A method and system for monitoring the preparation of seamless steel pipes

Abstract

The present application discloses a method and system for monitoring the preparation of seamless steel pipes. The method includes: obtaining the first billet raw material for the preparation of the first seamless steel pipe; obtaining the first raw material image information based on a camera; obtaining the first applied rolling force, the second applied rolling force, and the third applied rolling force; collecting the historical applied rolling force data set of the first billet raw material for preparation based on big data; training based on a rolling force evaluation model to obtain a first training result; obtaining second image information during the pipe rolling process according to the camera; uploading the first training result and the second image information to a steel pipe preparation monitoring system to dynamically monitor the pipe rolling process of the first billet raw material for preparation. This solves the technical problems in the prior art that the process of preparing seamless steel pipes is complex, the process of the pipe rolling link cannot be monitored in real time and dynamically, and further, the pipe rolling process parameters cannot be corrected in time, ultimately resulting in low quality of seamless steel pipe products.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence, and particularly to a method and system for monitoring the preparation of seamless steel pipes. Background Art

[0002] With the rapid development of the economy, the role of the steel industry in the national economy is becoming increasingly important. Among them, seamless steel pipes not only have economic characteristics, but also perform well in terms of service life and material quality. Therefore, the application demand is also increasing. They are widely used in various sectors such as automobiles, aviation, petroleum, chemical industry, construction, boilers, and military industries, playing an increasingly important role in the national economy and being called the blood vessels of industry.

[0003] With the continuous expansion of the application fields of seamless steel pipes, the requirements for product quality are getting higher and higher, especially in the application in high-tech fields such as aerospace. The demand for improving the quality of seamless steel pipes is becoming increasingly prominent. Many high-quality steel pipes in China need to be imported. Therefore, producing higher-quality steel pipes is an urgent problem to be solved.

[0004] In the process of implementing the technical solutions in the embodiments of this application, the inventors of this application found that the above technologies have at least the following technical problems:

[0005] In the prior art, the preparation process of seamless steel pipes is complex, it is difficult to monitor production manually, and the process of the pipe rolling link cannot be monitored in real time and dynamically. Furthermore, the process parameters of pipe rolling cannot be corrected in time, resulting in the technical problem of low quality of seamless steel pipe products. Summary of the Invention

[0006] In view of this, embodiments of the present application provide a method and system for monitoring the preparation of seamless steel pipes. The method includes: obtaining a first billet raw material for preparing a first seamless steel pipe; acquiring a holographic image of the first billet raw material based on a camera to obtain first raw material image information; obtaining a first applied rolling force, a second applied rolling force, and a third applied rolling force based on the first raw material image information, where the first applied rolling force and the second applied rolling force are rolling forces perpendicular to the moving direction of the first billet raw material, and the third applied rolling force is a rolling force parallel to the moving direction of the first billet raw material; collecting a historical dataset of applied rolling forces of the first billet raw material based on big data; inputting the first applied rolling force, the second applied rolling force, and the third applied rolling force into a rolling force evaluation model for training to obtain a first training result, where the rolling force evaluation model is formed by the historical dataset of applied rolling forces; obtaining second image information during the pipe rolling process based on the camera, where the second image information includes surface flatness information of the billet raw material; uploading the first training result and the second image information to a steel pipe preparation monitoring system to dynamically monitor the pipe rolling process of the first billet raw material. This solves the technical problems in the prior art that the process of preparing seamless steel pipes is complex, it is difficult to monitor production manually, and it is impossible to dynamically monitor the process of the pipe rolling link in real time. Furthermore, it is impossible to timely correct the process parameters of the pipe rolling, resulting in low quality of the finished seamless steel pipes. It achieves the technical effects of intelligently and dynamically monitoring the preparation process of seamless steel pipes, reducing the cost of manual supervision, realizing fast and accurate monitoring of the pipe rolling link, and further intelligently adjusting corresponding parameters based on the dynamic monitoring data, thereby reducing the scrap rate and improving the production efficiency of seamless steel pipes.

[0007] In view of the above problems, embodiments of the present application provide a method and system for monitoring the preparation of seamless steel pipes.

[0008] First aspect, the present application provides a method for monitoring the preparation of seamless steel pipes, which is realized through a monitoring system for the preparation of seamless steel pipes. Among them, the method includes: obtaining the first prepared billet raw material of the first seamless steel pipe; based on a camera, collecting holographic images of the first prepared billet raw material to obtain the first raw material image information; based on the first raw material image information, obtaining the first applied rolling force, the second applied rolling force, and the third applied rolling force, where the first applied rolling force and the second applied rolling force are rolling forces perpendicular to the moving direction of the first prepared billet raw material, and the third applied rolling force is a rolling force parallel to the moving direction of the first prepared billet raw material; based on big data, collecting the historical applied rolling force data set of the first prepared billet raw material; inputting the first applied rolling force, the second applied rolling force, and the third applied rolling force into a rolling force evaluation model for training to obtain a first training result, where the rolling force evaluation model is composed of the historical applied rolling force data set; according to the camera, obtaining the second image information during the pipe rolling process, and the second image information includes the surface flatness information of the billet raw material; uploading the first training result and the second image information to the steel pipe preparation monitoring system to dynamically monitor the pipe rolling process of the first prepared billet raw material.

[0009] On the other hand, the present application also provides a preparation monitoring system for seamless steel pipes, which is used to execute a preparation monitoring method for seamless steel pipes as described in the first aspect. Among them, the system includes: a first acquisition unit: the first acquisition unit is used to acquire the first prepared billet raw material of the first seamless steel pipe; a first acquisition unit: the first acquisition unit is used to perform holographic image acquisition on the first prepared billet raw material based on a camera to obtain first raw material image information; a second acquisition unit: the second acquisition unit is used to obtain a first applied rolling force, a second applied rolling force, and a third applied rolling force based on the first raw material image information, where the first applied rolling force and the second applied rolling force are rolling forces perpendicular to the moving direction of the first prepared billet raw material, and the third applied rolling force is a rolling force parallel to the moving direction of the first prepared billet raw material; a second acquisition unit: the second acquisition unit is used to collect a historical applied rolling force data set of the first prepared billet raw material based on big data; a third acquisition unit: the third acquisition unit is used to input the first applied rolling force, the second applied rolling force, and the third applied rolling force into a rolling force evaluation model for training to obtain a first training result, where the rolling force evaluation model is formed by the historical applied rolling force data set; a fourth acquisition unit: the fourth acquisition unit is used to obtain second image information of the pipe rolling process according to the camera, and the second image information includes the surface flatness information of the billet raw material; a first upload unit: the first upload unit is used to upload the first training result and the second image information to the steel pipe preparation monitoring system to dynamically monitor the pipe rolling process of the first prepared billet raw material.

