Pierced billet size abnormity analysis method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of seamless steel tube size anomaly analysis, in particular to a pierced billet size anomaly analysis method and device, electronic equipment and a storage medium. Performing frequency domain feature analysis on the plurality of pierced billet size queues to obtain a plurality of main frequency feature values; performing data reconstruction on each first continuous rolling production parameter queue according to the plurality of main frequency characteristic values to obtain a plurality of second continuous rolling production parameter queues; and finally, according to the correlation between the plurality of second continuous rolling production parameter queues and the pierced billet size queue, determining the generation reason of the pierced billet size deviation. According to the method, the continuous rolling production parameter queue is subjected to frequency domain transformation and inverse transformation, the length of the continuous rolling production parameter queue is the same as that of the pierced billet size queue, the size data and the production parameter data are integrated, reason analysis is conducted, and therefore the reason analysis result is more accurate.

Description

Technical Field

[0001] The present invention relates to the technical field of seamless steel pipe size anomaly analysis, and particularly to a method, device, electronic device and storage medium for analyzing the size anomaly of a rough pipe. Background Art

[0002] A seamless steel pipe is a long steel bar with a hollow cross-section and no seams around it. The most commonly used production process is to heat a solid billet, pierce it through a piercing mill, and then roll it through a rolling mill and a series of other processes, so that the billet gradually becomes a seamless steel pipe with certain dimensions and precision. This method has high production efficiency and is suitable for producing large-diameter and thick-wall seamless steel pipes.

[0003] A rough pipe refers to a semi-finished seamless steel pipe that has been initially processed and formed through processes such as piercing and rolling, but has not yet undergone a finishing process, and plays a key transitional role in the entire seamless steel pipe manufacturing process. Common size anomalies of seamless steel pipe rough pipes include out-of-tolerance outer diameter, out-of-tolerance wall thickness, and out-of-tolerance length. For the reasons for size anomalies, the current main method is to classify the size anomalies, and based on the results of the size anomaly classification, make a probabilistic estimate of the reasons.

[0004] With the continuous upgrading of the production line, the traceability of seamless steel pipes has become stronger. For example, it is possible to trace the current and torque of the rolling mill motor during the production process of a certain seamless steel pipe. However, various parameters of the production equipment have not played their due role in analyzing the size anomalies of seamless steel pipes, resulting in inaccurate and non-specific analysis results of the reasons for rough pipe anomalies and poor production guiding significance.

[0005] Based on this, it is necessary to develop and design a method for analyzing the size anomalies of rough pipes. Summary of the Invention

[0006] Embodiments of the present invention provide a method, device, electronic device and storage medium for analyzing the size anomalies of rough pipes, which are used to solve the problem that the results obtained by analyzing the size anomalies relying on the size data of the rough pipes themselves in the prior art are inaccurate.

[0007] In a first aspect, embodiments of the present invention provide a method for analyzing the size anomalies of rough pipes, including: Obtaining a plurality of rough pipe size queues, where the rough pipe size queues are constructed based on size data obtained from multiple detection positions of the rough pipe, and multiple data in the rough pipe size queues correspond to the same detection item; Performing frequency domain feature analysis on the plurality of rough pipe size queues to obtain a plurality of main frequency feature values, where the main frequency feature values represent the frequency values where the fluctuation characteristics of the rough pipe size queues are located; Data reconstruction is performed on each first tandem rolling production parameter queue according to the multiple main frequency eigenvalues, and multiple second tandem rolling production parameter queues are obtained, where the length of the second tandem rolling production parameter queue is the same as the length of the dummy bar size queue; According to the correlation between the multiple second tandem rolling production parameter queues and the dummy bar size queue, the cause of the dummy bar size deviation is determined.

[0008] In a possible implementation manner, the obtaining of the multiple dummy bar size queues includes: Obtain the total length of the dummy bar; According to the total length, a preset number of detection reference points are set at equal intervals along the axial direction of the dummy bar; Based on each detection reference point, multiple size arrays are obtained, where each size array corresponds to a detection item, each size array includes a preset number of size data, and the multiple size arrays include a wall thickness array and / or an outer diameter array; For each detection item, according to the detection reference points corresponding to the size arrays, multiple arrays are arranged and constructed into a dummy bar size queue.

