Movable horizontal continuous casting profile cutting equipment

Abstract

The invention relates to the technical field of cutting equipment, in particular to movable horizontal continuous casting profile cutting equipment which comprises a cutting equipment body and detection equipment, and the detection equipment comprises an infrared sensor, a vibration sensor and a detection processing module. The detection processing module is in communication connection with the infrared sensor and the vibration sensor to obtain an infrared image sequence and a vibration data sequence so as to carry out saw blade anomaly detection, and the saw blade anomaly detection process comprises the steps that the vibration data sequence is segmented, vibration segments are obtained, and vibration anomaly evaluation values of the vibration segments are determined; meanwhile, temperature identification is conducted on each infrared image in the infrared image sequence, and the abnormal high temperature representation degree of the saw blade in each infrared image is determined; and determining a saw blade abnormal index by combining the vibration abnormal evaluation value and the abnormal high-temperature expression degree, and further determining whether the saw blade is abnormal or not. According to the invention, the accuracy of abnormal detection of the saw blade of the cutting equipment is effectively improved.

Description

Technical Field

[0001] The invention relates to the technical field of cutting equipment, and in particular to a movable horizontal continuous casting profile cutting equipment. Background Art

[0002] With the continuous improvement of industrial automation, cutting equipment is increasingly used in metal material processing. Movable horizontal continuous casting profile cutting equipment is a kind of equipment specially used for cutting horizontal continuous casting profiles. It usually includes cutting frame, mobile wheel system, clamping device and cutting device. It is mobile and can be flexibly adjusted according to production needs. It is suitable for different production environments. The mobility and efficiency of horizontal continuous casting profile cutting equipment make it an indispensable part of modern industrial production, especially in occasions where frequent adjustment of production layout or improvement of production efficiency is required.

[0003] During the operation of the horizontal continuous casting profile cutting equipment, the wear of the saw blade in the cutting device and the deformation of the saw blade caused by the local temperature increase will directly affect the cutting quality of the horizontal continuous casting profile, so it is necessary to monitor the saw blade for abnormalities. In the prior art, the deformation of the saw blade is usually evaluated by manual experience when the machine is stopped, but this method is usually easily affected by subjective factors, the accuracy cannot be guaranteed, and it has a certain lag, and it can usually only be detected after the deformation is serious. Due to the wear of the saw blade and the deformation of the saw blade caused by the local temperature increase, the contact part of the saw blade is not sharp enough during cutting, which leads to abnormal vibration of the cutting device. Therefore, the saw blade vibration is monitored online, and the detected saw blade vibration signal is judged by the threshold comparison method to realize the saw blade abnormality detection, which can effectively avoid the lag of manual saw blade abnormality detection. However, since there may be certain differences in various parameters such as size and hardness between different batches of continuous casting profiles, there will be large differences in the monitored vibration signals. At the same time, when the pressure of the hydraulic module is inappropriate, it will also cause the cut material to shake during the cutting process, and then cause additional vibration abnormalities, which will lead to poor accuracy in detecting saw blade abnormalities by judging the monitored saw blade vibration signal through the threshold comparison method. Summary of the invention

[0004] The object of the present invention is to provide a movable horizontal continuous casting profile cutting device, which is used to solve the problem of inaccurate detection of abnormalities in the saw blade of the cutting device.

[0005] In order to solve the above technical problems, in the first aspect, the present invention provides a movable horizontal continuous casting profile cutting device, the cutting device comprises a cutting device body and a detection device, the detection device comprises an infrared sensor for detecting the surface temperature of a saw blade, a vibration sensor for detecting the vibration of the saw blade, and a detection processing module, the detection processing module is communicatively connected to the infrared sensor and the vibration sensor to obtain an infrared image sequence and a vibration data sequence, and performs saw blade abnormality detection according to the infrared image sequence and the vibration data sequence, the saw blade abnormality detection process comprises:

[0006] Segmenting the vibration data sequence to obtain individual vibration segments, and determining a vibration anomaly assessment value of each vibration segment according to fluctuation conditions of each vibration segment;

[0007] Performing temperature recognition on each infrared image in the infrared image sequence to determine the abnormal high temperature manifestation of the saw blade in each infrared image;

[0008] Determine the saw blade abnormality index according to the growth change of the vibration abnormality evaluation value and the growth change of the abnormal high temperature performance degree, and in combination with the magnitude of the vibration abnormality evaluation value and the abnormal high temperature performance degree near the current moment;

[0009] According to the saw blade abnormality indicator, it is determined whether there is a saw blade abnormality.

[0010] In combination with the first aspect above, in some possible implementations, determining the vibration anomaly assessment value of each vibration segment includes:

[0011] Determining a vibration mean value of each vibration segment according to an average distribution of vibration data in each vibration segment;

[0012] Determine a reference vibration segment in the vibration segments, and determine the vibration deviation between each vibration segment and the reference vibration segment according to the difference in vibration mean between each vibration segment and the reference vibration segment;

[0013] Determining an extreme value sequence of each vibration segment according to the extreme value distribution of the vibration data in each vibration segment;

[0014] Matching the extreme value sequence of each vibration segment with the extreme value sequence of the reference vibration segment, and determining the matching similarity index between each vibration segment and the reference vibration segment according to the matching result and in combination with the difference between each extreme value in the extreme value sequence of each vibration segment and the vibration mean of the reference vibration segment;

[0015] The vibration deviation and the matching similarity index are integrated to determine the vibration anomaly assessment value of each vibration segment.

[0016] In combination with the first aspect above, in some possible implementations, the extreme value sequence includes a maximum value sequence and a minimum value sequence, and determining a matching similarity index between each of the vibration segments and a reference vibration segment includes:

[0017] Taking the maximum value sequence and the minimum value sequence as a target extreme value sequence;

[0018] Matching the target extreme value sequence of each vibration segment with the target extreme value sequence corresponding to the reference vibration segment to obtain each extreme value matching pair;

[0019] Determine a sub-matching similarity index by comprehensively considering the matching distance between the extreme value points in each extreme value matching pair and the difference between each extreme value in the target extreme value sequence of each vibration segment and the vibration mean of the reference vibration segment;

[0020] The matching similarity index between each vibration segment and the reference vibration segment is determined by comprehensively analyzing the sub-matching similarity index corresponding to the maximum value sequence between each vibration segment and the reference vibration segment, and the sub-matching similarity index corresponding to the minimum value sequence between each vibration segment and the reference vibration segment.

[0021] In combination with the first aspect above, in some possible implementations, the first vibration segment among all the vibration segments is determined as a reference vibration segment.

[0022] In combination with the first aspect above, in some possible implementations, determining the abnormally high temperature manifestation of the saw blade in each infrared image includes:

[0023] Performing saw blade area segmentation on each infrared image in the infrared image sequence to obtain a saw blade area;

[0024] Segmenting the saw blade area to determine each abnormally high temperature area;

[0025] Determine a reference infrared image among all the infrared images in the infrared image sequence, and determine the abnormally high temperature expression of the saw blade in each infrared image based on the uniformity of grayscale distribution of the saw blade area in each infrared image in the infrared image sequence, the average distribution of grayscale values ​​in each abnormally high temperature area in the saw blade area, the area of ​​each abnormally high temperature area, and the difference in the average distribution of grayscale values ​​between the saw blade area in each infrared image in the infrared image sequence and the saw blade area of ​​the reference infrared image.