[0010] In a third aspect, an embodiment of the present application also provides a preparation monitoring system for seamless steel pipes, including a memory, a processor, and a computer program stored on the memory and executable on the processor. Among them, when the processor executes the program, the steps of the method described in the first aspect are implemented.

[0011] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0012] 1. Obtain the first billet raw material for preparing the first seamless steel pipe; based on a camera, collect the holographic image of the first billet raw material for preparation to obtain the first raw material image information; based on the first raw material image information, obtain the first applied rolling force, the second applied rolling force, and the third applied rolling force, where the first applied rolling force and the second applied rolling force are rolling forces perpendicular to the moving direction of the first billet raw material for preparation, and the third applied rolling force is a rolling force parallel to the moving direction of the first billet raw material for preparation; based on big data, collect the historical applied rolling force data set of the first billet raw material for preparation; input the first applied rolling force, the second applied rolling force, and the third applied rolling force into the rolling force evaluation model for training to obtain the first training result, where the rolling force evaluation model is formed by the historical applied rolling force data set; according to the camera, obtain the second image information during the pipe rolling process, and the second image information includes the surface flatness information of the billet raw material; upload the first training result and the second image information to the steel pipe preparation monitoring system to dynamically monitor the pipe rolling process of the first billet raw material for preparation. It achieves the technical effect of intelligently and dynamically monitoring the preparation process of seamless steel pipes, reducing the cost of manual supervision, realizing rapid and accurate monitoring of each production link, and further intelligently adjusting the corresponding parameters based on the dynamic monitoring data, thereby reducing the rejection rate and improving the production efficiency of seamless steel pipes.

[0013] 2. Through the rolling force evaluation model, by training the rolling force evaluation model with data, the rolling force evaluation model processes the input data more accurately, and thus the output first training result is also more accurate, achieving the technical effect of accuracy and high efficiency.

[0014] 3. By separately analyzing the pipe rolling results of the upper and lower radii in the pipe rolling link of the first billet raw material for preparation, it is possible to quickly judge whether the pipe rolling is uniform, and further adjust the rolling forces in the dynamic pipe rolling link of the first applied rolling force and the second applied rolling force according to the rolling force difference information of the upper and lower radii in the pipe rolling link of the first billet raw material for preparation, achieving the technical effect of real-time monitoring and real-time adjustment of the pipe rolling process and obtaining a higher finished product rate.

[0015] The above description is only an overview of the technical solution of this application. In order to understand the technical means of this application more clearly, it can be implemented according to the content of the description. And in order to make the above and other purposes, features, and advantages of this application more obvious and understandable, the specific implementation manners of this application are specifically given below. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the accompanying drawings required for use in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only exemplary. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on the provided drawings.

[0017] Figure 1 It is a schematic flow chart of a method for monitoring the preparation of seamless steel pipes in an embodiment of the present application;

[0018] Figure 2 It is a schematic flow chart of obtaining the lower radius tube rolling result of the first prepared tube blank raw material in a method for monitoring the preparation of seamless steel pipes in an embodiment of the present application;

[0019] Figure 3 It is a schematic flow chart of adjusting the first applied rolling force or the second applied rolling force in a method for monitoring the preparation of seamless steel pipes in an embodiment of the present application;

[0020] Figure 4 It is a schematic flow chart of information fusion of the first tag information and the second tag information in a method for monitoring the preparation of seamless steel pipes in an embodiment of the present application;

[0021] Figure 5 It is a schematic structural diagram of a system for monitoring the preparation of seamless steel pipes in an embodiment of the present application;

[0022] Figure 6 It is a schematic structural diagram of an exemplary electronic device in an embodiment of the present application.

[0023] Explanation of reference numerals:

[0024] The first acquisition unit 11, the first acquisition unit 12, the second acquisition unit 13, the second acquisition unit 14, the third acquisition unit 15, the fourth acquisition unit 16, the first upload unit 17, the bus 300, the receiver 301, the processor 302, the transmitter 303, the memory 304, the bus interface 305. Detailed implementation manners

[0025] By providing a method and system for monitoring the preparation of seamless steel pipes in the embodiments of the present application, the technical problems existing in the prior art are solved, including the complex process of seamless steel pipe preparation, the great difficulty in manual monitoring of production, the inability to monitor the process of the tube rolling link in real time and dynamically, and further the inability to timely correct the tube rolling process parameters, ultimately resulting in low quality of seamless steel pipe products. The technical effects are achieved as follows: intelligent dynamic monitoring of the seamless steel pipe preparation process, reduction of the cost of manual supervision, realization of fast and accurate monitoring of the tube rolling link, and further intelligent adjustment of corresponding parameters based on dynamic monitoring data, thereby reducing the rejection rate and improving the production efficiency of seamless steel pipes.

[0026] Next, the technical solutions in the embodiments of the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. It should be understood that the present application is not limited by the exemplary embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application. Additionally, it should be noted that for the sake of description, only the parts related to the present application are shown in the accompanying drawings rather than all of them.

[0027] The general idea of the technical solution provided by the present application is as follows:

[0028] The present application provides a method for monitoring the preparation of seamless steel pipes, and the method is applied to a system for monitoring the preparation of seamless steel pipes. Among them, the method includes: obtaining the first prepared billet raw material of the first seamless steel pipe; based on a camera, performing holographic image acquisition on the first prepared billet raw material to obtain the first raw material image information; based on the first raw material image information, obtaining the first applied rolling force, the second applied rolling force, and the third applied rolling force, where the first applied rolling force and the second applied rolling force are rolling forces perpendicular to the moving direction of the first prepared billet raw material, and the third applied rolling force is a rolling force parallel to the moving direction of the first prepared billet raw material; based on big data, collecting the historical applied rolling force data set of the first prepared billet raw material; inputting the first applied rolling force, the second applied rolling force, and the third applied rolling force into a rolling force evaluation model for training to obtain a first training result, where the rolling force evaluation model is composed of the historical applied rolling force data set; according to the camera, obtaining the second image information during the pipe rolling process, and the second image information includes the surface flatness information of the billet raw material; uploading the first training result and the second image information to the steel pipe preparation monitoring system to dynamically monitor the pipe rolling process of the first prepared billet raw material.

