Steam turbine rotor journal defect damage monitoring method and system

Abstract

The invention relates to the technical field of steam turbines, and discloses a steam turbine rotor journal defect damage monitoring method and system.The steam turbine rotor journal defect damage monitoring method comprises the steps that a rotor journal to be subjected to defect damage monitoring is shot, multiple multi-angle images are obtained, preprocessing splicing is conducted, and a panoramic image to be analyzed is obtained; performing region division on the panoramic image to be analyzed to obtain a plurality of sub panoramic image regions, and deploying a plurality of electromagnetic induction points; electromagnetic induction waves are sent to the electromagnetic induction points corresponding to all the sub panoramic image areas, and electromagnetic induction intensity is collected; all electromagnetic induction intensities are analyzed, suspected defect damage factors are calculated, whether defect damage exists in the rotor journal to be subjected to defect damage monitoring or not is judged according to the suspected defect damage factors, continuous monitoring can be carried out under the condition that normal operation of a steam turbine is not affected, accurate evaluation of the state of the rotor journal is achieved, and the reliability of the rotor journal is improved. The monitoring efficiency and accuracy are improved, potential risks are found in time, safe and stable operation of the steam turbine is guaranteed, and the maintenance cost is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of steam turbines, and in particular to a method and system for monitoring defects and damage of a steam turbine rotor journal. Background Art

[0002] As a power equipment widely used in modern industry, the stable operation of steam turbine is crucial to the safety and efficiency of the entire production system. The rotor is one of the core components of the steam turbine, and the rotor journal is the key part connecting the rotor and the bearing. During long-term operation, due to various reasons (such as material fatigue, corrosion, wear, etc.), the rotor journal may have defects or damage. If these defects are not discovered and handled in time, they may cause serious mechanical failures and even safety accidents.

[0003] At present, defect damage monitoring for turbine rotor journals mainly relies on regular shutdown inspection and maintenance. This method is not only time-consuming and labor-intensive, but also cannot achieve real-time online monitoring, which poses certain safety risks. In addition, although some traditional non-destructive testing technologies can detect defects to a certain extent, they often require professional operators and have limited ability to identify minor defects. Summary of the invention

[0004] The embodiment of the present invention provides a method and system for monitoring defects and damage of a turbine rotor journal, which can perform continuous monitoring without affecting the normal operation of the turbine, achieve accurate assessment of the rotor journal status, improve monitoring efficiency and accuracy, thereby timely discovering potential risks, ensuring the safe and stable operation of the turbine, and reducing maintenance costs.

[0005] In order to achieve the above object, the present invention provides a method for monitoring turbine rotor journal defects, comprising:

[0006] Taking multi-angle photos of the rotor journal to be monitored for defective damage to obtain multiple multi-angle images, and pre-processing and splicing the multi-angle images to obtain a panoramic image to be analyzed corresponding to the rotor journal to be monitored for defective damage;

[0007] Dividing the panoramic image to be analyzed into regions to obtain a plurality of sub-panoramic image regions, and deploying a plurality of electromagnetic induction points for each sub-panoramic image region;

[0008] Sending electromagnetic induction waves to the electromagnetic induction points corresponding to each sub-panoramic image area, and collecting the corresponding electromagnetic induction intensity;

[0009] All electromagnetic induction intensities are analyzed, and a suspected defect damage factor of the rotor journal to be monitored for defect damage is calculated based on the analysis result, and whether the rotor journal to be monitored for defect damage has defect damage is determined according to the suspected defect damage factor.