[0026] In combination with the first aspect above, in some possible implementations, determining the abnormally high temperature manifestation of the saw blade in each infrared image includes:

[0027] Determining a grayscale mean value of the saw blade area of ​​each infrared image in the infrared image sequence according to an average distribution of grayscale values ​​in the saw blade area of ​​each infrared image in the infrared image sequence;

[0028] Determining a grayscale difference index corresponding to each infrared image in the infrared image sequence according to a difference in grayscale mean between a saw blade region of each infrared image in the infrared image sequence and a saw blade region of the reference infrared image;

[0029] Determining the grayscale information entropy corresponding to each infrared image in the infrared image sequence according to the number of pixels with the same grayscale level in the saw blade area of ​​each infrared image in the infrared image sequence;

[0030] Determine the abnormal temperature representation value corresponding to each infrared image in the infrared image sequence by comprehensively analyzing the average distribution of gray values ​​in each abnormally high temperature area in the saw blade area of ​​each infrared image in the infrared image sequence and the area size of each abnormally high temperature area;

[0031] The grayscale difference index, grayscale information entropy and abnormal temperature expression value corresponding to each infrared image in the infrared image sequence are comprehensively considered to determine the abnormal high temperature expression degree of the saw blade in each infrared image.

[0032] In combination with the first aspect above, in some possible implementations, determining the saw blade abnormality index includes:

[0033] Determining an abnormal vibration growth value and an abnormal high temperature growth value according to the growth change of the vibration abnormality evaluation value and the growth change of the abnormal high temperature manifestation degree;

[0034] The saw blade abnormality index is determined based on the abnormal vibration growth value and the abnormal high temperature growth value, combined with the vibration abnormality evaluation value of the last vibration segment and the abnormal high temperature expression of the last infrared image in the infrared image sequence.

[0035] In combination with the first aspect above, in some possible implementations, determining the abnormal vibration growth value and the abnormal high temperature growth value includes:

[0036] Determine the difference in vibration anomaly assessment value between each subsequent vibration segment and its previous vibration segment in all the vibration segments, and use the normalized result of the mean of all the differences as the abnormal vibration growth value;

[0037] The difference in abnormal high temperature expression between each subsequent infrared image and the previous infrared image in the infrared image sequence is determined, and the normalized result of the mean of all the differences is used as the abnormal high temperature growth value.

[0038] In combination with the first aspect above, in some possible implementations, determining the saw blade abnormality index includes:

[0039] Determining a first abnormality index according to the vibration abnormality evaluation value of the last vibration segment and the abnormal vibration growth value;

[0040] determining a second abnormality indicator according to the abnormal high temperature expression degree of the last infrared image in the infrared image sequence and the abnormal high temperature growth value;

[0041] The saw blade abnormality index is determined by combining the first abnormality index and the second abnormality index.

[0042] In combination with the first aspect above, in some possible implementations, the saw blade abnormality detection process further includes: if there is a saw blade abnormality, replacing the current saw blade with a spare saw blade.

[0043] In order to solve the above technical problems, in a second aspect, the present invention also provides a saw blade abnormality detection method for a movable horizontal continuous casting profile cutting device, the method comprising:

[0044] Acquire an infrared image sequence and a vibration data sequence, wherein the infrared image of the infrared image sequence is obtained by detecting the surface temperature of the saw blade, and the vibration data in the vibration data sequence is obtained by detecting the vibration of the saw blade;

[0045] Segmenting the vibration data sequence to obtain individual vibration segments, and determining a vibration anomaly assessment value of each vibration segment according to fluctuation conditions of each vibration segment;

[0046] Performing temperature recognition on each infrared image in the infrared image sequence to determine the abnormal high temperature manifestation of the saw blade in each infrared image;

[0047] Determine the saw blade abnormality index according to the growth change of the vibration abnormality evaluation value and the growth change of the abnormal high temperature performance degree, and in combination with the magnitude of the vibration abnormality evaluation value and the abnormal high temperature performance degree near the current moment;

[0048] According to the saw blade abnormality indicator, it is determined whether there is a saw blade abnormality.

[0049] To solve the above technical problems, in a third aspect, the present invention further provides a saw blade anomaly detection system for a movable horizontal continuous casting profile cutting device, comprising a memory and a processor. The memory is used to store executable program code, and the processor is used to call and run the executable program code from the memory, so that the device executes the steps of the saw blade anomaly detection process in the above first aspect or any possible implementation of the first aspect.

[0050] To solve the above technical problems, in a fourth aspect, the present invention further provides a computer program product, which includes: a computer program code, which, when executed on a computer, enables the computer to execute the steps of the saw blade abnormality detection process in the above first aspect or any possible implementation of the first aspect.

[0051] To solve the above technical problems, in the fifth aspect, the present invention further provides a computer-readable storage medium, which stores a computer program code. When the computer program code runs on a computer, the computer executes the steps of the saw blade abnormality detection process in the above-mentioned first aspect or any possible implementation method of the first aspect.

[0052] The present invention has the following beneficial effects: an infrared image sequence is obtained by detecting the surface temperature of the saw blade, and a vibration data sequence is obtained by detecting the vibration of the saw blade; in order to facilitate subsequent joint analysis with the infrared image sequence, the vibration data sequence is segmented to obtain various vibration segments. When the saw blade is significantly worn and deformed, the contact part during cutting will not be sharp enough, and the contact part caused by the deformation will be subjected to uneven force, which will cause the corresponding vibration signal generated during the cutting process to have abnormal vibration. The specific abnormality is usually manifested as a high vibration amplitude and uneven moments corresponding to the high amplitude. Therefore, the vibration abnormality evaluation value of each vibration segment is determined according to the fluctuation of each vibration segment. At the same time, when a normal saw blade is cutting, the edge temperature of the saw blade increases significantly, and the temperature gradually becomes relatively low near the center of the circle, and the edge temperature of the saw blade is relatively uniform. Therefore, when the infrared image collected is not worn or deformed, the pixel value is usually more regular. When the edge of the saw blade is notched, worn, or deformed, the change in the contact area will cause the local temperature to be relatively higher than the normal area, which is reflected in the local highlight area in the converted grayscale image. Therefore, by performing temperature recognition on the saw blade area in each infrared image in the infrared image sequence, the abnormal high temperature expression of the saw blade in each infrared image can be determined. Considering that when the pressure of the hydraulic module is inappropriate, it will also cause the cutting material to shake during the cutting process, thereby causing additional vibration anomalies. However, when there is a real abnormality in the saw blade, its abnormal performance will become stronger and stronger with its continuous cutting. Therefore, in order to eliminate the interference caused by the vibration anomaly caused by the inappropriate pressure of the hydraulic module, it is necessary to further analyze the vibration anomaly evaluation value and the abnormal high temperature performance degree according to the growth change of the vibration anomaly evaluation value and the growth change of the abnormal high temperature performance degree, so as to obtain a more reliable optimized saw blade anomaly index, and finally determine whether there is a saw blade anomaly based on the saw blade anomaly index. Since the present invention detects the surface temperature and saw blade vibration of the saw blade during the operation of the cutting equipment, thereby obtaining an infrared image sequence and a vibration data sequence, and can adaptively determine an accurate saw blade anomaly index based on the infrared image sequence and the vibration data sequence, so as to accurately determine whether there is a saw blade anomaly, effectively improving the accuracy of the saw blade anomaly detection of the cutting equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0054] Figure 1 It is a structural schematic diagram of a movable horizontal continuous casting profile cutting device according to an embodiment of the present invention;