[0029] After introducing the basic principle of the present application, the various non-limiting implementation manners of the present application will be specifically introduced below with reference to the accompanying drawings of the specification.

[0030] Embodiment 1

[0031] Please refer to the attached Figure 1 , the embodiment of the present application provides a method for monitoring the preparation of seamless steel pipes. Among them, the method is applied to a system for monitoring the preparation of seamless steel pipes, and the system for monitoring the preparation of seamless steel pipes is communicatively connected to a camera. The method specifically includes the following steps:

[0032] Step S100: Obtain the first prepared billet raw material of the first seamless steel pipe;

[0033] Specifically, the seamless steel pipe refers to a steel pipe without welds on its surface and is formed by piercing a whole round steel. The preparation monitoring method of the seamless steel pipe is a method based on the preparation monitoring system of the seamless steel pipe for intelligently and dynamically monitoring the process of the pipe rolling link in the preparation process of the seamless steel pipe. The first seamless steel pipe refers to seamless steel pipes produced by any production method, having any shape, and for any use. The first prepared billet raw material refers to any billet for preparing seamless steel pipes, usually a high-quality (or alloy) solid round steel as the billet. By obtaining the billet raw material of the seamless steel pipe, the technical effect of mastering the basic material of the seamless steel pipe is achieved.

[0034] Step S200: Based on a camera, perform holographic image acquisition on the first prepared billet raw material to obtain first raw material image information;

[0035] Specifically, use a camera communicatively connected to the preparation monitoring system of the seamless steel pipe to briefly understand the shape, characteristics, etc. of the first prepared billet raw material. Through holographic image acquisition of the first prepared billet raw material, the image information of the first prepared billet raw material, that is, the first raw material image information, can be obtained. The holographic image uses the principle of double-beam interference. By making the object beam and another beam coherent with the object beam (reference beam) generate an interference pattern, the phase can be "merged" onto it, so that the phase and amplitude can be simultaneously recorded on the photosensitive film, and a holographic image can be obtained. Through the camera, the acquisition of the billet raw material image is realized.

[0036] Step S300: Based on the first raw material image information, obtain a first applied rolling force, a second applied rolling force, and a third applied rolling force, where the first applied rolling force and the second applied rolling force are rolling forces perpendicular to the moving direction of the first prepared billet raw material, and the third applied rolling force is a rolling force parallel to the moving direction of the first prepared billet raw material;

[0037] Specifically, based on the first raw material image information of the first prepared billet raw material collected by the camera, the rolling force conditions in each direction of the first prepared billet raw material can be obtained. Among them, the rolling forces perpendicular to the moving direction of the first prepared billet raw material are the first applied rolling force and the second applied rolling force, and the rolling force parallel to the moving direction of the first prepared billet raw material is the third applied rolling force. By analyzing the first raw material image information, the rolling force conditions in each direction of the prepared billet raw material are clarified.

[0038] Step S400: Based on big data, collect the historical applied rolling force data set of the first prepared billet raw material;

[0039] Step S500: Input the first applied rolling force, the second applied rolling force, and the third applied rolling force into the rolling force evaluation model for training to obtain a first training result. The rolling force evaluation model is assembled from the historical applied rolling force data set.

[0040] Specifically, the big data is the recorded data of the rolling force conditions of each billet raw material used in the historical production of seamless steel pipes. Based on the big data, the detailed information of the historical applied rolling force of the billet raw material is statistically obtained, that is, the historical applied rolling force data set of the first prepared billet raw material. Inputting the first applied rolling force, the second applied rolling force, and the third applied rolling force of the historical applied rolling force of the billet raw material into the rolling force evaluation model for training can obtain the corresponding training result, that is, the first training result. Among them, the first applied rolling force and the second applied rolling force are rolling forces perpendicular to the moving direction of the first prepared billet raw material, and the third applied rolling force is a rolling force parallel to the moving direction of the first prepared billet raw material. The rolling force evaluation model is a neural network model, with the characteristics of a neural network model, which can continuously self-train and learn according to the training data and continuously self-correct. When the output information of the rolling force evaluation model reaches a predetermined accuracy / convergence state, the supervised learning process ends. By training the rolling force evaluation model with data, the rolling force evaluation model can process the input data more accurately, and thus the output first training result is also more accurate, achieving the technical effect of accurately obtaining data information and improving the intelligence of the evaluation result.

[0041] Step S600: Obtain second image information of the pipe rolling process according to the camera. The second image information includes the surface flatness information of the billet raw material.

[0042] Specifically, use the camera to collect images of the pipe rolling link in the first seamless steel pipe production process from multiple angles and distances again, and the image information of the first seamless steel pipe rolling can be obtained, that is, the second image information. The second image information includes the surface flatness information of the billet raw material. The production process of seamless steel pipes mainly includes piercing, pipe rolling, and reducing diameter. Among them, pipe rolling production is the second process in the production of seamless steel pipes. The continuous rolling production process of steel pipes is an intermittent production process with typical characteristics such as multiple time periods, multiple variables, and complex linear correlation relationships between variables, which makes the relationship between the quality of steel pipes and process variables relatively complex. Through the camera, the technical effect of intelligently collecting images of the pipe rolling link of seamless steel pipes is achieved.

[0043] Step S700: Upload the first training result and the second image information to the steel pipe preparation monitoring system to dynamically monitor the pipe rolling process of the first prepared billet raw material.

[0044] Specifically, the steel pipe preparation monitoring system, namely the preparation monitoring system for seamless steel pipes, uploads the training results of the rolling force evaluation model and the images of the seamless steel pipe rolling process to the steel pipe preparation monitoring system. The steel pipe preparation monitoring system can intelligently and dynamically monitor the rolling process of the first prepared billet raw material. The images of the rolling process in the preparation of the first seamless steel pipe are collected in real time through a camera, and the rolling force of the first prepared billet raw material in the rolling process is evaluated in real time based on the rolling force evaluation model, achieving the technical effect of dynamically monitoring the rolling process of the first prepared billet raw material.

[0045] Further, as shown in the appendix Figure 2 In the embodiment of the present application, step S800 further includes:

[0046] Step S810: Obtain a first rolling force evaluation result according to the first training result;

[0047] Step S820: Obtain the upper radius surface image information and the lower radius surface image information of the first prepared billet raw material according to the second image information, where the upper radius surface image information corresponds to the first applied rolling force, and the lower radius surface image information corresponds to the second applied rolling force;

[0048] Step S830: Obtain the upper radius rolling result of the first prepared billet raw material according to the upper radius surface image information and the first applied rolling force;

[0049] Step S840: Obtain the lower radius rolling result of the first prepared billet raw material according to the lower radius surface image information and the second applied rolling force;

[0050] Step S850: Adjust the first rolling force evaluation result according to the upper radius rolling result and the lower radius rolling result.