[0010] Further, when the rotor journal to be monitored for defective damage is photographed at multiple angles to obtain multiple multi-angle images, and the multi-angle images are preprocessed and spliced ​​to obtain a panoramic image to be analyzed corresponding to the rotor journal to be monitored for defective damage, it includes:

[0011] Preprocessing the multi-angle images, wherein the preprocessing includes image enhancement, denoising and geometric correction;

[0012] Extracting key feature points from the preprocessed multi-angle images using a feature extraction algorithm, wherein the feature extraction algorithm includes one or more of a scale-invariant feature transform, an accelerated robust feature, or an oriented gradient histogram;

[0013] The extracted key feature points are matched using feature matching technology to determine the transformation relationship between adjacent images;

[0014] According to the transformation relationship, the matched images are stitched into a panoramic image using an image fusion technology, wherein the image fusion technology includes one or more of a weighted average method, multi-band fusion or a Laplacian pyramid fusion;

[0015] The stitched panoramic image is post-processed to obtain a panoramic image to be analyzed corresponding to the rotor journal to be monitored for defect damage, wherein the post-processing includes color balance adjustment and edge smoothing.

[0016] Furthermore, when analyzing all electromagnetic induction intensities and calculating the suspected defect damage factor of the rotor journal to be monitored for defect damage based on the analysis results, it includes:

[0017] Acquire a plurality of preset electromagnetic induction intensities corresponding to the electromagnetic induction points, and if all the electromagnetic induction intensities are equal to the preset electromagnetic induction intensities, determine that the rotor journal to be monitored for defect damage does not have defect damage;

[0018] If there is one or more electromagnetic induction intensities that are not equal to the preset electromagnetic induction intensity, it is determined that there is a suspected defect damage in the rotor journal to be monitored for defect damage;

[0019] Marking all sub-panoramic image regions whose electromagnetic induction strength is not equal to the preset electromagnetic induction strength as suspected;

[0020] Extracting all electromagnetic induction intensities of the sub-panoramic image area carrying the suspected marker;

[0021] Extracting the same electromagnetic induction intensity from all electromagnetic induction intensities and obtaining a plurality of electromagnetic induction intensity sequences;

[0022] Counting the first quantity of the electromagnetic induction intensity sequence;

[0023] Extracting one electromagnetic induction intensity from all electromagnetic induction intensity sequences respectively, and calculating a first electromagnetic induction intensity and value;

[0024] Obtaining a preset electromagnetic induction intensity, eliminating all electromagnetic induction intensity sequences that are less than the preset electromagnetic induction intensity, and counting a second number of remaining electromagnetic induction intensity sequences;

[0025] Extracting one electromagnetic induction intensity from the remaining electromagnetic induction intensity sequences respectively, and calculating a second electromagnetic induction intensity and value;

[0026] The sub-suspected factor of the rotor journal to be monitored for defective damage is calculated according to the first number, the second number, the first electromagnetic induction intensity sum value and the second electromagnetic induction intensity sum value.

[0027] Furthermore, when analyzing all electromagnetic induction intensities and calculating the suspected defect damage factor of the rotor journal to be monitored for defect damage based on the analysis results, it also includes:

[0028] All the suspected sub-factors are sorted by numerical size, and combined based on the large-small principle to obtain multiple suspected sub-factor combinations;

[0029] Calculate the sub-suspected factor difference of each sub-suspected factor combination, and calculate the average of all sub-suspected factor differences;

[0030] Generate a first mark for all sub-suspected factor combinations corresponding to sub-suspected factor differences greater than the average value;

[0031] generating a second mark for all sub-suspected factor combinations corresponding to the sub-suspected factor differences that are equal to the average value;

[0032] generating a third mark for all sub-suspected factor combinations corresponding to sub-suspected factor differences that are smaller than the average value;

[0033] Counting a first quantity of the first mark, a second quantity of the second mark, and a third quantity of the third mark;

[0034] A suspected defect damage factor of the rotor journal to be monitored for defect damage is calculated based on the first number, the second number, and the third number.

