnace body and the pushing track during the blast furnace pushing, and can reflect the vibration modal characteristics of the blast furnace body and the track during the blast furnace pushing combined with the wind load.

[0040] Specifically, the orthogonal experimental table should characterize as many characteristics of the thrust at the contact between the pushing tray and the toothed pushing track and the piston connecting rod as possible during the blast furnace pushing process, and then reflect the vibration modal characteristics of the blast furnace body and the track during the blast furnace pushing. In this example, four groups of hydraulic piston pushing are used, and the factors affecting the pushing force are: the friction coefficient of the pushing track surface, the seam width at the track connection, the height difference at the track connection, and the ambient wind speed, a total of 4 factors. Assuming that each factor corresponds to 3 horizontal levels, four groups of orthogonal experimental tables should be used. Each group of orthogonal experimental tables has 4 columns and 12 rows, 4 columns correspond to 4 factors affecting the pushing force, and 12 rows correspond to 3 horizontal levels for each factor. 12 groups of experiments should be designed. The data types in the blast furnace pushing process include data collected by wind speed sensors, acceleration sensors, inclination sensors, laser displacement sensors and strain force sensors, including hydraulic piston pushing force data, wind speed data, blast furnace movement speed data and acceleration data.

[0041] S4: Generate data samples that drive machine learning through digital simulation;

[0042] Select any one of the multiple thrust size combinations in the orthogonal experiment table, and bring it into the established blast furnace pushing finite element simulation model, select the contact point between the pushing tray at the bottom of the blast furnace and the tooth groove pushing track and the piston connecting rod as the excitation application point, select the center of each of the 14 sections of the blast furnace body and the contact point between the pushing track and the sliding shoe as the measurement point, apply excitation at the excitation application point through dynamic finite element simulation, and obtain the real-time dynamic response of each measuring point through dynamic finite element simulation; repeat this step until all combinations in the orthogonal experiment table are executed, and the required machine learning sample can be obtained: hydraulic piston connecting rod thrust-system response spectrum sample.

[0043] Specifically, the finite element simulation model can also be replaced by the CAE simulation model, which covers all aspects of the use of computer software and hardware tools to assist engineering design and analysis. CAE not only includes finite element analysis, but may also include computer-aided design (CAD), computer-aided manufacturing (CAM), optimization design, multi-physics field analysis, etc. CAE simulation is widely used in product design, engineering analysis, system optimization and other fields. It can help engineers predict product performance before actual manufacturing, evaluate the feasibility of design solutions, optimize product structure, and reduce R&D costs and risks.

[0044] S5: Transient response measurement of furnace body and moving track during blast furnace moving;

[0045] The method in S4 is adopted, by applying excitation at the same excitation point as S4, and installing sensors at the same measurement points as S4 to measure the transient response of the furnace body during the movement of the blast furnace, thereby obtaining the transient response test data of the furnace body and the pushing track during the movement of the blast furnace.

[0046] Specifically, sensors are arranged at the measuring points of the blast furnace pushing facilities, including wind speed sensors and inclination sensors distributed along the height of the blast furnace body; strain force sensors and laser displacement sensors are arranged along the rails of the blast furnace pushing track, and the laser displacement sensors are used to measure the width of the rail joints.

[0047] S6: Obtain the optimal machine learning model through model training and testing of sample data;

[0048] Preferably, the obtained machine learning samples are trained using a cross-validation method, using 12-fold cross-validation, where the data set is divided into 12 equal parts, 11 parts of the data set are selected as training samples for training, and the remaining part is tested. This process is repeated 12 times, each time selecting a different part as the test sample.

[0049] According to the characteristics of the sample data, several suitable machine learning models are selected. The data-driven machine learning algorithms include CNN neural network, RNN neural network, DBN neural network based on the generation model of restricted Boltzmann machine RBMs, support vector machine SVM, and BP neural network algorithm, that is, back propagation algorithm, but not limited to this. Through data-driven, the results after model training are compared with the test sample data. If the accuracy requirements are met, the final optimal machine learning model can be obtained. If the accuracy requirements are not met, the model training steps are repeated until the accuracy meets the requirements.