[0051] Specifically, according to the training result of the rolling force evaluation model, the rolling force of the first prepared billet raw material by the rolling force evaluation model, that is, the first rolling force evaluation result, can be obtained. Further, the image information of the rolling process in the preparation of the first seamless steel pipe collected by the camera is analyzed, and the image of the rolling process of the first prepared billet raw material is divided into upper radius surface image information and lower radius surface image information, where the upper radius surface image information corresponds to the first applied rolling force, and the lower radius surface image information corresponds to the second applied rolling force. Further analysis is performed on the upper radius surface image information and the lower radius surface image information respectively.

[0052] Based on the upper radius surface image information and the first applied rolling force corresponding to the upper radius surface image information, the upper radius tube rolling result of the first prepared tube blank material can be obtained. Based on the lower radius surface image information and the second applied rolling force corresponding to the lower radius surface image information, the lower radius tube rolling result of the first prepared tube blank material can be obtained. By comprehensively analyzing the upper radius tube rolling result and the lower radius tube rolling result, the training result of the rolling force evaluation model is adjusted, that is, the first rolling force evaluation result is comprehensively analyzed and adjusted.

[0053] By separately analyzing the first applied rolling force and the second applied rolling force received by the first prepared tube blank material based on the image information of the tube rolling process, the upper and lower radius tube rolling results of the first prepared tube blank material are obtained respectively. Further, by comprehensively analyzing, the overall tube rolling evaluation result of the first prepared tube blank material is obtained, and the training result of the rolling force evaluation model is further adjusted.

[0054] Further, as shown in the appendix Figure 3 it is shown that step S900 of the embodiment of the present application further includes:

[0055] Step S910: Determine whether the upper radius tube rolling result and / or the lower radius tube rolling result reach the preset tube rolling process result;

[0056] Step S920: If the upper radius tube rolling result or the lower radius tube rolling result reaches the preset tube rolling process result, obtain the first rolling force difference information between the first applied rolling force and the second applied rolling force;

[0057] Step S930: If the first rolling force difference information is positive, obtain a first evaluation result, where the first evaluation result includes that the first applied rolling force is greater than the second applied rolling force;

[0058] Step S940: If the first rolling force difference information is negative, obtain a second evaluation result, where the second evaluation result includes that the first applied rolling force is less than the second applied rolling force;

[0059] Step S950: Adjust the first applied rolling force or the second applied rolling force according to the first evaluation result or the second evaluation result.

[0060] Specifically, based on the application field of the first seamless steel pipe and the corresponding production requirements, the preparation results that each preparation link of the first seamless steel pipe should achieve are evaluated. The preset rolling pipe process result refers to the standard result of reaching the standard preset for the preparation result of the rolling pipe link of the first seamless steel pipe. Among them, judging whether the preparation result of the rolling pipe link of the first seamless steel pipe reaches the preset rolling pipe process result is a judgment of three situations: the first is to judge whether the upper radius rolling pipe result reaches the preset rolling pipe process result; the second is to judge whether the lower radius rolling pipe result reaches the preset rolling pipe process result; the third is to judge whether the upper radius rolling pipe result and the lower radius rolling pipe result reach the preset rolling pipe process result. The three judgment situations correspond to different judgment results.

[0061] When the upper radius rolling pipe result or the lower radius rolling pipe result reaches the preset rolling pipe process result, calculate the rolling force difference between the first applied rolling force corresponding to the upper radius rolling pipe result and the second applied rolling force corresponding to the lower radius rolling pipe result at this time, that is, the first rolling force difference information. Among them, when the first rolling force difference information is positive, it means that the first applied rolling force is greater than the second applied rolling force, and at this time, a first evaluation result is obtained; when the first rolling force difference information is negative, it means that the first applied rolling force is less than the second applied rolling force, and at this time, a second evaluation result is obtained. Further, according to the first evaluation result or the second evaluation result, adjust the first applied rolling force or the second applied rolling force so that the first applied rolling force or the second applied rolling force is the same, that is, adjust until the first rolling force difference information is 0.

[0062] By respectively analyzing the rolling pipe results of the upper and lower radii of the rolling pipe link of the first prepared billet raw material, it is possible to quickly judge whether the rolling pipe is uniform. Further, according to the rolling force difference information of the upper and lower radii of the rolling pipe link of the first prepared billet raw material, the first applied rolling force corresponding to the upper radius surface and the second applied rolling force corresponding to the lower radius surface of the first prepared billet raw material are adjusted for the rolling force of the dynamic rolling pipe link, achieving the technical effect of real-time monitoring of the rolling pipe process and real-time adjustment, and obtaining a higher finished product rate.

[0063] Further, step S910 of the embodiment of the present application further includes:

[0064] Step S911: If both the upper radius rolling pipe result and the lower radius rolling pipe result do not reach the preset rolling pipe process result, obtain the first moving speed information of the first prepared billet raw material under the third applied rolling force;

[0065] Step S912: Obtain the first influence parameter of the first moving speed information on the first applied rolling force, and the second influence parameter on the second applied rolling force;

[0066] Step S913: Obtain the first actual applied rolling force information based on the first applied rolling force and the first influencing parameter, and obtain the second actual applied rolling force information based on the second applied rolling force and the second influencing parameter;

[0067] Step S914: Input the first actual applied rolling force information, the second actual applied rolling force information, and the third applied rolling force into the rolling force evaluation model for secondary training to obtain a second training result;

[0068] Step S915: Compare the second training result with the first training result and adjust the first moving speed information.

[0069] Specifically, when both the upper radius pipe rolling result and the lower radius pipe rolling result do not reach the preset pipe rolling process result, the first prepared billet raw material is offset under the third applied rolling force, and the seamless steel pipe preparation monitoring system automatically obtains the speed at which the first prepared billet raw material is offset under the third applied rolling force, that is, the first moving speed information.

[0070] The seamless steel pipe preparation monitoring system intelligently analyzes the influence of the first moving speed information on the first applied rolling force and the second applied rolling force, that is, obtains the first influencing parameter and the second influencing parameter. Based on the influencing parameters, analyze the influence of the influencing parameters on the corresponding applied rolling forces respectively, that is, the influence of the first influencing parameter on the first applied rolling force, and the influence of the second influencing parameter on the second applied rolling force, to obtain the first actual applied rolling force information of the first applied rolling force under the first influencing parameter, and the second actual applied rolling force information of the second applied rolling force under the second influencing parameter.