[0055] Figure 2 A first isometric schematic diagram of the overall structure of a cutting device according to an embodiment of the present invention;

[0056] Figure 3 A second isometric schematic diagram of the overall structure of the cutting device according to an embodiment of the present invention;

[0057] Figure 4 This is a schematic diagram of the state of the third cylinder when the cutting device according to the embodiment of the present invention is cutting;

[0058] Figure 5 A schematic diagram of the structure of a suction cup of a cutting device according to an embodiment of the present invention;

[0059] Figure 6 A schematic structural diagram of a first motor of a cutting device according to an embodiment of the present invention;

[0060] Figure 7 For the embodiment of the present invention Figure 6 A schematic diagram of the structure enlargement at the center A;

[0061] Figure 8 A flowchart of the process of detecting abnormality of a saw blade according to an embodiment of the present invention;

[0062] Fig. 9 A flowchart of the steps of determining the vibration abnormality evaluation value of each vibration segment according to an embodiment of the present invention;

[0063] Fig.10 A flowchart of the steps of determining the abnormal high temperature manifestation of the saw blade in each infrared image according to an embodiment of the present invention;

[0064] Fig.11 It is a structural schematic diagram of a saw blade anomaly detection system of a movable horizontal continuous casting profile cutting device according to an embodiment of the present invention;

[0065] Among them: 1 is a workbench; 2 is a slide rail; 3 is a mobile frame; 4 is a chain drive structure; 5 is a material transmission support frame; 6 is a first motor; 7 is a screw; 8 is a support rod; 9 is a first cylinder; 10 is a second motor; 11 is a saw blade; 12 is a support arm; 13 is a second cylinder; 14 is a fixed plate; 15 is a third motor; 16 is a sleeve; 17 is a suction cup; 18 is a mounting bolt; 19 is a third cylinder; 20 is a pressure plate; 21 is an infrared sensor; 22 is a vibration sensor. DETAILED DESCRIPTION

[0066] In order to clearly illustrate the technical features of the present invention, the present invention is described in detail below through specific implementation methods in conjunction with the accompanying drawings.

[0067] Embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present invention. It should be understood that the drawings and embodiments of the present invention are only for exemplary purposes and are not intended to limit the scope of protection of the present invention.

[0068] It should be understood that the various steps described in the method embodiments of the present invention may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.

[0069] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0070] It should be noted that the concepts such as "first" and "second" mentioned in the present invention are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0071] Although operations or steps are described in a specific order in the drawings in the embodiments of the present invention, it should not be understood that it is required to perform these operations or steps in the specific order shown or in a serial order, or that all the operations or steps shown must be performed to obtain the desired results. In the embodiments of the present invention, these operations or steps may be performed in series; these operations or steps may also be performed in parallel; or some of these operations or steps may be performed.

[0072] At the same time, it is understood that the data involved in the technical solution of the present invention (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of the relevant laws, regulations and relevant provisions. Unless otherwise defined, all technical and scientific terms used in the present invention have the same meanings as those generally understood by technicians in the technical field of the present invention, and all parameters or indicators in the formulas involved in the present invention are normalized values ​​that eliminate the influence of dimensions.

[0073] In order to solve the problem of inaccurate detection of saw blade abnormality of cutting equipment, an embodiment of the present invention provides a movable horizontal continuous casting profile cutting equipment, which includes a cutting equipment body and a detection equipment, the detection equipment includes an infrared sensor, a vibration sensor and a detection processing module, the infrared sensor and the vibration sensor are respectively used to detect the infrared image of the saw blade surface temperature and the vibration data of the saw blade vibration during the operation of the cutting equipment, the detection processing module is communicatively connected to the infrared sensor and the vibration sensor to obtain an infrared image sequence and a vibration data sequence, and analyzes the infrared image sequence and the vibration data sequence to evaluate the saw blade deformation and edge wear caused by high temperature during the continuous cutting process, determine the saw blade abnormality index, and finally determine whether there is a saw blade abnormality based on the saw blade abnormality index, thereby effectively improving the accuracy of saw blade abnormality detection and ensuring the cutting quality of the profile.

[0074] A movable horizontal continuous casting profile cutting device provided by an embodiment of the present invention will be described in detail below with reference to the accompanying drawings.

[0075] Figure 1 FIG. 1 shows a schematic structural diagram of a movable horizontal continuous casting profile cutting device provided by an embodiment of the present invention, such as Figure 1 As shown, the cutting device 0 includes a cutting device body 01 and a detection device 02, the detection device 02 includes an infrared sensor 21, a vibration sensor 22 and a detection processing module 05, and the detection processing module 05 is connected to the infrared sensor 21 and the vibration sensor 22 by wired or wireless communication. In the embodiment of the present invention, wireless communication is adopted.

[0076] Among them, the cutting equipment body 01 refers to the existing movable horizontal continuous casting profile cutting equipment. The movable horizontal continuous casting profile cutting equipment provided in the embodiment of the present invention is a movable horizontal continuous casting profile cutting equipment that adds a detection equipment 02 on the basis of the existing movable horizontal continuous casting profile cutting equipment to perform abnormal detection on the saw blade in the cutting device of the existing movable horizontal continuous casting profile cutting equipment.

[0077] Figure 2 and Figure 3 A first isometric schematic diagram and a second isometric schematic diagram of the overall structure of the movable horizontal continuous casting profile cutting device provided by an embodiment of the present invention are respectively given, Figure 4-Figure 6 A state schematic diagram of the third cylinder, a structural schematic diagram of the suction cup, and a structural schematic diagram of the first motor of the movable horizontal continuous casting profile cutting device provided by an embodiment of the present invention are respectively given. Figure 7 express Figure 6 A schematic diagram of the enlarged structure at point A in the middle.

[0078] Combined with the above Figure 2-Figure 7For the movable horizontal continuous casting profile cutting equipment provided by the embodiment of the present invention, a slide rail 2 and a material transfer support frame 5 are placed on the workbench 1, the continuous casting profile is placed on the material transfer support frame 5, and the cutting equipment is moved by the moving frame 3 and the chain drive structure 4, and is positioned manually. The first cylinder 9 and the third cylinder 15 are supported by the screw 7 and the support rod 8, and the third cylinder 19 is controlled by the first motor 6 to press the pressing plate 20 to fix the continuous casting profile, and then the first cylinder 9 is controlled by the first motor 6 to move horizontally and longitudinally, and the saw blade 11 is controlled by the second motor 10 to work, and the working state of the saw blade 11 is obtained by the infrared sensor 21 and the vibration sensor 22 to determine the wear.