[0009] In a possible implementation manner, the frequency domain feature analysis of the multiple dummy bar size queues to obtain multiple main frequency eigenvalues includes: From the multiple dummy bar size queues, a dummy bar size queue is taken out traversally as the queue to be analyzed; Determine the upper limit value of the frequency for frequency domain analysis according to the total amount of data in the queue to be analyzed; Take the quotient of the upper limit value of the frequency and the total number of preset frequencies as the lower limit value of the frequency; Perform frequency domain feature extraction on the queue to be analyzed according to the upper limit value of the frequency and the lower limit value of the frequency, and obtain multiple first frequency domain values; Add the frequencies corresponding to the multiple maximum values among the multiple first frequency domain values to the main frequency feature array; If the traversal of the multiple dummy bar size queues is not completed, jump to the step of taking out a dummy bar size queue traversally from the multiple dummy bar size queues as the queue to be analyzed.

[0010] In a possible implementation manner, the performing of frequency domain feature extraction on the queue to be analyzed according to the upper limit value of the frequency and the lower limit value of the frequency to obtain multiple frequency domain values includes: Perform frequency domain feature extraction on the queue to be analyzed according to the first formula to obtain multiple first frequency domain values, where the first formula is:

[0011] In the formula, is the th first frequency domain value, is the total number of data in the queue to be analyzed, is the th data in the queue to be analyzed, is the natural constant, is the pi, is the lower limit value of the frequency, is the upper limit value of the frequency, is the base quantity, is the imaginary unit.

[0012] In a possible implementation manner, the data reconstruction of each first tandem rolling production parameter queue according to the multiple main frequency characteristic values to obtain multiple second tandem rolling production parameter queues includes: For each first tandem rolling production parameter queue, the following steps are respectively executed: Performing frequency domain feature extraction on the first tandem rolling production parameter queue according to the multiple main frequency characteristic values to obtain multiple second frequency domain values; According to the length of the raw tube size queue, performing inverse frequency domain transformation on the multiple second frequency domain values to obtain a second tandem rolling production parameter queue.

[0013] In a possible implementation manner, the performing inverse frequency domain transformation on the multiple second frequency domain values according to the length of the raw tube size queue to obtain a second tandem rolling production parameter queue includes: Performing inverse frequency domain transformation on the multiple second frequency domain values according to the second formula and the length of the raw tube size queue to obtain a second tandem rolling production parameter queue, where the second formula is:

[0014] In the formula, is the th data in the second tandem rolling production parameter queue, is the th second frequency domain value, is the total number of the second frequency domain values, is the natural constant, is the pi, is the lower limit value of the frequency when performing frequency domain main feature analysis on the raw tube size queue, is the th multiple frequency coefficient corresponding to the second frequency domain value, is the base quantity when performing frequency domain main feature analysis on the raw tube size queue, is the imaginary unit.

[0015] In a possible implementation manner, the determining the cause of the raw tube size deviation according to the correlation between the multiple second tandem rolling production parameter queues and the raw tube size queue includes: For each rough tube size queue, the following steps are respectively executed: Calculate the similarity between the rough tube size queue and the multiple second tandem rolling production parameter queues respectively, and construct a similarity vector by arranging the obtained multiple similarity values in a predetermined order; Find multiple reference vectors from multiple vector classes that are closest to the similarity vector; Take the vector class to which the majority of vectors in the multiple reference vectors belong as the target class; Take the deviation cause corresponding to the majority of vectors in the target class as the cause of the rough tube size deviation.

[0016] In a second aspect, an embodiment of the present invention provides a rough tube size anomaly analysis device for implementing the rough tube size anomaly analysis method described in the first aspect above or any possible implementation manner of the first aspect. The rough tube size anomaly analysis device includes: A rough tube size data acquisition module for acquiring multiple rough tube size queues, where the rough tube size queue is constructed according to size data obtained from multiple detection positions of the rough tube, and multiple data in the rough tube size queue correspond to the same detection item; A rough tube size volatility analysis module for performing frequency domain feature analysis on the multiple rough tube size queues to obtain multiple main frequency feature values, where the main frequency feature value represents the frequency value where the fluctuation characteristic of the rough tube size queue is located; A production parameter reconstruction module for respectively performing data reconstruction on each first tandem rolling production parameter queue according to the multiple main frequency feature values to obtain multiple second tandem rolling production parameter queues, where the length of the second tandem rolling production parameter queue is the same as the length of the rough tube size queue; And, A size deviation cause analysis module for determining the cause of the rough tube size deviation according to the correlation between the multiple second tandem rolling production parameter queues and the rough tube size queue.