[0071] Furthermore, input the first actual applied rolling force information, the second actual applied rolling force information, and the third applied rolling force into the rolling force evaluation model for secondary training to obtain a second training result. The rolling force evaluation model is a neural network model in machine learning. It reflects many basic characteristics of the human brain function. It is a deep feedforward neural network with characteristics such as local connection and weight sharing, and is a highly complex non-linear dynamic learning system. Compare the second training result with the first training result and make corresponding adjustments to the speed at which the first prepared billet raw material is offset under the third applied rolling force.

[0072] The rolling force evaluation model established based on the neural network model can output accurate training results, thus having strong analysis and calculation capabilities and achieving accurate and efficient technical effects.

[0073] Furthermore, step S915 of the embodiment of the present application further includes:

[0074] Step S9151: Traverse and parse the historical applied rolling force dataset to generate a preset rolling force distribution result;

[0075] Step S9152: Construct a Markov chain between the steel pipe moving speed and the training result of the rolling force evaluation model;

[0076] Step S9153: Based on the Markov chain, obtain the preset steel pipe moving speed information corresponding to the preset rolling force distribution result;

[0077] Step S9154: Adjust the first moving speed information according to the preset steel pipe moving speed information.

[0078] Specifically, traverse and parse the detailed information of the historical applied rolling force of the first prepared billet raw material to generate information on the rolling forces received by the rolling pipe environment of the prepared billet raw material that meets the preparation requirements, that is, the preset rolling force distribution result. Further, based on different steel pipe moving speeds, construct a Markov chain for the training results of the rolling force evaluation model at different steel pipe moving speeds. The Markov chain is a random process in probability theory and mathematical statistics that has the Markov property and exists in a discrete exponential set and state space. The Markov chain is a typical representative in the theory of random processes. It relies on using the current state of the system to infer the state of the system at the next equal time interval by solving the state transition matrix. Therefore, the advantage of the Markov theory is its memorylessness. The current state is independent of the historical state and is based on the next future state. The Markov chain is applicable to random systems with large randomness and obvious data fluctuations. Based on the Markov chain, obtain the preset steel pipe moving speed information corresponding to the preset rolling force distribution result, and adjust the first moving speed information accordingly according to the preset steel pipe moving speed information.

[0079] By constructing a Markov chain between the steel pipe moving speed and the training result of the rolling force evaluation model, the technical effect of dynamically adjusting the moving speed of the first prepared billet raw material under the third applied rolling force based on the preset steel pipe moving speed information is achieved.

[0080] Further, step S9153 of the embodiment of the present application further includes:

[0081] Step S91531: Determine a first mapping relationship according to the first moving speed information and the preset rolling force distribution result;

[0082] Step S91532: Construct a first state distribution database of the historical applied rolling force dataset according to the first mapping relationship;

[0083] Step S91533: Obtain the first probability of the steel pipe being at the first expected moving speed according to the first state distribution database.

[0084] Step S91534: Determine whether the first probability meets the first expected probability;

[0085] Step S91535: If the first probability meets the first expected probability, obtain the preset steel pipe moving speed information corresponding to the preset rolling force distribution result.

[0086] Specifically, based on the first moving speed information and the preset rolling force distribution result, determine the mapping relationship between the first moving speed information and the preset rolling force distribution result, that is, the first mapping relationship. Further, construct the offset situation of the first prepared billet raw material under each applied rolling force in the historical applied rolling force dataset. The applied rolling force data and the offset situation of the corresponding first prepared billet raw material in all historical data constitute the first state distribution database. According to the first state distribution database, based on the rolling force data information received by the first prepared billet raw material, obtain the probability that the corresponding steel pipe is at the first expected moving speed, that is, the first probability. Among them, the first expected moving speed refers to the speed at which the first prepared billet raw material should theoretically move based on the preparation requirements. Determine whether the first probability meets the first expected probability. If the first probability meets the first expected probability, the preparation monitoring system of the seamless steel pipe automatically obtains the preset steel pipe moving speed information corresponding to the preset rolling force distribution result. Among them, the preset steel pipe moving speed information refers to information such as the moving speed of the first seamless steel pipe rolling process based on the preparation requirements.

[0087] Based on the historical applied rolling force dataset of the first prepared billet raw material in the big data, analyze the moving situation of the first prepared billet raw material under the currently applied rolling force, achieving the technical effect of adjusting the rolling force received by the first prepared billet raw material to meet the preset steel pipe moving speed.

[0088] Further, as shown in the appendix Figure 4 The steps S1000 of the embodiment of the present application further include:

[0089] Step S1010: Perform feature marking on the first applied rolling force, the second applied rolling force, and the third applied rolling force, denoted as the first label information;

[0090] Step S1020: Perform feature marking on the second image information, denoted as the second label information;

[0091] Step S1030: Perform information fusion on the first label information and the second label information, and attach it to the prepared first seamless steel pipe for finished product verification.

[0092] Specifically, feature marking is performed on the first applied rolling force, the second applied rolling force, and the third applied rolling force, denoted as the first label information; feature marking is performed on the second image information of the first prepared tube blank raw material during the tube rolling process, denoted as the second label information. The first label information and the second label information are fused, and the fusion result is comprehensively analyzed and attached to the prepared first seamless steel tube for later finished product verification.

[0093] By recording the main process parameters of the tube rolling link of the first seamless steel tube and recording the main information on the finished product of the first seamless steel tube, the technical effect of facilitating the rapid verification of the tube rolling process during later finished product verification is achieved.