[0035] Further, when judging whether the rotor journal to be monitored for defect damage has defect damage according to the suspected defect damage factor, it includes:

[0036] Judging whether the rotor journal to be monitored for defect damage has defect damage according to the relationship between the suspected defect damage factor and a preset suspected defect damage factor;

[0037] When the suspected defect damage factor is less than the preset suspected defect damage factor, it is determined that the rotor journal to be monitored for defect damage does not have defect damage;

[0038] When the suspected defect damage factor is greater than or equal to the preset suspected defect damage factor, it is determined that the rotor journal to be monitored for defect damage has defect damage.

[0039] In order to achieve the above object, the present invention also provides a turbine rotor journal defect damage monitoring system, comprising:

[0040] The first module is used to shoot the rotor journal to be monitored for defective damage at multiple angles to obtain multiple multi-angle images, and pre-process and splice the multi-angle images to obtain a panoramic image to be analyzed corresponding to the rotor journal to be monitored for defective damage;

[0041] The second module is used to divide the panoramic image to be analyzed into regions to obtain multiple sub-panoramic image regions, and deploy multiple electromagnetic induction points for each sub-panoramic image region;

[0042] The third module is used to send electromagnetic induction waves to the electromagnetic induction points corresponding to each sub-panoramic image area and collect the corresponding electromagnetic induction intensity;

[0043] The fourth module is used to analyze all electromagnetic induction intensities, and calculate the suspected defect damage factor of the rotor shaft journal to be monitored for defect damage based on the analysis results, and determine whether the rotor shaft journal to be monitored for defect damage has defect damage according to the suspected defect damage factor.

[0044] Furthermore, the first module is used for:

[0045] The first module is used to preprocess the multi-angle image, wherein the preprocessing includes image enhancement, denoising and geometric correction;

[0046] The first module is used to extract key feature points from the preprocessed multi-angle image using a feature extraction algorithm, wherein the feature extraction algorithm includes one or more of a scale-invariant feature transform, an accelerated robust feature, or an oriented gradient histogram;

[0047] The first module is used to match the extracted key feature points using feature matching technology to determine the transformation relationship between adjacent images;

[0048] The first module is used to stitch the matched images into a panoramic image using image fusion technology according to the transformation relationship, wherein the image fusion technology includes one or more of weighted averaging, multi-band fusion or Laplacian pyramid fusion;

[0049] The first module is used to post-process the stitched panoramic image to obtain the panoramic image to be analyzed corresponding to the rotor journal to be monitored for defect damage, wherein the post-processing includes color balance adjustment and edge smoothing.

[0050] Furthermore, the fourth module is used for:

[0051] The fourth module is used to obtain a plurality of preset electromagnetic induction intensities corresponding to the electromagnetic induction points, and if all the electromagnetic induction intensities are equal to the preset electromagnetic induction intensities, it is determined that the rotor journal to be monitored for defect damage does not have defect damage;

[0052] The fourth module is used to determine whether there is a suspected defect damage in the rotor journal to be monitored for defect damage if there is one or more electromagnetic induction intensities that are not equal to the preset electromagnetic induction intensity;

[0053] The fourth module is used to mark all sub-panoramic image areas whose electromagnetic induction intensity is not equal to the preset electromagnetic induction intensity as suspected;

[0054] The fourth module is used to extract all electromagnetic induction intensities of the sub-panoramic image area carrying the suspected mark;

[0055] The fourth module is used to extract the same electromagnetic induction intensity from all electromagnetic induction intensities and obtain multiple electromagnetic induction intensity sequences;

[0056] The fourth module is used to count the first number of electromagnetic induction intensity sequences;

[0057] The fourth module is used to extract an electromagnetic induction intensity from all electromagnetic induction intensity sequences respectively, and calculate the first electromagnetic induction intensity and value;

[0058] The fourth module is used to obtain a preset electromagnetic induction intensity, eliminate all electromagnetic induction intensity sequences that are less than the preset electromagnetic induction intensity, and count the second number of remaining electromagnetic induction intensity sequences;

[0059] The fourth module is used to extract one electromagnetic induction intensity from the remaining electromagnetic induction intensity sequence respectively, and calculate the second electromagnetic induction intensity and value;

[0060] The fourth module is used to calculate the sub-suspected factor of the rotor journal to be monitored for defect damage according to the first number, the second number, the first electromagnetic induction intensity sum value and the second electromagnetic induction intensity sum value.