[0017] In a third aspect, an embodiment of the present invention provides an electronic device including a memory and a processor. A computer program that can run on the processor is stored in the memory, and when the processor executes the computer program, the steps of the method described in the first aspect above or any possible implementation manner of the first aspect are implemented.

[0018] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps of the method described in the first aspect above or any possible implementation manner of the first aspect are implemented.

[0019] The beneficial effects of the embodiments of the present invention compared with the prior art are: An embodiment of the present invention discloses a method for analyzing abnormal sizes of semifinished pipes. First, a plurality of semifinished pipe size queues are obtained. Among them, the semifinished pipe size queues are constructed based on size data obtained from multiple detection positions of the semifinished pipes, and multiple data in the semifinished pipe size queues correspond to the same detection item. Then, frequency-domain feature analysis is performed on the plurality of semifinished pipe size queues to obtain a plurality of main frequency feature values. Among them, the main frequency feature value represents the frequency value where the fluctuation characteristics of the semifinished pipe size queue are located. Next, data reconstruction is performed on each first continuous rolling production parameter queue according to the plurality of main frequency feature values to obtain a plurality of second continuous rolling production parameter queues. Among them, the length of the second continuous rolling production parameter queue is the same as the length of the semifinished pipe size queue. Finally, according to the correlation between the plurality of second continuous rolling production parameter queues and the semifinished pipe size queues, the cause of the deviation of the semifinished pipe size is determined. By performing frequency-domain feature analysis on the semifinished pipe size queues, determining a plurality of main frequency features, and then performing frequency-domain transformation and inverse transformation on the continuous rolling production parameter queues according to the plurality of main frequency features, a continuous rolling production parameter queue with the same length as the semifinished pipe size queue is obtained. In this way, the length of the continuous rolling production parameter queue is the same as the length of the semifinished pipe size queue, and the main frequency features of the semifinished pipe size are retained. On this basis, similarity calculation is performed between the semifinished pipe size queue and the plurality of continuous rolling production parameter queues to construct a similarity vector, and a judgment on the cause of the deviation of the semifinished pipe size is made by referring to the reasons of the majority of vectors in the nearest class of the similarity vector. The method of the present invention combines size data and production parameter data for cause analysis, so the result of cause analysis is more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0021] Figure 1 is a flowchart of the method for analyzing abnormal sizes of semifinished pipes provided by the embodiment of the present invention; Figure 2 is a schematic diagram of the principle of the process for determining the cause of the deviation of the semifinished pipe size provided by the embodiment of the present invention; Figure 3 is a functional block diagram of the device for analyzing abnormal sizes of semifinished pipes provided by the embodiment of the present invention; Figure 4 is a functional block diagram of the electronic device provided by the embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present invention. However, those skilled in the art should clearly understand that the present invention can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, and methods are omitted to avoid unnecessary details from interfering with the description of the present invention.

[0023] To make the objectives, technical solutions, and advantages of the present invention clearer, the following will be described through specific embodiments in conjunction with the accompanying drawings.

[0024] The following provides a detailed description of the embodiments of the present invention. These embodiments are implemented on the premise of the technical solutions of the present invention, and detailed implementation manners and specific operation processes are given. However, the protection scope of the present invention is not limited to the following embodiments.

[0025] Figure 1 It is a flowchart of a method for analyzing abnormal sizes of rough tubes provided for the embodiments of the present invention.

[0026] As Figure 1 shown, it shows a flowchart for implementing a method for analyzing abnormal sizes of rough tubes provided for the embodiments of the present invention, which is described in detail as follows: In step 101, multiple rough tube size queues are obtained, where each rough tube size queue is constructed based on size data obtained from multiple detection positions of the rough tube, and multiple data in the rough tube size queue correspond to the same detection item.

[0027] In some embodiments, the obtaining of multiple rough tube size queues includes: Obtaining the total length of the rough tube; According to the total length, setting a preset number of detection reference points at equal intervals along the axial direction of the rough tube; Based on each detection reference point, obtaining multiple size arrays, where each size array corresponds to a detection item, each size array includes a preset number of size data, and the multiple size arrays include a wall thickness array and / or an outer diameter array; For each detection item, arranging and constructing multiple arrays according to the detection reference points corresponding to the size arrays to form a rough tube size queue.

[0028] Exemplarily, the rough tubes in the embodiments of the present invention are semi-finished seamless steel tubes that are rolled and formed by a continuous rolling device and have not been finely processed. Thanks to technological progress, the production parameters of the continuous rolling device during the production process of each rough tube can be obtained through traceability means.