[0050] Part of the transient response data of blast furnace movement obtained in S4 and S5 is used as driving data, and the optimal machine learning model obtained by training in S6 is used to predict the blast furnace movement performance.

[0051] Further, such as Figure 2 As shown, several measuring points are arranged at the furnace bottom pushing tray 1, the furnace bottom concrete foundation 2, the blast furnace body 3 and the transient response and wind speed measuring point 4, respectively, for measuring the real-time parameters of the furnace body during the blast furnace pushing.

[0052] Further, such as Figure 3 As shown, several measuring points are arranged at the bottom tray 1 of the push rail, the rail (square steel) 2, the reverse thrust rack 3, the strain measuring point 4 and the rail joint width measuring point 5, respectively, for measuring the real-time parameters of the push rail during the blast furnace pushing process.

[0053] Further, such as Figure 4 As shown, the machine learning model includes an input and output layer, a nonlinear discrete differential operator processing layer, a hidden layer composed of multiple neural networks, and a nonlinear activation function layer.

[0054] Furthermore, as a preferred implementation scheme of this embodiment, a terminal device for predicting the blast furnace moving performance based on data driven is proposed, such as Figure 5 As shown, the terminal device 200 includes at least one memory 210, at least one processor 220, and a bus 230 connecting different platform systems.

[0055] The memory 210 may include a readable medium in the form of a volatile memory, such as a random access memory (RAM) 211 and / or a cache memory 212 , and may further include a read-only memory (ROM) 213 .

[0056] Among them, the memory 210 also stores a computer program, and the computer program can be executed by the processor 220, so that the processor 220 executes any of the above-mentioned data-driven prediction methods for blast furnace push performance in the embodiments of the present application, and its specific implementation method is consistent with the implementation method and the technical effect achieved in the above-mentioned embodiments, and some contents are not repeated. The memory 210 can also include a program / utility 214 having a set (at least one) of program modules 215, such program modules include but are not limited to: an operating system, one or more application programs, other program modules and program data, each of these examples or some combination may include the implementation of a network environment.

[0057] Accordingly, the processor 220 may execute the above-mentioned computer programs, and may execute the program / utility 214 .

[0058] Bus 230 may be a bus representing one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures.

[0059] The terminal device 200 may also communicate with one or more external devices 240 such as keyboards, pointing devices, Bluetooth devices, etc., and may also communicate with one or more devices that can interact with the terminal device 200, and / or communicate with any device (such as a router, a modem, etc.) that enables the terminal device 200 to communicate with one or more other computing devices. Such communication may be performed through an input / output (I / O) interface 250. In addition, the terminal device 200 may also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN) and / or a public network, such as the Internet) through a network adapter 260. The network adapter 260 may communicate with other modules of the terminal device 200 through a bus 230. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the terminal device 200, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms, etc.

[0060] Furthermore, as a preferred implementation scheme of this embodiment, a computer-readable storage medium for a data-driven prediction method of blast furnace push performance is proposed, and the computer-readable storage medium stores instructions, and when the instructions are executed by the processor, any of the above-mentioned data-driven prediction methods of blast furnace push performance is implemented. Its specific implementation method is consistent with the implementation method and the technical effect achieved in the above-mentioned embodiment, and some contents are not repeated here.

[0061] like Figure 6 As shown, the program product 300 for realizing the above-mentioned prediction method of blast furnace pushing performance based on data drive provided in this embodiment can adopt portable compact disk read-only memory (CD-ROM) and include program code, and can be run on terminal equipment, such as personal computer. However, the program product 300 of the present invention is not limited to this. In this document, the readable storage medium can be any tangible medium containing or storing a program, which can be used or used in combination with an instruction execution system, device or device. The program product 300 can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0062] Computer-readable storage media may include data signals propagated in baseband or as part of a carrier wave, wherein readable program codes are carried. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The readable storage medium may also be any readable medium other than the readable storage medium, which may send, propagate, or transmit a program used by or in combination with an instruction execution system, an apparatus, or a device. The program code contained on the readable storage medium may be transmitted with any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above. The program code for performing the operation of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and also conventional procedural programming languages ​​such as "C" language or similar programming languages. The program code may be executed entirely on a user computing device, partially on a user device, as an independent software package, partially on a user computing device, partially on a remote computing device, or entirely on a remote computing device or server. Where a remote computing device is involved, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0063] The above shows and describes the basic principle and main features of the present invention and the advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments, and the above embodiments and descriptions are only for explaining the principle of the present invention.