[0061] Furthermore, the fourth module is used for:

[0062] The fourth module is used to sort all the sub-suspected factors by numerical value and combine them based on the large-small principle to obtain multiple sub-suspected factor combinations;

[0063] The fourth module is used to calculate the sub-suspected factor difference of each sub-suspected factor combination, and calculate the average value of all sub-suspected factor differences;

[0064] The fourth module is used to generate a first mark for the sub-suspected factor combination corresponding to all sub-suspected factor differences greater than the average value;

[0065] The fourth module is used to generate a second mark for the sub-suspected factor combination corresponding to all sub-suspected factor differences equal to the average value;

[0066] The fourth module is used to generate a third mark for the sub-suspected factor combination corresponding to all sub-suspected factor differences that are smaller than the average value;

[0067] The fourth module is used to count a first quantity of the first mark, a second quantity of the second mark, and a third quantity of the third mark;

[0068] The fourth module is used to calculate the suspected defect damage factor of the rotor journal to be monitored for defect damage based on the first number, the second number and the third number.

[0069] Furthermore, the fourth module is used for:

[0070] The fourth module is used to determine whether the rotor journal to be monitored for defect damage has defect damage according to the relationship between the suspected defect damage factor and the preset suspected defect damage factor;

[0071] The fourth module is used to determine that there is no defect damage in the rotor journal to be monitored for defect damage when the suspected defect damage factor is less than the preset suspected defect damage factor;

[0072] The fourth module is used to determine whether the rotor journal to be monitored for defect damage has defect damage when the suspected defect damage factor is greater than or equal to the preset suspected defect damage factor.

[0073] Compared with the prior art, the present invention has the following beneficial effects:

[0074] The present invention discloses a method and system for monitoring defect damage of a turbine rotor journal. The method comprises the following steps: photographing a rotor journal to be monitored for defect damage to obtain a plurality of multi-angle images, pre-processing and splicing the images to obtain a panoramic image to be analyzed; dividing the panoramic image to be analyzed into regions to obtain a plurality of sub-panoramic image regions, and deploying a plurality of electromagnetic induction points; sending electromagnetic induction waves to the electromagnetic induction points corresponding to each sub-panoramic image region to collect electromagnetic induction intensity; analyzing all electromagnetic induction intensities to calculate suspected defect damage factors, and judging whether the rotor journal to be monitored for defect damage exists according to the suspected defect damage factors. The method can perform continuous monitoring without affecting the normal operation of the turbine, realize accurate evaluation of the rotor journal status, improve monitoring efficiency and accuracy, thereby timely discovering potential risks, ensuring safe and stable operation of the turbine, and reducing maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0076] Figure 1 A schematic flow chart of a method for monitoring a turbine rotor journal defect in an embodiment of the present invention is shown;

[0077] Figure 2 A schematic structural diagram of a steam turbine rotor journal defect damage monitoring system in an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0078] The specific implementation of the present invention is further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0079] In the description of the present application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0080] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0081] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0082] The following is a description of preferred embodiments of the present invention with reference to the accompanying drawings.

[0083] like Figure 1 As shown, an embodiment of the present invention discloses a method for monitoring turbine rotor journal defects and damage, comprising:

[0084] S110: photographing the rotor journal to be monitored for defective damage at multiple angles to obtain multiple multi-angle images, and preprocessing and splicing the multi-angle images to obtain a panoramic image to be analyzed corresponding to the rotor journal to be monitored for defective damage;

[0085] In some embodiments of the present application, when a rotor journal to be monitored for defective damage is photographed at multiple angles to obtain multiple multi-angle images, and the multi-angle images are pre-processed and spliced ​​to obtain a panoramic image to be analyzed corresponding to the rotor journal to be monitored for defective damage, the method includes:

[0086] Preprocessing the multi-angle images, wherein the preprocessing includes image enhancement, denoising and geometric correction;

[0087] Extracting key feature points from the preprocessed multi-angle images using a feature extraction algorithm, wherein the feature extraction algorithm includes one or more of a scale-invariant feature transform, an accelerated robust feature, or an oriented gradient histogram;

[0088] The extracted key feature points are matched using feature matching technology to determine the transformation relationship between adjacent images;

[0089] According to the transformation relationship, the matched images are stitched into a panoramic image using an image fusion technology, wherein the image fusion technology includes one or more of a weighted average method, multi-band fusion or a Laplacian pyramid fusion;

[0090] The stitched panoramic image is post-processed to obtain a panoramic image to be analyzed corresponding to the rotor journal to be monitored for defect damage, wherein the post-processing includes color balance adjustment and edge smoothing.

[0091] The beneficial effect of the above technical solution is: the present invention performs multi-angle shooting of the rotor shaft journal to be monitored for defective damage to obtain multiple multi-angle images, and pre-processes and splices the multi-angle images to obtain a panoramic image to be analyzed corresponding to the rotor shaft journal to be monitored for defective damage, which can lay the foundation for the precise deployment of electromagnetic induction points, thereby ensuring the accuracy of defect damage monitoring.

[0092] S120: Dividing the panoramic image to be analyzed into regions to obtain a plurality of sub-panoramic image regions, and deploying a plurality of electromagnetic induction points for each sub-panoramic image region;

[0093] In this embodiment, the area is divided according to the size of the panoramic image to be analyzed, and the electromagnetic induction points are evenly deployed.

[0094] S130: sending electromagnetic induction waves to the electromagnetic induction points corresponding to each sub-panoramic image area, and collecting the corresponding electromagnetic induction intensity;

[0095] S140: Analyze all electromagnetic induction intensities, and calculate the suspected defect damage factor of the rotor journal to be monitored for defect damage based on the analysis result, and determine whether the rotor journal to be monitored for defect damage has defect damage according to the suspected defect damage factor.

[0096] In some embodiments of the present application, when analyzing all electromagnetic induction intensities and calculating the suspected defect damage factor of the rotor journal to be monitored for defect damage based on the analysis results, it includes:

[0097] Acquire a plurality of preset electromagnetic induction intensities corresponding to the electromagnetic induction points, and if all the electromagnetic induction intensities are equal to the preset electromagnetic induction intensities, determine that the rotor journal to be monitored for defect damage does not have defect damage;

[0098] If there is one or more electromagnetic induction intensities that are not equal to the preset electromagnetic induction intensity, it is determined that there is a suspected defect damage in the rotor journal to be monitored for defect damage;

[0099] Marking all sub-panoramic image regions whose electromagnetic induction strength is not equal to the preset electromagnetic induction strength as suspected;

[0100] Extracting all electromagnetic induction intensities of the sub-panoramic image area carrying the suspected marker;

[0101] Extracting the same electromagnetic induction intensity from all electromagnetic induction intensities and obtaining a plurality of electromagnetic induction intensity sequences;

[0102] Counting the first quantity of the electromagnetic induction intensity sequence;

[0103] Extracting one electromagnetic induction intensity from all electromagnetic induction intensity sequences respectively, and calculating a first electromagnetic induction intensity and value;

[0104] Obtaining a preset electromagnetic induction intensity, eliminating all electromagnetic induction intensity sequences that are less than the preset electromagnetic induction intensity, and counting a second number of remaining electromagnetic induction intensity sequences;

[0105] Extracting one electromagnetic induction intensity from the remaining electromagnetic induction intensity sequences respectively, and calculating a second electromagnetic induction intensity and value;

[0106] The sub-suspected factor of the rotor journal to be monitored for defective damage is calculated according to the first number, the second number, the first electromagnetic induction intensity sum value and the second electromagnetic induction intensity sum value.