[0029] As mentioned above, for the analysis of abnormal rough tube sizes, it is currently mainly carried out through the rough tube sizes themselves, and the given cause analysis conclusions usually point to a certain process, with problems of being not specific and inaccurate.

[0030] On the other hand, there are many technical difficulties in analyzing the causes of size anomalies through the production parameters of continuous rolling equipment. First of all, the production parameter data of continuous rolling equipment is complex and has a lot of data noise, which affects the results of anomaly analysis; secondly, the lengths of the production parameter data are different, and it is difficult to correspond to the sizes of the raw tubes.

[0031] In the present invention, from the aspect of size data, the raw tubes are divided into a predetermined number of detection reference points according to the total length of the raw tube size, and then multiple size detection data are obtained based on the detection reference points. For example, for the wall thickness detection item, multiple wall thickness values are obtained circumferentially based on the detection reference points, and these wall thickness values are constructed into an array. In this way, multiple arrays corresponding to multiple detection reference points are obtained. After the detection is completed, the multiple arrays of each detection item are arranged according to the positions of the reference points, and a raw tube size queue is obtained. By this means, the raw tube size data is arranged in a predetermined order, and a predetermined number of monitoring points are obtained.

[0032] In step 102, frequency domain feature analysis is performed on the multiple raw tube size queues to obtain multiple main frequency feature values, where the main frequency feature value represents the frequency value where the fluctuation characteristics of the raw tube size queue are located.

[0033] In some embodiments, the frequency domain feature analysis is performed on the multiple raw tube size queues to obtain multiple main frequency feature values, including: Traversingly take out a raw tube size queue from the multiple raw tube size queues as the queue to be analyzed; Determine the upper limit value of the frequency for frequency domain analysis according to the total amount of data in the queue to be analyzed; Take the quotient of the upper limit value of the frequency and the total number of preset frequencies as the lower limit value of the frequency; Perform frequency domain feature extraction on the queue to be analyzed according to the upper limit value of the frequency and the lower limit value of the frequency to obtain multiple first frequency domain values; Add the frequencies corresponding to the multiple maximum values among the multiple first frequency domain values to the main frequency feature array; If the traversal of the multiple raw tube size queues is not completed, jump to the step of traversingly taking out a raw tube size queue from the multiple raw tube size queues as the queue to be analyzed.

[0034] In some embodiments, the performing frequency domain feature extraction on the queue to be analyzed according to the upper limit value of the frequency and the lower limit value of the frequency to obtain multiple frequency domain values, including: Perform frequency domain feature extraction on the queue to be analyzed according to the first formula to obtain multiple first frequency domain values, where the first formula is:

[0035] In the formula, is the th first frequency domain value, is the total number of data in the queue to be analyzed, is the th data in the queue to be analyzed, is the natural constant, is the pi, is the lower limit value of frequency, is the upper limit value of frequency, is the base quantity, is the imaginary unit.

[0036] Exemplarily, in order to unify the production parameter data and the quantity of dimension data and eliminate the noise of the production parameter data, the present invention performs frequency domain feature analysis on the dimension data queue.

[0037] In terms of frequency domain feature analysis, the present invention determines an upper limit value of frequency for frequency analysis based on the total number of data in the raw pipe dimension queue. Generally, this upper limit value of frequency is less than half of the total number of data in the raw pipe dimension queue. Then, based on this upper limit value of frequency, multiple frequency values are determined with an integer as the divisor, that is, the upper limit value of frequency is an integer multiple of other frequency values. For example, the raw pipe dimension queue is constructed according to 10 arrays, and each array has 13 data. It can be known that the total number of data in the raw pipe dimension queue is 130. Then the upper limit value of frequency is less than 65, and the upper limit value is an integer multiple of the lower limit value. Combined with the number of data in the array, it is determined to be 5 (lower limit frequency).

[0038] Then, according to the upper limit value and the lower limit value of frequency, the raw pipe dimension queue is subjected to frequency domain feature extraction by using the first formula, and frequency domain values corresponding to multiple frequency values are obtained:

[0039] In the formula, is the th first frequency domain value, is the total number of data in the queue to be analyzed, is the th data in the queue to be analyzed, is the natural constant, is the pi, is the lower limit value of frequency, is the upper limit value of frequency, is the base quantity, is the imaginary unit.