[0079] When the saw blade 11 is determined to need to be replaced, the first motor 6 controls the third cylinder 19 to move the saw blade 11 to the second cylinder 13, two suction cups 17 are installed through the support arm 12 and the fixed plate 14, and the third motor 15 controls the second cylinder 13 to move the fixed plate forward, and the sleeve 16 is inserted into the mounting bolt 18 of the saw blade 11, the saw blade 11 is disassembled, and the saw blade is fixed by the suction cup 17, and the second cylinder is controlled to move backward again to complete the saw blade determination and replacement.

[0080] Since the movable horizontal continuous casting profile cutting equipment provided by the embodiment of the present invention focuses on the detection equipment 02, the detection equipment 02 will be introduced in detail below with reference to the accompanying drawings.

[0081] The infrared sensor 21 included in the detection device 02 is used to collect the surface infrared image of the saw blade when the saw blade is cutting (hereinafter referred to as the infrared image), and send the collected infrared image to the detection processing module 05. Figure 7 As shown, the infrared sensor 21 is installed in front of the saw blade, so that a complete infrared image of the saw blade surface can be obtained while avoiding sparks splashed during cutting. The set acquisition time interval of the infrared sensor 21 is 0.5s to 1s, that is, an infrared image of the saw blade is collected once every 0.5s to 1s. The embodiment of the present invention sets the acquisition time interval to 1s. It should be understood that the setting of the acquisition time interval needs to be determined based on the rotation speed of the saw blade, and it is necessary to ensure that the saw blade rotates a complete number of times every 1s to ensure that the same part of the saw blade is located in the same position in different images. For example, the cutting speed is set to 60 revolutions per second here.

[0082] like Figure 7As shown, the vibration sensor 22 included in the detection device 02 is installed at the servo motor of the connected saw blade of the existing movable horizontal continuous casting profile cutting device, and is used to collect vibration data generated by the saw blade during cutting, and the vibration data refers to amplitude data, and the collected vibration is sent to the detection processing module 05. The sampling frequency of the vibration sensor 22 is 10Hz-100Hz, that is, 10-100 vibration data are collected per second. The sampling frequency of the vibration sensor 22 is set to 100Hz in the embodiment of the present invention.

[0083] The detection device 02 includes a detection processing module 05 that receives infrared images and vibration data collected by the infrared sensor 21 and the vibration sensor 22, and arranges the acquired infrared images in chronological order with the start time of cutting as the starting point, thereby obtaining an infrared image sequence, and arranges the acquired vibration data in chronological order, thereby obtaining a vibration data sequence. It should be understood that the above-mentioned acquired infrared image sequence and vibration data sequence are both composed of infrared images and vibration data acquired during a continuous cutting process. The detection processing module 05 analyzes the infrared image sequence and vibration data sequence, performs saw blade abnormality detection, and when an abnormality is detected in the saw blade, the current saw blade is replaced with a spare saw blade.

[0084] The following will introduce the procedures for saw blade abnormality detection in combination with specific steps.

[0085] like Figure 8 As shown, the steps of detecting saw blade abnormality specifically include:

[0086] Step S100: segmenting the vibration data sequence to obtain vibration segments, and determining the vibration anomaly assessment value of each vibration segment according to the fluctuation of each vibration segment.

[0087] According to the set acquisition time interval of each infrared image in the infrared image sequence, the vibration data sequence is segmented to obtain each vibration segment. Since the set acquisition time interval is set to 1s in the embodiment of the present invention, a vibration segment and a corresponding infrared image can be obtained every 1s.

[0088] When the saw blade is obviously worn and deformed, the contact part during cutting will not be sharp enough, and the deformation will cause uneven force on the contact part, which will cause abnormal vibration in the vibration signal generated during the cutting process. The specific abnormality is usually manifested as high vibration amplitude and unevenness of the time corresponding to the high amplitude. Therefore, by analyzing the fluctuation of each vibration segment, the vibration abnormality evaluation value of each vibration segment can be evaluated.

[0089] When analyzing the fluctuation of each vibration segment, considering that the heating and wear of the saw blade are relatively weakest at the beginning of saw blade cutting, by comparing the subsequent vibration segments with the vibration segments at the beginning stage, when the vibration data of the subsequent vibration segments are higher than the average distribution of the vibration data of the vibration segments at the beginning stage, and the matching degree of the vibration segments is lower, it means that the subsequent vibration segments are more likely to have vibration abnormalities, thereby determining the vibration abnormality evaluation value of each vibration segment.

[0090] Further, in an embodiment of the present invention, if Fig. 9 As shown, the vibration anomaly evaluation value of each vibration segment is determined, and the implementation steps include:

[0091] Step S101: determining the vibration mean of each vibration segment according to the average distribution of vibration data in each vibration segment;

[0092] Step S102: determining a reference vibration segment in the vibration segment, and determining a vibration deviation between each vibration segment and the reference vibration segment according to a difference in vibration mean between each vibration segment and the reference vibration segment;

[0093] Step S103: determining an extreme value sequence of each vibration segment according to the extreme value distribution of the vibration data in each vibration segment;

[0094] Step S104: matching the extreme value sequence of each vibration segment with the extreme value sequence of the reference vibration segment, and determining the matching similarity index between each vibration segment and the reference vibration segment according to the matching result and in combination with the difference between each extreme value in the extreme value sequence of each vibration segment and the vibration mean of the reference vibration segment;

[0095] Step S105: integrating the vibration deviation and matching similarity index to determine the vibration anomaly assessment value of each vibration segment.

[0096] For the above steps, the mean is calculated based on all vibration data in each vibration segment to obtain the vibration mean. The first vibration segment among all vibration segments is used as the reference vibration segment, and the vibration mean of the reference vibration segment is used as the reference vibration mean, at which time the heating and wear of the saw blade are relatively weakest.

[0097] For any vibration segment after the first vibration segment, taking the nth vibration segment as an example, when n=1, it refers to the second vibration segment, and the difference between the vibration mean of the nth vibration segment and the vibration mean of the reference vibration segment, i.e., the reference vibration mean, is calculated, and the difference is used as the vibration deviation between the nth vibration segment and the reference vibration segment. Of course, for the first vibration segment, the corresponding vibration deviation is 0.

[0098] During the operation of the saw blade, each vibration segment is the vibration performance of a complete saw blade after multiple rotations. Therefore, if a local position of the saw blade is worn, chipped, or even deformed, the corresponding fixed position is rotating at a uniform speed, and the corresponding moments of the vibration data reflected in multiple vibration segments are the same. Therefore, based on this analysis, it is necessary to match the vibration data of each vibration segment with the reference vibration segment to determine whether the abnormal vibration corresponding to each extreme point is actual wear or defect.