[0094] In summary, the embodiments of the present application have the following technical effects:

[0095] 1. By obtaining the first prepared tube blank raw material of the first seamless steel tube; based on a camera, performing holographic image acquisition on the first prepared tube blank raw material to obtain the first raw material image information; based on the first raw material image information, obtaining the first applied rolling force, the second applied rolling force, and the third applied rolling force, where the first applied rolling force and the second applied rolling force are rolling forces perpendicular to the moving direction of the first prepared tube blank raw material, and the third applied rolling force is a rolling force parallel to the moving direction of the first prepared tube blank raw material; based on big data, collecting the historical applied rolling force data set of the first prepared tube blank raw material; inputting the first applied rolling force, the second applied rolling force, and the third applied rolling force into the rolling force evaluation model for training to obtain the first training result, where the rolling force evaluation model is composed of the historical applied rolling force data set; according to the camera, obtaining the second image information of the tube rolling process, and the second image information includes the surface flatness information of the tube blank raw material; uploading the first training result and the second image information to the steel tube preparation monitoring system to dynamically monitor the tube rolling process of the first prepared tube blank raw material. The technical effect of intelligently and dynamically monitoring the preparation process of seamless steel tubes is achieved, the cost of manual supervision is reduced, rapid and accurate monitoring of each production link is realized, and corresponding parameters are intelligently adjusted based on the dynamic monitoring data, thereby reducing the scrap rate and improving the production efficiency of seamless steel tubes.

[0096] 2. Through the rolling force evaluation model, by performing data training on the rolling force evaluation model, the rolling force evaluation model processes input data more accurately, and thus the output first training result is also more accurate, achieving the technical effect of accuracy and high efficiency.

[0097] 3. By separately analyzing the tube rolling results of the upper and lower radii in the tube rolling process of the first prepared billet raw material, it is possible to quickly determine whether the tube rolling is uniform. Further, based on the rolling force difference information of the upper and lower radii in the tube rolling process of the first prepared billet raw material, the rolling force of the dynamic tube rolling process is adjusted for the first applied rolling force and the second applied rolling force, achieving the technical effect of real-time monitoring of the tube rolling process and real-time adjustment, and obtaining a higher finished product rate.

[0098] Embodiment 2

[0099] Based on the preparation monitoring method of a seamless steel pipe in the foregoing embodiment and the same inventive concept, the present invention also provides a preparation monitoring system for a seamless steel pipe. Please refer to the appendix Figure 5 , and the system includes:

[0100] The first acquisition unit 11: The first acquisition unit 11 is used to acquire the first prepared billet raw material of the first seamless steel pipe;

[0101] The first acquisition unit 12: The first acquisition unit 12 is used to acquire a holographic image of the first prepared billet raw material based on a camera, and obtain first raw material image information;

[0102] The second acquisition unit 13: The second acquisition unit 13 is used to obtain the first applied rolling force, the second applied rolling force, and the third applied rolling force based on the first raw material image information. Among them, the first applied rolling force and the second applied rolling force are rolling forces perpendicular to the moving direction of the first prepared billet raw material, and the third applied rolling force is a rolling force parallel to the moving direction of the first prepared billet raw material;

[0103] The second acquisition unit 14: The second acquisition unit 14 is used to collect a historical applied rolling force data set of the first prepared billet raw material based on big data;

[0104] The third acquisition unit 15: The third acquisition unit 15 is used to input the first applied rolling force, the second applied rolling force, and the third applied rolling force into a rolling force evaluation model for training to obtain a first training result, where the rolling force evaluation model is formed by the historical applied rolling force data set;

[0105] The fourth acquisition unit 16: The fourth acquisition unit 16 is used to obtain second image information of the tube rolling process based on the camera, and the second image information includes the surface flatness information of the billet raw material;

[0106] The first uploading unit 17: The first uploading unit 17 is used to upload the first training result and the second image information to the steel pipe preparation monitoring system to dynamically monitor the tube rolling process of the first prepared billet raw material.

[0107] Furthermore, the system further includes:

[0108] A fifth acquisition unit, configured to acquire a first rolling force evaluation result according to the first training result;

[0109] A sixth acquisition unit, configured to acquire the upper radius surface image information and the lower radius surface image information of the first prepared tube blank raw material according to the second image information, wherein the upper radius surface image information corresponds to the first applied rolling force, and the lower radius surface image information corresponds to the second applied rolling force;

[0110] A seventh acquisition unit, configured to acquire an upper radius tube rolling result of the first prepared tube blank raw material according to the upper radius surface image information and the first applied rolling force;

[0111] An eighth acquisition unit, configured to acquire a lower radius tube rolling result of the first prepared tube blank raw material according to the lower radius surface image information and the second applied rolling force;

[0112] A first adjustment unit, configured to adjust the first rolling force evaluation result according to the upper radius tube rolling result and the lower radius tube rolling result.

[0113] Further, the system further includes:

[0114] A first judgment unit, configured to judge whether the upper radius tube rolling result and / or the lower radius tube rolling result reaches a preset tube rolling process result;

[0115] A ninth acquisition unit, configured to acquire first rolling force difference information between the first applied rolling force and the second applied rolling force if the upper radius tube rolling result or the lower radius tube rolling result reaches the preset tube rolling process result;

[0116] A tenth acquisition unit, configured to acquire a first evaluation result if the first rolling force difference information is positive, where the first evaluation result includes that the first applied rolling force is greater than the second applied rolling force;

[0117] An eleventh acquisition unit, configured to acquire a second evaluation result if the first rolling force difference information is negative, where the second evaluation result includes that the first applied rolling force is less than the second applied rolling force;

[0118] A second adjustment unit, configured to adjust the first applied rolling force or the second applied rolling force according to the first evaluation result or the second evaluation result.

[0119] Further, the system further includes:

[0120] A twelfth acquisition unit, configured to acquire first moving speed information of the first prepared tube blank under the third applied rolling force if both the upper radius tube rolling result and the lower radius tube rolling result do not reach the preset tube rolling process result;

[0121] A thirteenth acquisition unit, configured to acquire a first influence parameter of the first moving speed information on the first applied rolling force and a second influence parameter on the second applied rolling force;

[0122] A fourteenth acquisition unit, configured to acquire first actual applied rolling force information according to the first applied rolling force and the first influence parameter, and acquire second actual applied rolling force information according to the second applied rolling force and the second influence parameter;

[0123] A fifteenth acquisition unit, configured to input the first actual applied rolling force information, the second actual applied rolling force information, and the third applied rolling force into the rolling force evaluation model for secondary training to obtain a second training result;

[0124] A third adjustment unit, configured to compare the second training result with the first training result and adjust the first moving speed information.

[0125] Further, the system further includes:

[0126] A first generation unit, configured to traverse and parse the historical applied rolling force data set to generate a preset rolling force distribution result;

[0127] A first construction unit, configured to construct a Markov chain between the steel pipe moving speed and the rolling force evaluation model training result;

[0128] A sixteenth acquisition unit, configured to acquire preset steel pipe moving speed information corresponding to the preset rolling force distribution result based on the Markov chain;

[0129] A fourth adjustment unit, configured to adjust the first moving speed information according to the preset steel pipe moving speed information.