[0040] For each billet size queue, multiple frequency domain values are obtained through the above formula. These frequency domain values reflect the volatility of the billet size data analyzed from the frequency domain direction. Select several main frequency domain values from these frequency domain values, and the corresponding frequencies are used as the main frequency characteristic values of the billet size queue. For example, in one selection method, the frequencies corresponding to the N frequency domain values with the largest values are selected as the main frequency characteristic values; in some other methods, the sum of all frequency domain values is calculated, a reference value is obtained through proportional calculation based on the sum, and then multiple largest frequency domain values are sequentially selected from the frequency domain values. The sum of these largest frequency domain values is greater than the reference value, and the frequencies corresponding to these largest frequency domain values are used as the main frequency characteristic values. After all billet size queues go through the above steps, the final multiple main frequency characteristic values are obtained.

[0041] In step 103, according to the multiple main frequency characteristic values, data reconstruction is performed on each first continuous rolling production parameter queue to obtain multiple second continuous rolling production parameter queues, where the length of the second continuous rolling production parameter queue is the same as that of the billet size queue.

[0042] In some embodiments, the data reconstruction is performed on each first continuous rolling production parameter queue according to the multiple main frequency characteristic values to obtain multiple second continuous rolling production parameter queues, including: For each first continuous rolling production parameter queue, the following steps are respectively executed: Frequency domain feature extraction is performed on the first continuous rolling production parameter queue according to the multiple main frequency characteristic values to obtain multiple second frequency domain values; According to the length of the billet size queue, inverse frequency domain transformation is performed on the multiple second frequency domain values to obtain the second continuous rolling production parameter queue.

[0043] In some embodiments, the inverse frequency domain transformation is performed on the multiple second frequency domain values according to the length of the billet size queue to obtain the second continuous rolling production parameter queue, including: According to the second formula and the length of the billet size queue, inverse frequency domain transformation is performed on the multiple second frequency domain values to obtain the second continuous rolling production parameter queue, where the second formula is:

[0044] In the formula, is the th data of the second continuous rolling production parameter queue, is the th second frequency domain value, is the total number of second frequency domain values, is the natural constant, is the pi, is the lower limit value of the frequency when performing frequency domain main feature analysis on the billet size queue, is the multiplication factor corresponding to the th second frequency domain value, is the base number when performing frequency domain main feature analysis on the raw pipe size queue, is the imaginary unit.

[0045] Exemplarily, the continuous rolling production parameter items generally include: continuous rolling inlet temperature, continuous rolling rolling force, roll motor speed, roll motor current, roll motor torque, mandrel carriage speed, mandrel carriage current, mandrel carriage torque, etc. It can be seen that the continuous rolling production parameters are a quantity that changes with time, and these quantities are closely related to the size of the raw pipe. The first continuous rolling production parameter queue is a data queue obtained based on these production parameters. As mentioned above, these data queues are noisy, and it is not easy to keep the data length unified with the raw pipe size queue, which brings difficulties to the abnormal analysis of the raw pipe size.

[0046] Therefore, the embodiment of the present invention performs frequency domain feature extraction on the first continuous rolling production parameter queue according to the multiple main frequency values obtained in the foregoing steps to obtain frequency domain values, and then obtains the second continuous rolling production parameter queue through inverse frequency domain transformation. Among them, the number of data in the obtained second continuous rolling production parameter queue is the same as the total number of data in the raw pipe size data queue. In terms of inverse transformation, the present invention applies the second formula:

[0047] In the formula, is the th data of the second continuous rolling production parameter queue, is the th second frequency domain value, is the total number of second frequency domain values, is the natural constant, is the pi, is the lower limit value of the frequency when performing frequency domain main feature analysis on the raw pipe size queue, is the th multiplication factor corresponding to the second frequency domain value, is the base number when performing frequency domain main feature analysis on the raw pipe size queue, is the imaginary unit.

[0048] In step 104, according to the correlation between the multiple second continuous rolling production parameter queues and the raw pipe size queue, the cause of the raw pipe size deviation is determined.

[0049] In some embodiments, the determining the cause of the raw pipe size deviation according to the correlation between the multiple second continuous rolling production parameter queues and the raw pipe size queue includes: For each raw pipe size queue, the following steps are respectively executed: Calculate the similarity between the raw tube size queue and the multiple second continuous rolling production parameter queues respectively, and construct the obtained multiple similarity values into a similarity vector in a predetermined order; Find multiple reference vectors from multiple vector classes that are closest to the similarity vector; Take the vector class to which the majority of vectors in the multiple reference vectors belong as the target class; Take the deviation cause corresponding to the majority of vectors in the target class as the cause of the raw tube size deviation.