[0064] The present invention is explained from the viewpoints of purpose of use, efficiency, progress and novelty, and the practical progress it has is in line with the functional enhancement and use requirements emphasized by the Patent Law. The above description and drawings of this application are only preferred embodiments of this application, and are not intended to limit this application. Therefore, all structures, devices, features, etc. that are similar or identical to those of this application, that is, all equivalent replacements or modifications made in accordance with the scope of the patent application of this application, should fall within the scope of protection of the patent application of this application.

[0065] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A data-driven prediction method for blast furnace movement performance, characterized in that: The following steps are involved: S1. Establish a three-dimensional data model of the blast furnace moving system based on the blast furnace moving site data and the blast furnace moving construction drawing data; S2. According to the obtained three-dimensional data model, based on the parametric idea, a finite element simulation model of the blast furnace push system is established; S3. Design an orthogonal experimental model based on the force conditions of the blast furnace, and calculate the combined force characteristics and vibration modal characteristics of the furnace body and the push track; S4. Input the obtained force combination characteristics and vibration modal characteristics of the furnace body and the push rail into the finite element simulation model for simulation calculation to obtain a machine learning data sample; S5. Collect transient response data of the furnace and the push track through sensors; S6. Based on the machine learning data samples, a training data result is obtained by training through a cross-validation method, and the training data result is compared with the transient response data for data accuracy, and the result with the highest accuracy is selected as the optimal machine learning model; S7. Based on the optimal machine learning model, the blast furnace pushing performance is predicted in combination with transient response data to obtain the prediction results.

2. The method for predicting blast furnace movement performance based on data drive according to claim 1, characterized in that: The three-dimensional data model includes a three-dimensional data model of a blast furnace body, a three-dimensional data model of a sliding tray and a sliding track data model.

3. The method for predicting blast furnace movement performance based on data drive according to claim 1, characterized in that: Step S2 includes the following steps: S401. Set the material properties, boundary conditions and load parameters of the blast furnace push system in the three-dimensional data model; S402. Meshing the three-dimensional data model using finite element analysis software to generate a finite element network model; S403. According to the material properties, boundary conditions and load data, the finite element network model is respectively verified to obtain a finite element simulation model.

4. The method for predicting blast furnace movement performance based on data drive according to claim 1, characterized in that: The sensors described in step S5 include a wind speed sensor, an acceleration sensor, an inclination sensor, a laser displacement sensor and a strain force sensor, which are respectively used to collect wind speed data of the blast furnace body, acceleration data of the blast furnace body, inclination data of the blast furnace body, displacement transient response data of the blast furnace body and stress transient response data of the blast furnace push track.

5. The method for predicting blast furnace movement performance based on data drive according to claim 1, characterized in that: The cross-validation method described in step S6 uses 12-fold cross-validation, in which the machine learning data sample is divided into 12 equal parts, 11 parts of the machine learning data sample are selected as training samples for training, and the remaining part is tested. This process is repeated 12 times, and a different part is selected as the training data result each time.

6. The method for predicting blast furnace movement performance based on data drive according to claim 5, characterized in that: The training algorithm is a composite neural network, which integrates at least a CNN neural network, an RNN neural network, and a DBN neural network generation model based on restricted Boltzmann machines (RBMs). The training algorithm supports vector machines (SVMs) and combines a BP neural network algorithm, namely a back propagation algorithm.

7. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for predicting the blast furnace movement performance based on data drive described in any one of claims 1 to 6 is implemented.

8. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for predicting the blast furnace movement performance based on data drive described in any one of claims 1 to 6 is implemented.