[0130] Further, the system further includes:

[0131] A first determination unit, configured to determine a first mapping relationship according to the first moving speed information and the preset rolling force distribution result;

[0132] A second construction unit, which is used to construct a first state distribution database of the historical applied rolling force data set according to the first mapping relationship;

[0133] A seventeenth acquisition unit, which is used to acquire a first probability that the steel pipe is at a first expected moving speed according to the first state distribution database;

[0134] A first judgment unit, which is used to judge whether the first probability meets a first expected probability;

[0135] An eighteenth acquisition unit, which is used to acquire preset steel pipe moving speed information corresponding to the preset rolling force distribution result if the first probability meets the first expected probability.

[0136] Furthermore, the system further includes:

[0137] A first marking unit, which is used to perform feature marking on the first applied rolling force, the second applied rolling force, and the third applied rolling force, and record it as first label information;

[0138] A second marking unit, which is used to perform feature marking on the second image information, and record it as second label information;

[0139] A first fusion unit, which is used to perform information fusion on the first label information and the second label information, and attach it to the prepared first seamless steel pipe for finished product verification.

[0140] In this specification, each embodiment is described in a progressive manner. The key point of each embodiment is the difference from other embodiments. The Figure 1 previously described method for monitoring the preparation of a seamless steel pipe and specific examples in Embodiment 1 are equally applicable to the system for monitoring the preparation of a seamless steel pipe in this embodiment. Through the detailed description of the method for monitoring the preparation of a seamless steel pipe above, those skilled in the art can clearly know the system for monitoring the preparation of a seamless steel pipe in this embodiment. Therefore, for the sake of simplicity of the specification, it will not be described in detail here. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method part.

[0141] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0142] Exemplary electronic device

[0143] Reference is made below Figure 6 to describe the electronic device of the embodiments of the present application.

[0144] Figure 6 FIG. shows a schematic structural diagram of an electronic device according to an embodiment of the present application.

[0145] Based on the inventive concept of a method for monitoring the preparation of seamless steel pipes in the foregoing embodiment, the present invention further provides a system for monitoring the preparation of seamless steel pipes, on which a computer program is stored, and when the program is executed by a processor, the steps of any of the methods for monitoring the preparation of seamless steel pipes described above are implemented.

[0146] Wherein, in Figure 6 , the bus architecture (represented by bus 300), bus 300 may include any number of interconnected buses and bridges, and bus 300 links together various circuits including one or more processors represented by processor 302 and a memory represented by memory 304. Bus 300 may also link together various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art, and thus will not be further described herein. Bus interface 305 provides an interface between bus 300 and receiver 301 and transmitter 303. Receiver 301 and transmitter 303 may be the same element, i.e., a transceiver, which provides a unit for communicating with various other devices over a transmission medium.

[0147] Processor 302 is responsible for managing bus 300 and general processing, while memory 304 may be used to store data used by processor 302 when performing operations.

[0148] The present application provides a method for monitoring the preparation of seamless steel pipes. The method is applied to a monitoring system for the preparation of seamless steel pipes. The method includes: obtaining the first billet raw material for the preparation of the first seamless steel pipe; based on a camera, collecting holographic images of the first billet raw material for preparation to obtain first raw material image information; based on the first raw material image information, obtaining the first applied rolling force, the second applied rolling force, and the third applied rolling force, where the first applied rolling force and the second applied rolling force are rolling forces perpendicular to the moving direction of the first billet raw material for preparation, and the third applied rolling force is a rolling force parallel to the moving direction of the first billet raw material for preparation; based on big data, collecting a historical applied rolling force data set of the first billet raw material for preparation; inputting the first applied rolling force, the second applied rolling force, and the third applied rolling force into a rolling force evaluation model for training to obtain a first training result, where the rolling force evaluation model is formed by the historical applied rolling force data set; obtaining second image information of the pipe rolling process according to the camera, and the second image information includes surface flatness information of the billet raw material; uploading the first training result and the second image information to the steel pipe preparation monitoring system to dynamically monitor the pipe rolling process of the first billet raw material for preparation. It solves the technical problems in the prior art that the process of seamless steel pipe preparation is complex, it is difficult to monitor production manually, and it is impossible to dynamically monitor the process of the pipe rolling link in real time. Further, it is impossible to timely correct the pipe rolling process parameters, resulting in low quality of seamless steel pipe products. It achieves the technical effect of intelligently and dynamically monitoring the preparation process of seamless steel pipes, reducing the cost of manual supervision, realizing rapid and accurate monitoring of the pipe rolling link, and further intelligently adjusting corresponding parameters based on dynamic monitoring data, thereby reducing the rejection rate and improving the production efficiency of seamless steel pipes.

[0149] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a device, or a computer program product. Therefore, the present application can adopt the form of a complete software embodiment, a complete hardware embodiment, or an embodiment combining software and hardware aspects. In addition, the present application is in the form of a computer program product that can be implemented on one or more computer-usable storage media containing computer-usable program code. The computer-usable storage media include, but are not limited to: USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disk memories, compact disc read-only memories (CD-ROMs), optical memories, and other media that can store program code.

[0150] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable data processing devices to generate a machine, such that the instructions executed by the processors of the computer or other programmable data processing devices produce a system for implementing the functions specified in one or more flows Figure 1 or more flows and / or blocks Figure 1 or more blocks.

[0151] These computer program instructions can also be stored in a computer-readable memory capable of guiding a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including an instruction system that implements the functions specified in one or more flows Figure 1 or more flows and / or blocks Figure 1 or more blocks.

[0152] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operating steps are executed on the computer or other programmable device to generate a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more flows Figure 1 or more flows and / or blocks Figure 1 or more blocks. Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications to these embodiments once they learn the basic creative concepts. Therefore, the appended claims are intended to be construed as including the preferred embodiments and all changes and modifications falling within the scope of the present invention.

[0153] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these changes and modifications.