[0050] Exemplarily, the similarity between the raw tube size queue and the multiple second continuous rolling production parameter queues is calculated, and the obtained similarity values are constructed into a similarity vector, which can reflect the correlation between the continuous rolling production parameters and the abnormality of the raw tube size.

[0051] As Figure 2 shown, the present invention first obtains some sample similarity vectors 202. The acquisition process of these sample similarity vectors 202 is the same as that of the above similarity vectors. Then, these sample similarity vectors 202 are clustered to obtain multiple vector classes 201. For a certain vector class 201, the majority of the sample similarity vectors 202 therein correspond to the same abnormal cause. For example, through clustering, vector classes C1 to Cn 201 are obtained. Among them, the cause of the majority of the sample similarity vectors 201 in the C1 vector class 201 is the skew of the mandrel, and the cause of the majority of the sample similarity vectors 202 in the C2 vector class 201 is the misalignment of the equipment. For the similarity vector 203 obtained by performing similarity calculation with the raw tube size queue, find a predetermined number of sample similarity vectors 202 that are closest from these vector classes 201. For example, find 3 sample similarity vectors 202 that are closest. Then, take the class to which the majority of these 3 sample similarity vectors 202 belong as the target class, and take the cause of the target class as the cause of the size abnormality.

[0052] Embodiment of the method for analyzing abnormal sizes of semifinished pipes in the present invention. First, a plurality of semifinished pipe size queues are obtained. Among them, the semifinished pipe size queues are constructed based on size data obtained from multiple detection positions of the semifinished pipes, and multiple data in the semifinished pipe size queues correspond to the same detection item. Then, frequency-domain feature analysis is performed on the plurality of semifinished pipe size queues to obtain a plurality of main frequency feature values. Among them, the main frequency feature value represents the frequency value where the fluctuation characteristics of the semifinished pipe size queue are located. Next, data reconstruction is performed on each first tandem rolling production parameter queue according to the plurality of main frequency feature values to obtain a plurality of second tandem rolling production parameter queues. Among them, the length of the second tandem rolling production parameter queue is the same as the length of the semifinished pipe size queue. Finally, according to the correlation between the plurality of second tandem rolling production parameter queues and the semifinished pipe size queues, the cause of the size deviation of the semifinished pipes is determined. In the embodiment of the present invention, by performing frequency-domain feature analysis on the semifinished pipe size queues, a plurality of main frequency features are determined. Then, according to the plurality of main frequency features, frequency-domain transformation and inverse transformation are performed on the tandem rolling production parameter queues to obtain tandem rolling production parameter queues with the same length as the semifinished pipe size queues. In this way, the length of the tandem rolling production parameter queues is the same as the length of the semifinished pipe size queues, and the main frequency features of the semifinished pipe sizes are retained. On this basis, similarity calculation is performed between the semifinished pipe size queues and the plurality of tandem rolling production parameter queues to construct a similarity vector, and a judgment on the cause of the size deviation of the semifinished pipes is made by referring to the reasons of the majority vectors in the nearest class of the similarity vector. The method of the present invention combines size data and production parameter data for cause analysis, so the cause analysis result is more accurate.

[0053] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution is prior or subsequent. The order of execution of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0054] The following is the device embodiment of the present invention. For the details not described in detail therein, reference can be made to the corresponding method embodiment above.

[0055] Figure 3 is the functional block diagram of the device for analyzing abnormal sizes of semifinished pipes provided by the embodiment of the present invention. Referring to Figure 3 , the device for analyzing abnormal sizes of semifinished pipes includes: a semifinished pipe size data acquisition module 301, a semifinished pipe size volatility analysis module 302, a production parameter reconstruction module 303, and a size deviation cause analysis module 304, where: The semifinished pipe size data acquisition module 301 is used to acquire a plurality of semifinished pipe size queues. Among them, the semifinished pipe size queues are constructed based on size data obtained from multiple detection positions of the semifinished pipes, and multiple data in the semifinished pipe size queues correspond to the same detection item; The rough tube size volatility analysis module 302 is used to perform frequency-domain feature analysis on the multiple rough tube size queues to obtain multiple main frequency feature values, where the main frequency feature value represents the frequency value where the volatility characteristics of the rough tube size queue are located; The production parameter reconstruction module 303 is used to perform data reconstruction on each first continuous rolling production parameter queue according to the multiple main frequency feature values to obtain multiple second continuous rolling production parameter queues, where the length of the second continuous rolling production parameter queue is the same as the length of the rough tube size queue; The size deviation cause analysis module 304 is used to determine the cause of the rough tube size deviation according to the correlation between the multiple second continuous rolling production parameter queues and the rough tube size queue.