[0099] Therefore, the maximum and minimum points corresponding to each vibration segment are determined, and the maximum sequence and the minimum sequence are constructed in chronological order. The maximum sequence and the minimum sequence are both extreme value sequences, thereby determining the two extreme value sequences corresponding to all vibration segments (including the first vibration segment).

[0100] For any vibration segment after the first vibration segment, taking the nth vibration segment as an example, and taking the maximum value sequence as a target extreme value sequence as an example, the absolute value of the difference between each extreme value (here refers to the maximum value) in the target extreme value sequence of the nth vibration segment and the vibration mean of the reference vibration segment, that is, the reference vibration mean, is calculated, and the norm function is used to linearly normalize the absolute value of the difference, and the normalized value is used as the matching weight of the extreme value point.

[0101] Then, the target extreme value sequence of the nth vibration segment is matched with the target extreme value sequence of the reference vibration segment by DTW. After DTW matching, each extreme value matching pair is obtained. Each extreme value matching pair is composed of two extreme value points located in the target extreme value sequence of the nth vibration segment and the target extreme value sequence of the reference vibration segment. The matching distance corresponding to each extreme value matching pair is determined. The matching distance refers to the absolute value of the difference between the two extreme value points in each extreme value matching pair. Since each extreme value point in the target extreme value sequence of the nth vibration segment has a corresponding matching weight, each extreme value matching pair here will also correspond to a matching weight. The matching weight is used as the weight of the matching distance of each extreme value matching pair. The matching distances of all extreme value matching pairs are weighted and accumulated, and the weighted accumulated value is negatively correlated and mapped, so as to obtain the sub-matching similarity index corresponding to the maximum value sequence between the nth vibration segment and the reference vibration segment. In the embodiment of the present invention, the reciprocal of the sum of the weighted cumulative value and the set adjustment parameter is taken to perform negative correlation mapping processing on the weighted cumulative value, and the obtained reciprocal is the sub-matching similarity index. The setting adjustment parameter is set to prevent the denominator from being 0. In the embodiment of the present invention, the value of the setting adjustment parameter can be set to 0.01.

[0102] In the above process of determining the sub-matching similarity index corresponding to the maximum value sequence between the nth vibration segment and the reference vibration segment, the matching weight of the extreme point is obtained by linearly normalizing the absolute value of the difference between each extreme value (here, the maximum value) in the target extreme value sequence of the nth vibration segment and the vibration mean of the reference vibration segment, that is, the reference vibration mean. The larger the matching weight, the greater the difference between the extreme point and the reference vibration mean, and the more likely the extreme point is to show abnormal vibration. Therefore, the corresponding matching distance is amplified, that is, the larger the reference weight, so a more accurate sub-matching similarity index can be obtained. At the same time, since the saw blade rotation behavior in each vibration segment is exactly the same under normal circumstances, after DTW matching, it can be determined that the local position of the saw blade corresponding to the cutting part causing the current vibration is the same. Therefore, when the sub-matching similarity index between the nth vibration segment and the reference vibration segment is smaller, the probability of new wear or deformation in the nth vibration segment is relatively greater than that in the reference vibration segment.

[0103] In the same manner as the above-mentioned determination of the sub-matching similarity index corresponding to the maximum value sequence between the nth vibration segment and the reference vibration segment, when the minimum value sequence is taken as an example of a target maximum value sequence, the sub-matching similarity index corresponding to the minimum value sequence between the nth vibration segment and the reference vibration segment can be determined. The sub-matching similarity index corresponding to the maximum value sequence between the nth vibration segment and the reference vibration segment and the average value of the sub-matching similarity index corresponding to the minimum value sequence between the nth vibration segment and the reference vibration segment are calculated, and the average value is used as the matching similarity index between the nth vibration segment and the reference vibration segment.

[0104] The matching similarity index between the nth vibration segment and the reference vibration segment is used as a weight, and the vibration deviation between the nth vibration segment and the reference vibration segment is used as a base value and multiplied by the weight to obtain the vibration anomaly evaluation value of the nth vibration segment. The larger the vibration anomaly evaluation value is, the more it is considered that the vibration of the saw blade in the nth vibration segment is relatively more unstable than the first vibration segment, and the vibration caused by the same local position of the saw blade during cutting is different.

[0105] It should be understood that, for the first vibration segment, since it is itself a reference vibration segment, its corresponding vibration deviation is 0, and therefore the vibration abnormality evaluation value of the first vibration segment is 0.

[0106] Step S200: performing temperature recognition on each infrared image in the infrared image sequence to determine the abnormal high temperature manifestation of the saw blade in each infrared image.

[0107] When a normal saw blade is cutting, the edge temperature of the saw blade increases significantly, and the temperature gradually becomes relatively low near the center of the circle, and the edge temperature of the saw blade is relatively uniform. Therefore, when the infrared image collected is not worn or deformed, the pixel value is usually more regular. When the edge of the saw blade is notched, worn, or deformed, the change in the contact area will cause the local temperature to be relatively higher than the normal area, which is reflected in the local highlight area in the converted grayscale image. Therefore, by performing temperature recognition on the saw blade area in each infrared image in the infrared image sequence, the abnormal high temperature expression of the saw blade in each infrared image can be determined.

[0108] Further, in an embodiment of the present invention, if Fig.10 As shown, the abnormal high temperature manifestation of the saw blade in each infrared image is determined, and the implementation steps include:

[0109] Step S201: performing saw blade area segmentation on each infrared image in the infrared image sequence to obtain a saw blade area;

[0110] Step S202: segmenting the saw blade area to determine each abnormally high temperature area;

[0111] Step S203: Determine a baseline infrared image among all the infrared images in the infrared image sequence, comprehensively consider the uniformity of grayscale distribution of the saw blade area in each infrared image in the infrared image sequence, the average distribution of grayscale values ​​in each abnormally high temperature area in the saw blade area, the area of ​​each abnormally high temperature area, and the difference in average grayscale values ​​between the saw blade area in each infrared image in the infrared image sequence and the saw blade area in the baseline infrared image, and determine the abnormally high temperature expression of the saw blade in each infrared image.

[0112] For the above steps, for each infrared image in the infrared image sequence, the infrared image is first converted into a grayscale image, and the infrared image converted into a grayscale image is preliminarily segmented to segment the saw blade area. In order to determine whether there is local high heat at the edge of the saw blade due to deformation, wear and other problems, the saw blade area needs to be further analyzed. When the saw blade is cutting, the edge temperature increases significantly, and then transfers to the inside of the saw blade that is not in direct contact with the material. Therefore, the temperature in the captured infrared image usually decreases from the edge to the center of the circle, and the local overheating caused by deformation, wear and other problems is also confused with the temperature of the edge itself. Therefore, based on this situation, it is necessary to analyze the temperature performance of the saw blade edge.