[0107] In this embodiment, the sub-suspect factor of the rotor journal to be monitored for defect damage is calculated according to the following formula:

[0108]

[0109] Among them, T is the sub-suspected factor of the rotor journal to be monitored for defect damage, t is the preset electromagnetic induction intensity, R1 is the first electromagnetic induction intensity and value, R2 is the second electromagnetic induction intensity and value, Q1 is the first quantity, and Q2 is the second quantity.

[0110] The beneficial effect of the above technical solution is: the present invention calculates the sub-suspected factor of the rotor journal to be monitored for defect damage according to the first quantity, the second quantity, the first electromagnetic induction intensity sum and the second electromagnetic induction intensity sum, which can ensure the accurate calculation of the sub-suspected factor, ensure the accuracy of the calculation, avoid errors, and at the same time provide reliable data support for the calculation of the suspected defect damage factor.

[0111] In some embodiments of the present application, when analyzing all electromagnetic induction intensities and calculating the suspected defect damage factor of the rotor journal to be monitored for defect damage based on the analysis results, it also includes:

[0112] All the suspected sub-factors are sorted by numerical size, and combined based on the large-small principle to obtain multiple suspected sub-factor combinations;

[0113] Calculate the sub-suspected factor difference of each sub-suspected factor combination, and calculate the average of all sub-suspected factor differences;

[0114] Generate a first mark for all sub-suspected factor combinations corresponding to sub-suspected factor differences greater than the average value;

[0115] generating a second mark for all sub-suspected factor combinations corresponding to the sub-suspected factor differences that are equal to the average value;

[0116] generating a third mark for all sub-suspected factor combinations corresponding to sub-suspected factor differences that are smaller than the average value;

[0117] Counting a first quantity of the first mark, a second quantity of the second mark, and a third quantity of the third mark;

[0118] A suspected defect damage factor of the rotor journal to be monitored for defect damage is calculated based on the first number, the second number, and the third number.

[0119] In this embodiment, the big-small principle refers to extracting the largest sub-suspected factor and the smallest sub-suspected factor, combining them to obtain a sub-suspected factor combination, extracting the adjacent value of the largest sub-suspected factor and the adjacent value of the smallest sub-suspected factor, combining the two adjacent values ​​to obtain a sub-suspected factor combination, and the rest are combined according to this rule.

[0120] In this embodiment, the suspected defect damage factor of the rotor journal to be monitored for defect damage is calculated according to the following formula:

[0121]

[0122] Among them, f is the suspected defect damage factor of the rotor journal to be monitored for defect damage, ln is the sign of the logarithmic function, B1 is the third quantity, B2 is the first quantity, and B3 is the second quantity.

[0123] The beneficial effect of the above technical solution is that the present invention calculates the suspected defect damage factor of the rotor journal to be monitored for defect damage based on the first number, the second number and the third number, thereby ensuring the calculation accuracy of the suspected defect damage factor and improving the calculation efficiency.

[0124] In some embodiments of the present application, when judging whether the rotor journal to be monitored for defect damage has defect damage according to the suspected defect damage factor, it includes:

[0125] Judging whether the rotor journal to be monitored for defect damage has defect damage according to the relationship between the suspected defect damage factor and a preset suspected defect damage factor;

[0126] When the suspected defect damage factor is less than the preset suspected defect damage factor, it is determined that the rotor journal to be monitored for defect damage does not have defect damage;

[0127] When the suspected defect damage factor is greater than or equal to the preset suspected defect damage factor, it is determined that the rotor journal to be monitored for defect damage has defect damage.

[0128] The beneficial effects of the above technical solution are: it can carry out continuous monitoring without affecting the normal operation of the turbine, realize accurate assessment of the rotor journal status, improve the efficiency and accuracy of monitoring, thereby timely discover potential risks, ensure the safe and stable operation of the turbine, and reduce maintenance costs.