[0056] Figure 4 It is a functional block diagram of the electronic device provided by the embodiment of the present invention. As Figure 4 shown, the electronic device 4 of this embodiment includes: a processor 400 and a memory 401, and a computer program 402 that can run on the processor 400 is stored in the memory 401. When the processor 400 executes the computer program 402, the steps in the above-mentioned various rough tube size anomaly analysis methods and embodiments are implemented, such as Figure 1 the steps 101 to 104 shown.

[0057] Exemplarily, the computer program 402 can be divided into one or more modules / units, and the one or more modules / units are stored in the memory 401 and executed by the processor 400 to complete the present invention.

[0058] The electronic device 4 can be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The electronic device 4 may include, but is not limited to, a processor 400 and a memory 401. Those skilled in the art can understand that Figure 4 it is only an example of the electronic device 4 and does not constitute a limitation on the electronic device 4. It may include more or fewer components than shown in the figure, or combine some components, or different components. For example, the electronic device 4 may further include input / output devices, network access devices, a bus, etc.

[0059] The so-called processor 400 may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0060] The memory 401 may be an internal storage unit of the electronic device 4, such as the hard disk or memory of the electronic device 4. The memory 401 may also be an external storage device of the electronic device 4, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, etc. equipped on the electronic device 4. Further, the memory 401 may also include both the internal storage unit and the external storage device of the electronic device 4. The memory 401 is used to store the computer program 402 and other programs and data required by the electronic device 4. The memory 401 may also be used to temporarily store data that has been output or is to be output.

[0061] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiments can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of this application. The specific working processes of the units and modules in the above system can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0062] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0063] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0064] In the embodiments provided by the present invention, it should be understood that the disclosed device / electronic device and method can be implemented in other ways. For example, the device / electronic device embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical or other forms.

[0065] The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they can be located in one place, or can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0066] In addition, the functional units in each embodiment of the present invention can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0067] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above-described embodiments of the method of the present invention, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-described various method and apparatus embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0068] The above-described embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for analyzing the abnormal size of waste pipes, characterized in that: include: Acquire multiple waste pipe size queues, wherein the waste pipe size queues are constructed according to size data obtained from multiple detection positions of the waste pipe, and multiple data in the waste pipe size queues correspond to the same detection item; Performing frequency domain characteristic analysis on the plurality of waste pipe size queues to obtain a plurality of main frequency characteristic values, wherein the main frequency characteristic values ​​represent frequency values ​​where fluctuation characteristics of the waste pipe size queues are located; Reconstructing data of each first continuous rolling production parameter queue according to the plurality of main frequency characteristic values ​​to obtain a plurality of second continuous rolling production parameter queues, wherein the length of the second continuous rolling production parameter queue is the same as the length of the waste pipe size queue; According to the correlation between the plurality of second continuous rolling production parameter queues and the waste pipe size queues, the cause of the waste pipe size deviation is determined.

2. The method for analyzing the abnormal size of waste pipes according to claim 1, characterized in that: The step of obtaining multiple queues of waste pipe sizes includes: Get the total length of the waste pipe; According to the total length, a preset number of detection reference points are set at equal intervals along the axial direction of the rough pipe; Acquire multiple dimension arrays based on each detection reference point, wherein each dimension array corresponds to a detection item, each dimension array includes a preset number of dimension data, and the multiple dimension arrays include a wall thickness array and / or an outer diameter array; For each detection item, multiple arrays are arranged according to the detection reference points corresponding to the size arrays to construct a rough pipe size queue.

3. The method for analyzing the abnormal size of waste pipes according to claim 1, characterized in that: The frequency domain characteristic analysis is performed on the multiple queues of waste pipe sizes to obtain multiple main frequency characteristic values, including: From the plurality of waste pipe size queues, traversally extract waste pipe size queues as queues to be analyzed; Determine the upper frequency limit of the frequency domain analysis according to the total amount of data in the queue to be analyzed; The quotient of the upper frequency limit value and the total number of preset frequencies is used as the lower frequency limit value; Perform frequency domain feature extraction on the queue to be analyzed according to the frequency upper limit value and the frequency lower limit value to obtain a plurality of first frequency domain values; Adding frequencies corresponding to multiple maximum values ​​among the multiple first frequency domain values ​​to a main frequency feature array; If the traversal of the plurality of waste pipe size queues is not completed, the process jumps to the step of traversing and taking out waste pipe size queues from the plurality of waste pipe size queues as queues to be analyzed.