[0113] Therefore, for the saw blade area of ​​each infrared image in the infrared image sequence, the Otsu threshold segmentation method is used to segment the saw blade area to obtain the high grayscale area in the current saw blade area, and the high grayscale area is segmented again by the Otsu threshold segmentation method to obtain each high grayscale pixel point, and the high grayscale pixel point is referred to as an abnormally high temperature pixel point, and the abnormally high temperature pixel point is connected to determine the domain, so as to obtain each connected domain, and each connected domain obtained is each abnormally high temperature area. When determining the connected domain of the abnormally high temperature pixel point, it is determined whether there are other abnormally high temperature pixels in the eight neighborhoods of each abnormally high temperature pixel point. If so, each abnormally high temperature pixel point and other abnormally high temperature pixels in its eight neighborhoods are merged into the same connected domain, so as to obtain each connected domain. In the above process of obtaining each abnormally high temperature area, since the Otsu threshold segmentation method considers the overall image and obtains the best segmentation threshold in the overall image, the difference between the high temperature area and the abnormally high temperature area is usually not large enough compared to the center of the saw blade, that is, the abnormally high temperature area is not so obvious in the overall saw blade area image through statistical means. Therefore, it is necessary to first use the Otsu threshold segmentation method to segment the saw blade area to obtain a high grayscale area. Since the abnormally high temperature area will be relatively obvious in the high temperature area, the Otsu threshold segmentation method is used to segment the high grayscale area, so as to finally obtain the abnormally high temperature area.

[0114] According to the above method, each abnormally high temperature area in the saw blade area of ​​all infrared images in the infrared image sequence can be determined. Based on the actual situation corresponding to deformation and severe wear, the area is usually not very small, so a screening threshold is set to eliminate the abnormally high temperature area with a number of pixels less than the set screening threshold, thereby obtaining the final abnormally high temperature areas. The screening threshold can be reasonably set according to the actual situation. The embodiment of the present invention sets the value of the screening threshold to 10.

[0115] The first infrared image among all the infrared images in the infrared image sequence is taken as the reference infrared image. The heating and wear of the saw blade corresponding to the reference infrared image are relatively weak. For any infrared image after the first infrared image, taking the nth infrared image as an example, when n=1, it refers to the second infrared image. The average distribution of the grayscale values ​​of the saw blade area of ​​the nth infrared image is compared with the average distribution of the grayscale values ​​of the saw blade area of ​​the reference infrared image. When the average distribution of the grayscale values ​​of the saw blade area of ​​the nth infrared image is at least greater than the average distribution of the grayscale values ​​of the saw blade area of ​​the reference infrared image, it can be considered that there may be a higher possible abnormal temperature, and then it is considered that the abnormal high temperature is caused by abnormal conditions such as wear and deformation, and the higher the temperature, the higher the possibility. At the same time, the better the uniformity of the grayscale distribution of the saw blade area of ​​the nth infrared image, that is, the worse the concentration of the grayscale distribution, it means that the temperature of the saw blade at this time has multiple different amplitudes and changes greatly, and then compared with the normal saw blade, its temperature performance may have local high temperature caused by defects, deformation, etc. Moreover, the higher the average distribution of grayscale values ​​in each abnormally high temperature area of ​​the saw blade area of ​​the nth infrared image and the larger the area of ​​each abnormally high temperature area, it means that the current high temperature area still shows a large local high temperature, and the local high temperature is more likely to be caused by local abnormality.

[0116] Based on the above analysis, by comprehensively analyzing the uniformity of the grayscale distribution of the saw blade area in each infrared image in the infrared image sequence, the average distribution of grayscale values ​​in each abnormally high temperature area in the saw blade area, the area size of each abnormally high temperature area, and the difference in the average grayscale values ​​between the saw blade area in each infrared image in the infrared image sequence and the saw blade area in the baseline infrared image, the abnormally high temperature expression of the saw blade in each infrared image can be determined.

[0117] In an embodiment of the present invention, for each infrared image in the infrared image sequence, the average value of the grayscale value in the saw blade area of ​​the infrared image is determined to obtain the grayscale mean. The grayscale mean corresponding to the reference infrared image is used as the reference grayscale mean. Similarly, taking the nth infrared image as an example, the grayscale difference index corresponding to the nth infrared image is determined according to the difference between the grayscale mean corresponding to the nth infrared image and the grayscale mean corresponding to the reference infrared image. The number of pixels with the same grayscale level in the saw blade area of ​​the nth infrared image is determined to determine the information entropy, and the information entropy is called grayscale information entropy. At the same time, the average value of the grayscale value in each abnormally high temperature area in the saw blade area of ​​the nth infrared image is determined to obtain the average grayscale value, and the number of pixels in each abnormally high temperature area is normalized to obtain the normalized area area. In an embodiment of the present invention, the number of pixels in each abnormally high temperature area is normalized using the norm function to obtain the normalized area area.

[0118] Finally, based on the grayscale difference index and grayscale information entropy corresponding to the nth infrared image, as well as the normalized area and average grayscale value corresponding to each abnormally high temperature area in the saw blade area, the abnormal high temperature expression of the saw blade in each infrared image can be determined.

[0119] In the embodiment of the present invention, the abnormal high temperature manifestation of the saw blade in each infrared image is determined, and the corresponding calculation formula is:

[0120]

[0121] Among them, T n Indicates the abnormal high temperature performance of the saw blade in the nth infrared image; a n represents the grayscale difference index corresponding to the nth infrared image; w n represents the grayscale mean value corresponding to the nth infrared image; w 0 represents the grayscale mean value corresponding to the reference infrared image; b n represents the grayscale information entropy corresponding to the nth infrared image; t nm represents the average gray value corresponding to the mth abnormally high temperature area in the saw blade area of ​​the nth infrared image; s ′ nm represents the normalized area corresponding to the mth abnormally high temperature region in the saw blade area of ​​the nth infrared image; M represents the total number of abnormally high temperature regions in the saw blade area of ​​the nth infrared image.

[0122] In the above calculation formula, the grayscale difference index a n It reflects the temperature basic performance of the nth infrared image. When the temperature basic performance is large, if the grayscale information entropy b n The larger the value of is, the more it is considered that the temperature of the saw blade at this time has multiple different amplitudes, and thus compared with the normal saw blade, its temperature performance may have local high temperature caused by defects, deformation, etc. The larger the average grayscale value and normalized area corresponding to each abnormally high temperature area in the saw blade area of ​​the nth infrared image, the more likely it is that the saw blade area is caused by a large local high temperature when the temperature base performance is large. Therefore, the product of the average grayscale value and the normalized area corresponding to each abnormally high temperature area is accumulated to obtain the abnormal temperature performance value, and the grayscale difference index and the grayscale information entropy are regarded as the abnormal temperature performance value as the sensitivity of the saw blade area of ​​the nth infrared image to the possibility of abnormality, so as to finally obtain the abnormal high temperature performance degree of the saw blade in the nth infrared image. The larger the value of the abnormal high temperature performance degree is, the greater the possibility of abnormal high temperature performance of the current saw blade collected by the infrared sensor 21.

[0123] Step S300: Determine the saw blade abnormality index according to the growth change of the vibration abnormality evaluation value and the growth change of the abnormal high temperature performance degree, and in combination with the magnitude of the vibration abnormality evaluation value and the abnormal high temperature performance degree near the current moment.