Claims

1. A preparation monitoring method for seamless steel pipes, which is applied to a preparation monitoring system for seamless steel pipes. The preparation monitoring system for seamless steel pipes is communicatively connected to a camera. Among them, The method includes: Obtaining the first prepared billet raw material of the first seamless steel pipe; Based on a camera, performing holographic image acquisition on the first prepared billet raw material to obtain the first raw material image information; Based on the first raw material image information, obtaining the first applied rolling force, the second applied rolling force, and the third applied rolling force, wherein the first applied rolling force and the second applied rolling force are rolling forces perpendicular to the moving direction of the first prepared billet raw material, and the third applied rolling force is a rolling force parallel to the moving direction of the first prepared billet raw material; Based on big data, collecting the historical applied rolling force data set of the first prepared billet raw material; Inputting the first applied rolling force, the second applied rolling force, and the third applied rolling force into a rolling force evaluation model for training to obtain a first training result, wherein the rolling force evaluation model is formed by the historical applied rolling force data set; According to the camera, obtaining the second image information of the pipe rolling process, and the second image information includes the surface flatness information of the billet raw material; Uploading the first training result and the second image information to a steel pipe preparation monitoring system to dynamically monitor the pipe rolling process of the first prepared billet raw material; The method further includes: Obtaining a first rolling force evaluation result according to the first training result; According to the second image information, obtaining the upper radius surface image information and the lower radius surface image information of the first prepared billet raw material, wherein the upper radius surface image information corresponds to the first applied rolling force, and the lower radius surface image information corresponds to the second applied rolling force; Obtaining the upper radius pipe rolling result of the first prepared billet raw material according to the upper radius surface image information and the first applied rolling force; Obtaining the lower radius pipe rolling result of the first prepared billet raw material according to the lower radius surface image information and the second applied rolling force; Adjusting the first rolling force evaluation result according to the upper radius pipe rolling result and the lower radius pipe rolling result.

2. The method according to claim 1, wherein The method further includes: Judging whether the upper radius pipe rolling result and / or the lower radius pipe rolling result reaches a preset pipe rolling process result; If the upper radius pipe rolling result or the lower radius pipe rolling result reaches the preset pipe rolling process result, obtaining the first rolling force difference information between the first applied rolling force and the second applied rolling force; If the first rolling force difference information is positive, obtaining a first evaluation result, and the first evaluation result includes that the first applied rolling force is greater than the second applied rolling force; If the first rolling force difference information is negative, obtaining a second evaluation result, and the second evaluation result includes that the first applied rolling force is less than the second applied rolling force; Adjusting the first applied rolling force or the second applied rolling force according to the first evaluation result or the second evaluation result.

3. The method according to claim 2, wherein The method further includes: If both the upper radius pipe rolling result and the lower radius pipe rolling result do not reach the preset pipe rolling process result, obtaining the first moving speed information of the first prepared billet raw material under the third applied rolling force; Obtain the first influence parameter of the first applied rolling force on the first moving speed information and the second influence parameter of the second applied rolling force on the first moving speed information; According to the first applied rolling force and the first influence parameter, obtain the first actual applied rolling force information, and according to the second applied rolling force and the second influence parameter, obtain the second actual applied rolling force information; Input the first actual applied rolling force information, the second actual applied rolling force information, and the third applied rolling force into the rolling force evaluation model for secondary training to obtain the second training result; Compare the second training result with the first training result and adjust the first moving speed information.

4. The method according to claim 3, wherein, The adjustment of the first moving speed information further includes: Traverse and analyze the historical applied rolling force data set to generate a preset rolling force distribution result; Construct a Markov chain between the steel pipe moving speed and the training result of the rolling force evaluation model; Based on the Markov chain, obtain the preset steel pipe moving speed information corresponding to the preset rolling force distribution result; Adjust the first moving speed information according to the preset steel pipe moving speed information.

5. The method according to claim 4, wherein, The obtaining of the preset steel pipe moving speed information corresponding to the preset rolling force distribution result further includes: Determine the first mapping relationship according to the first moving speed information and the preset rolling force distribution result; Construct the first state distribution database of the historical applied rolling force data set according to the first mapping relationship; Obtain the first probability of the steel pipe at the first expected moving speed according to the first state distribution database; Judge whether the first probability meets the first expected probability; If the first probability meets the first expected probability, obtain the preset steel pipe moving speed information corresponding to the preset rolling force distribution result.

6. The method according to claim 1, wherein, The method further includes: Perform feature marking on the first applied rolling force, the second applied rolling force, and the third applied rolling force, denoted as the first label information; Perform feature marking on the second image information, denoted as the second label information; Fuse the first label information and the second label information and attach them to the prepared first seamless steel pipe for finished product verification.

7. A preparation monitoring system for seamless steel pipes, wherein, The system includes: The first obtaining unit: The first obtaining unit is used to obtain the first prepared billet raw material of the first seamless steel pipe; The first acquisition unit: The first acquisition unit is used to perform holographic image acquisition on the first prepared billet raw material based on a camera to obtain the first raw material image information; The second obtaining unit: The second obtaining unit is used to obtain the first applied rolling force, the second applied rolling force, and the third applied rolling force based on the first raw material image information, where the first applied rolling force and the second applied rolling force are rolling forces perpendicular to the moving direction of the first prepared billet raw material, and the third applied rolling force is a rolling force parallel to the moving direction of the first prepared billet raw material; The second acquisition unit: The second acquisition unit is used to collect the historical applied rolling force data set of the first prepared billet raw material based on big data; The third obtaining unit: The third obtaining unit is configured to input the first applied rolling force, the second applied rolling force, and the third applied rolling force into a rolling force evaluation model for training to obtain a first training result, wherein the rolling force evaluation model is assembled from the historical applied rolling force data set; The fourth obtaining unit: The fourth obtaining unit is configured to obtain second image information of the pipe rolling process according to the camera, and the second image information includes the surface flatness information of the billet raw material; The first uploading unit: The first uploading unit is configured to upload the first training result and the second image information to a steel pipe preparation monitoring system to dynamically monitor the pipe rolling process of the first prepared billet raw material; The system further includes: A fifth obtaining unit, configured to obtain a first rolling force evaluation result according to the first training result; A sixth obtaining unit, configured to obtain the upper radius surface image information and the lower radius surface image information of the first prepared billet raw material according to the second image information, wherein the upper radius surface image information corresponds to the first applied rolling force, and the lower radius surface image information corresponds to the second applied rolling force; A seventh obtaining unit, configured to obtain an upper radius pipe rolling result of the first prepared billet raw material according to the upper radius surface image information and the first applied rolling force; An eighth obtaining unit, configured to obtain a lower radius pipe rolling result of the first prepared billet raw material according to the lower radius surface image information and the second applied rolling force; A first adjustment unit, configured to adjust the first rolling force evaluation result according to the upper radius pipe rolling result and the lower radius pipe rolling result.

8. A preparation monitoring system for seamless steel pipes, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein, When the processor executes the program, the steps of the method according to any one of claims 1 to 6 are implemented.

Images