[0129] In order to further explain the technical idea of ​​the present invention, the technical solution of the present invention is now described in combination with specific application scenarios.

[0130] Correspondingly, such as Figure 2 As shown, the present application also provides a turbine rotor journal defect damage monitoring system, comprising:

[0131] The first module is used to shoot the rotor journal to be monitored for defective damage at multiple angles to obtain multiple multi-angle images, and pre-process and splice the multi-angle images to obtain a panoramic image to be analyzed corresponding to the rotor journal to be monitored for defective damage;

[0132] The second module is used to divide the panoramic image to be analyzed into regions to obtain multiple sub-panoramic image regions, and deploy multiple electromagnetic induction points for each sub-panoramic image region;

[0133] The third module is used to send electromagnetic induction waves to the electromagnetic induction points corresponding to each sub-panoramic image area and collect the corresponding electromagnetic induction intensity;

[0134] The fourth module is used to analyze all electromagnetic induction intensities, and calculate the suspected defect damage factor of the rotor shaft journal to be monitored for defect damage based on the analysis results, and determine whether the rotor shaft journal to be monitored for defect damage has defect damage according to the suspected defect damage factor.

[0135] In some embodiments of the present application, the first module is used to:

[0136] The first module is used to preprocess the multi-angle image, wherein the preprocessing includes image enhancement, denoising and geometric correction;

[0137] The first module is used to extract key feature points from the preprocessed multi-angle image using a feature extraction algorithm, wherein the feature extraction algorithm includes one or more of a scale-invariant feature transform, an accelerated robust feature, or an oriented gradient histogram;

[0138] The first module is used to match the extracted key feature points using feature matching technology to determine the transformation relationship between adjacent images;

[0139] The first module is used to stitch the matched images into a panoramic image using image fusion technology according to the transformation relationship, wherein the image fusion technology includes one or more of weighted averaging, multi-band fusion or Laplacian pyramid fusion;

[0140] The first module is used to post-process the stitched panoramic image to obtain the panoramic image to be analyzed corresponding to the rotor journal to be monitored for defect damage, wherein the post-processing includes color balance adjustment and edge smoothing.

[0141] In some embodiments of the present application, the fourth module is used to:

[0142] The fourth module is used to obtain a plurality of preset electromagnetic induction intensities corresponding to the electromagnetic induction points, and if all the electromagnetic induction intensities are equal to the preset electromagnetic induction intensities, it is determined that the rotor journal to be monitored for defect damage does not have defect damage;

[0143] The fourth module is used to determine whether there is a suspected defect damage in the rotor journal to be monitored for defect damage if there is one or more electromagnetic induction intensities that are not equal to the preset electromagnetic induction intensity;

[0144] The fourth module is used to mark all sub-panoramic image areas whose electromagnetic induction intensity is not equal to the preset electromagnetic induction intensity as suspected;

[0145] The fourth module is used to extract all electromagnetic induction intensities of the sub-panoramic image area carrying the suspected mark;

[0146] The fourth module is used to extract the same electromagnetic induction intensity from all electromagnetic induction intensities and obtain multiple electromagnetic induction intensity sequences;

[0147] The fourth module is used to count the first number of electromagnetic induction intensity sequences;

[0148] The fourth module is used to extract an electromagnetic induction intensity from all electromagnetic induction intensity sequences respectively, and calculate the first electromagnetic induction intensity and value;

[0149] The fourth module is used to obtain a preset electromagnetic induction intensity, eliminate all electromagnetic induction intensity sequences that are less than the preset electromagnetic induction intensity, and count the second number of remaining electromagnetic induction intensity sequences;

[0150] The fourth module is used to extract one electromagnetic induction intensity from the remaining electromagnetic induction intensity sequence respectively, and calculate the second electromagnetic induction intensity and value;

[0151] The fourth module is used to calculate the sub-suspected factor of the rotor journal to be monitored for defect damage according to the first number, the second number, the first electromagnetic induction intensity sum value and the second electromagnetic induction intensity sum value.