[0124] Taking into account that when the pressure of the hydraulic module is inappropriate, it will also cause the cutting material to shake during the cutting process, and then cause additional vibration abnormalities. However, when there is a real abnormality in the saw blade, its abnormal performance will become stronger and stronger with its continuous cutting. Therefore, in order to eliminate the interference of vibration abnormalities caused by the inappropriate pressure of the hydraulic module, it is necessary to further analyze the vibration abnormality evaluation value and the abnormal high temperature performance degree according to the growth and change of the vibration abnormality evaluation value and the growth and change of the abnormal high temperature performance degree, so as to obtain a more reliable optimized saw blade abnormality indicator.

[0125] In an embodiment of the present invention, the saw blade abnormality index is determined, and the implementation steps include:

[0126] Determining an abnormal vibration growth value and an abnormal high temperature growth value according to the growth change of the vibration abnormality evaluation value and the growth change of the abnormal high temperature manifestation degree;

[0127] The saw blade abnormality index is determined based on the abnormal vibration growth value and the abnormal high temperature growth value, combined with the vibration abnormality evaluation value of the last vibration segment and the abnormal high temperature expression of the last infrared image in the infrared image sequence.

[0128] For the above steps, in all vibration segments, the difference between the abnormal vibration growth value of the nth vibration segment and the abnormal vibration growth value of the previous n-1th vibration segment is calculated, and all the differences are averaged, and then the norm function is used for linear normalization to obtain the abnormal vibration growth value. Similarly, in the infrared image sequence, the difference between the abnormal high temperature expression degree corresponding to the nth infrared image and the abnormal high temperature expression degree corresponding to the previous n-1th infrared image is averaged, and then the norm function is used for linear normalization to obtain the abnormal high temperature growth value. Then, the norm function is used to linearly normalize the vibration abnormality evaluation value of the last vibration segment in all vibration segments and the abnormal high temperature expression degree of the last infrared image in the infrared image sequence, respectively, so as to obtain the normalized value of the vibration abnormality evaluation value and the normalized value of the abnormal high temperature expression degree. Furthermore, the first abnormal index is determined based on the normalized value of the abnormal vibration growth value and the vibration abnormality evaluation value, and the second abnormal index is determined based on the abnormal high temperature growth value and the normalized value of the abnormal high temperature manifestation; the saw blade abnormal index is determined by combining the first abnormal index and the second abnormal index.

[0129] In the embodiment of the present invention, the saw blade abnormality index is determined, and the corresponding calculation formula is:

[0130] F=softmax(Z′*kz+T′*kt);

[0131] Among them, F represents the saw blade abnormality index; softmax represents the normalization function; Z′*kz represents the first abnormality index, Z′ represents the normalized value of the vibration abnormality evaluation value; kz represents the abnormal vibration growth value; T′*kt represents the second abnormality index, T′ represents the normalized value of the abnormal high temperature performance, and kt represents the abnormal high temperature growth value.

[0132] In the above calculation formula, the larger the normalized value of the vibration anomaly evaluation value and the normalized value of the abnormal high temperature expression corresponding to the last vibration segment and the last infrared image close to the current moment, and the higher the growth degree of the vibration anomaly evaluation values ​​corresponding to all vibration segments and the abnormal high temperature expression degrees corresponding to all infrared images, it means that the abnormal performance of the current saw blade is relatively higher, and there is a higher probability that there are abnormal problems such as severe wear and deformation.

[0133] Step S400: Determine whether there is a saw blade abnormality according to the saw blade abnormality indicator.

[0134] A saw blade abnormality index threshold is pre-set, and the saw blade abnormality index threshold is reasonably set according to needs. The embodiment of the present invention sets the saw blade abnormality index threshold to be 0.7. The saw blade abnormality index calculated above is compared with the saw blade abnormality index threshold. When the saw blade abnormality index is less than or equal to the saw blade abnormality index threshold, it means that the current saw blade does not have a saw blade abnormality; and when the saw blade abnormality index is greater than the saw blade abnormality index threshold, it means that the current saw blade is likely to have abnormal problems such as severe wear and deformation. At this time, it is judged that the saw blade has an abnormality, and the detection processing module 05 sends a saw blade replacement signal to the spare saw blade replacement module. After receiving the saw blade replacement signal, the spare saw blade replacement module controls the replacement of the current saw blade with the spare saw blade. After replacing the current saw blade with the spare saw blade and continuing the cutting operation, the spare saw blade is checked for saw blade abnormalities in the same manner as the above-mentioned method for checking the current saw blade for saw blade abnormalities. If the spare saw blade also has an abnormality in the middle of the process, the equipment is paused and the saw blade is replaced by a professional; otherwise, a complete equipment maintenance and other operations are performed after the current batch of materials is cut.

[0135] Based on the same inventive concept, an embodiment of the present invention further provides a saw blade abnormality detection method for a movable horizontal continuous casting profile cutting device, the method comprising:

[0136] Acquire an infrared image sequence and a vibration data sequence, wherein the infrared image of the infrared image sequence is obtained by detecting the surface temperature of the saw blade, and the vibration data in the vibration data sequence is obtained by detecting the vibration of the saw blade;

[0137] Segmenting the vibration data sequence to obtain individual vibration segments, and determining a vibration anomaly assessment value of each vibration segment according to fluctuation conditions of each vibration segment;

[0138] Performing temperature recognition on each infrared image in the infrared image sequence to determine the abnormal high temperature manifestation of the saw blade in each infrared image;

[0139] Determine the saw blade abnormality index according to the growth change of the vibration abnormality evaluation value and the growth change of the abnormal high temperature performance degree, and in combination with the magnitude of the vibration abnormality evaluation value and the abnormal high temperature performance degree near the current moment;

[0140] According to the saw blade abnormality indicator, it is determined whether there is a saw blade abnormality.

[0141] Based on the same inventive concept, the embodiment of the present invention also provides a saw blade abnormality detection system for a movable horizontal continuous casting profile cutting device, such as Fig.11 As shown, the system includes: a memory 501, a processor 502, and a computer program 503 stored in the memory 501 and running on the processor 502, wherein when the processor 502 executes the computer program 503, the system can execute the steps of the saw blade abnormality detection process introduced above.

[0142] The embodiment of the present invention can divide the system into functional modules according to the above-mentioned saw blade abnormality detection process method example. For example, it can correspond to each functional module, or two or more functions can be integrated into one processing module. The above-mentioned integrated module can be implemented in the form of hardware. It should be noted that the division of modules in this embodiment is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0143] Based on the same inventive concept, an embodiment of the present invention further provides a computer program product, which includes: computer program code, when the computer program code is run on a computer, the computer executes the steps of the saw blade abnormality detection process introduced above.

[0144] Based on the same inventive concept, an embodiment of the present invention further provides a computer-readable storage medium, which stores computer program code. When the computer program code runs on a computer, the computer executes the steps of the saw blade abnormality detection process introduced above.