4. The method for analyzing the abnormal size of waste pipes according to claim 3, characterized in that: The extracting frequency domain features of the queue to be analyzed according to the frequency upper limit value and the frequency lower limit value to obtain a plurality of first frequency domain values ​​includes: Frequency domain features are extracted from the queue to be analyzed according to a first formula to obtain a plurality of first frequency domain values, wherein the first formula is: In the formula, For the The first frequency domain value, is the total number of data in the queue to be analyzed, The queue to be analyzed data, is a natural constant, is the circumference of a circle, is the lower frequency limit, is the upper frequency limit, is the cardinality number, Is an imaginary unit.

5. The method for analyzing the abnormal size of waste pipes according to claim 1, characterized in that: The step of reconstructing data of each first continuous rolling production parameter queue according to the multiple main frequency characteristic values ​​to obtain multiple second continuous rolling production parameter queues includes: For each first continuous rolling production parameter queue, perform the following steps respectively: Performing frequency domain feature extraction on the first continuous rolling production parameter queue according to the multiple main frequency feature values ​​to obtain multiple second frequency domain values; According to the length of the waste pipe size queue, the multiple second frequency domain values ​​are subjected to an inverse frequency domain transformation to obtain a second continuous rolling production parameter queue.

6. The method for analyzing the abnormal size of waste pipes according to claim 5, characterized in that: The method of performing an inverse frequency domain transformation on the plurality of second frequency domain values ​​according to the length of the waste pipe size queue to obtain a second continuous rolling production parameter queue includes: According to the second formula and the length of the waste pipe size queue, the multiple second frequency domain values ​​are subjected to inverse frequency domain transformation to obtain the second continuous rolling production parameter queue, wherein the second formula is: In the formula, The second continuous rolling production parameter queue data, For the The second frequency domain value, is the total number of second frequency domain values, is a natural constant, is the circumference of a circle, is the lower frequency limit for frequency domain main characteristic analysis of the waste pipe size queue. For the The frequency multiplication coefficient corresponding to the second frequency domain value is is the cardinality number when performing frequency domain main feature analysis on the size queue of the waste pipe, Is an imaginary unit.

7. The method for analyzing the abnormal size of waste pipes according to any one of claims 1 to 6, characterized in that: The determining the cause of the waste pipe size deviation according to the correlation between the plurality of second continuous rolling production parameter queues and the waste pipe size queues includes: For each queue size, perform the following steps: Calculating the similarities between the waste pipe size queue and the plurality of second continuous rolling production parameter queues respectively, and arranging the obtained plurality of similarity values ​​in a predetermined order to construct a similarity vector; Finding multiple reference vectors closest to the similar vector from multiple vector classes; Taking the vector class to which the largest number of the plurality of reference vectors belongs as the target class; The deviation causes corresponding to the majority of vectors in the target class are taken as the causes of the deviation in the size of the waste pipe.

8. A device for analyzing the abnormal size of a waste pipe, characterized in that: Used to implement the method for analyzing the abnormal size of waste pipes according to any one of claims 1 to 7, the device for analyzing the abnormal size of waste pipes comprises: The waste pipe size data acquisition module is used to acquire multiple waste pipe size queues, wherein the waste pipe size queues are constructed according to the size data obtained from multiple detection positions of the waste pipe, and multiple data in the waste pipe size queues correspond to the same detection item; The waste pipe size fluctuation analysis module is used to perform frequency domain characteristic analysis on the plurality of waste pipe size queues to obtain a plurality of main frequency characteristic values, wherein the main frequency characteristic value represents the frequency value where the waste pipe size queue fluctuation characteristic is located; A production parameter reconstruction module, used for reconstructing data of each first continuous rolling production parameter queue according to the multiple main frequency characteristic values, to obtain multiple second continuous rolling production parameter queues, wherein the length of the second continuous rolling production parameter queue is the same as the length of the waste pipe size queue; as well as, The size deviation cause analysis module is used to determine the cause of the waste pipe size deviation according to the correlation between the multiple second continuous rolling production parameter queues and the waste pipe size queues.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method as claimed in any one of claims 1 to 7 are implemented.

Images