[0145] It should be noted that the above-described embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A movable horizontal continuous casting profile cutting device, characterized in that: The cutting device comprises a cutting device body and a detection device, wherein the detection device comprises an infrared sensor for detecting the surface temperature of a saw blade, a vibration sensor for detecting the vibration of the saw blade, and a detection processing module, wherein the detection processing module is communicatively connected to the infrared sensor and the vibration sensor to obtain an infrared image sequence and a vibration data sequence, and performs saw blade abnormality detection according to the infrared image sequence and the vibration data sequence, wherein the saw blade abnormality detection process comprises: Segmenting the vibration data sequence to obtain individual vibration segments, and determining a vibration anomaly assessment value of each vibration segment according to fluctuation conditions of each vibration segment; Performing temperature recognition on each infrared image in the infrared image sequence to determine the abnormal high temperature manifestation of the saw blade in each infrared image; Determine the saw blade abnormality index according to the growth change of the vibration abnormality evaluation value and the growth change of the abnormal high temperature performance degree, and in combination with the magnitude of the vibration abnormality evaluation value and the abnormal high temperature performance degree near the current moment; According to the saw blade abnormality indicator, it is determined whether there is a saw blade abnormality.

2. The movable horizontal continuous casting profile cutting equipment according to claim 1, characterized in that: Determine the vibration anomaly assessment value for each vibration segment, including: Determining a vibration mean value of each vibration segment according to an average distribution of vibration data in each vibration segment; Determine a reference vibration segment in the vibration segments, and determine the vibration deviation between each vibration segment and the reference vibration segment according to the difference in vibration mean between each vibration segment and the reference vibration segment; Determining an extreme value sequence of each vibration segment according to the extreme value distribution of the vibration data in each vibration segment; Matching the extreme value sequence of each vibration segment with the extreme value sequence of the reference vibration segment, and determining the matching similarity index between each vibration segment and the reference vibration segment according to the matching result and in combination with the difference between each extreme value in the extreme value sequence of each vibration segment and the vibration mean of the reference vibration segment; The vibration deviation and the matching similarity index are integrated to determine the vibration anomaly assessment value of each vibration segment.

3. The movable horizontal continuous casting profile cutting equipment according to claim 2, characterized in that: The extreme value sequence includes a maximum value sequence and a minimum value sequence, and determining a matching similarity index between each vibration segment and a reference vibration segment includes: Taking the maximum value sequence and the minimum value sequence as a target extreme value sequence; Matching the target extreme value sequence of each vibration segment with the target extreme value sequence corresponding to the reference vibration segment to obtain each extreme value matching pair; Determine a sub-matching similarity index by comprehensively considering the matching distance between the extreme value points in each extreme value matching pair and the difference between each extreme value in the target extreme value sequence of each vibration segment and the vibration mean of the reference vibration segment; The matching similarity index between each vibration segment and the reference vibration segment is determined by comprehensively analyzing the sub-matching similarity index corresponding to the maximum value sequence between each vibration segment and the reference vibration segment, and the sub-matching similarity index corresponding to the minimum value sequence between each vibration segment and the reference vibration segment.

4. The movable horizontal continuous casting profile cutting equipment according to claim 2, characterized in that: The first vibration segment among all the vibration segments is determined as a reference vibration segment.

5. The movable horizontal continuous casting profile cutting equipment according to claim 1, characterized in that: Determine the degree of abnormally high temperatures in the saw blade in each infrared image, including: Performing saw blade area segmentation on each infrared image in the infrared image sequence to obtain a saw blade area; Segmenting the saw blade area to determine each abnormally high temperature area; Determine a reference infrared image among all the infrared images in the infrared image sequence, and determine the abnormally high temperature expression of the saw blade in each infrared image based on the uniformity of grayscale distribution of the saw blade area in each infrared image in the infrared image sequence, the average distribution of grayscale values ​​in each abnormally high temperature area in the saw blade area, the area of ​​each abnormally high temperature area, and the difference in the average distribution of grayscale values ​​between the saw blade area in each infrared image in the infrared image sequence and the saw blade area of ​​the reference infrared image.

6. The movable horizontal continuous casting profile cutting equipment according to claim 5, characterized in that: Determine the degree of abnormally high temperatures in the saw blade in each infrared image, including: Determining a grayscale mean value of the saw blade area of ​​each infrared image in the infrared image sequence according to an average distribution of grayscale values ​​in the saw blade area of ​​each infrared image in the infrared image sequence; Determining a grayscale difference index corresponding to each infrared image in the infrared image sequence according to a difference in grayscale mean between a saw blade region of each infrared image in the infrared image sequence and a saw blade region of the reference infrared image; Determining the grayscale information entropy corresponding to each infrared image in the infrared image sequence according to the number of pixels with the same grayscale level in the saw blade area of ​​each infrared image in the infrared image sequence; Determine the abnormal temperature representation value corresponding to each infrared image in the infrared image sequence by comprehensively analyzing the average distribution of gray values ​​in each abnormally high temperature area in the saw blade area of ​​each infrared image in the infrared image sequence and the area size of each abnormally high temperature area; The grayscale difference index, grayscale information entropy and abnormal temperature expression value corresponding to each infrared image in the infrared image sequence are comprehensively considered to determine the abnormal high temperature expression degree of the saw blade in each infrared image.

7. The movable horizontal continuous casting profile cutting equipment according to claim 1, characterized in that: Determine saw blade abnormality indicators, including: Determining an abnormal vibration growth value and an abnormal high temperature growth value according to the growth change of the vibration abnormality evaluation value and the growth change of the abnormal high temperature manifestation degree; The saw blade abnormality index is determined based on the abnormal vibration growth value and the abnormal high temperature growth value, combined with the vibration abnormality evaluation value of the last vibration segment and the abnormal high temperature expression of the last infrared image in the infrared image sequence.

8. The movable horizontal continuous casting profile cutting equipment according to claim 7, characterized in that: Determine abnormal vibration growth values ​​and abnormal high temperature growth values, including: Determine the difference in vibration anomaly assessment value between each subsequent vibration segment and its previous vibration segment in all the vibration segments, and use the normalized result of the mean of all the differences as the abnormal vibration growth value; The difference in abnormal high temperature expression between each subsequent infrared image and the previous infrared image in the infrared image sequence is determined, and the normalized result of the mean of all the differences is used as the abnormal high temperature growth value.

9. The movable horizontal continuous casting profile cutting equipment according to claim 7, characterized in that: Determine saw blade abnormality indicators, including: Determining a first abnormality index according to the vibration abnormality evaluation value of the last vibration segment and the abnormal vibration growth value; determining a second abnormality indicator according to the abnormal high temperature expression degree of the last infrared image in the infrared image sequence and the abnormal high temperature growth value; The saw blade abnormality index is determined by combining the first abnormality index and the second abnormality index.

10. The movable horizontal continuous casting profile cutting equipment according to claim 1, characterized in that: The saw blade abnormality detection process also includes: if there is a saw blade abnormality, replacing the current saw blade with a spare saw blade.

Images