[0152] In some embodiments of the present application, the fourth module is used to:

[0153] The fourth module is used to sort all the sub-suspected factors by numerical value and combine them based on the large-small principle to obtain multiple sub-suspected factor combinations;

[0154] The fourth module is used to calculate the sub-suspected factor difference of each sub-suspected factor combination, and calculate the average value of all sub-suspected factor differences;

[0155] The fourth module is used to generate a first mark for the sub-suspected factor combination corresponding to all sub-suspected factor differences greater than the average value;

[0156] The fourth module is used to generate a second mark for the sub-suspected factor combination corresponding to all sub-suspected factor differences equal to the average value;

[0157] The fourth module is used to generate a third mark for the sub-suspected factor combination corresponding to all sub-suspected factor differences that are smaller than the average value;

[0158] The fourth module is used to count a first quantity of the first mark, a second quantity of the second mark, and a third quantity of the third mark;

[0159] The fourth module is used to calculate the suspected defect damage factor of the rotor journal to be monitored for defect damage based on the first number, the second number and the third number.

[0160] In some embodiments of the present application, the fourth module is used to:

[0161] The fourth module is used to determine whether the rotor journal to be monitored for defect damage has defect damage according to the relationship between the suspected defect damage factor and the preset suspected defect damage factor;

[0162] The fourth module is used to determine that there is no defect damage in the rotor journal to be monitored for defect damage when the suspected defect damage factor is less than the preset suspected defect damage factor;

[0163] The fourth module is used to determine whether the rotor journal to be monitored for defect damage has defect damage when the suspected defect damage factor is greater than or equal to the preset suspected defect damage factor.

[0164] In the description of the above embodiments, specific features, structures, materials or characteristics may be combined in a suitable manner in any one or more embodiments or examples.

[0165] Although the present invention has been described above with reference to the embodiments, various modifications may be made thereto and parts thereof may be replaced with equivalents without departing from the scope of the present invention. In particular, as long as there is no structural conflict, the various features in the embodiments disclosed by the present invention may be used in combination with each other in any manner, and the fact that these combinations are not fully described in this specification is only for the sake of omitting space and saving resources.

[0166] Those skilled in the art can understand that the above are only preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions recorded in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for monitoring turbine rotor journal defects, characterized in that: include: Taking multi-angle photos of the rotor journal to be monitored for defective damage to obtain multiple multi-angle images, and pre-processing and splicing the multi-angle images to obtain a panoramic image to be analyzed corresponding to the rotor journal to be monitored for defective damage; Dividing the panoramic image to be analyzed into regions to obtain a plurality of sub-panoramic image regions, and deploying a plurality of electromagnetic induction points for each sub-panoramic image region; Sending electromagnetic induction waves to the electromagnetic induction points corresponding to each sub-panoramic image area, and collecting the corresponding electromagnetic induction intensity; All electromagnetic induction intensities are analyzed, and a suspected defect damage factor of the rotor journal to be monitored for defect damage is calculated based on the analysis result, and whether the rotor journal to be monitored for defect damage has defect damage is determined according to the suspected defect damage factor.

2. The method for monitoring turbine rotor journal defects according to claim 1, characterized in that: When a rotor journal to be monitored for defective damage is photographed at multiple angles to obtain multiple multi-angle images, and the multi-angle images are preprocessed and spliced ​​to obtain a panoramic image to be analyzed corresponding to the rotor journal to be monitored for defective damage, the method includes: Preprocessing the multi-angle images, wherein the preprocessing includes image enhancement, denoising and geometric correction; Extracting key feature points from the preprocessed multi-angle images using a feature extraction algorithm, wherein the feature extraction algorithm includes one or more of a scale-invariant feature transform, an accelerated robust feature, or an oriented gradient histogram; The extracted key feature points are matched using feature matching technology to determine the transformation relationship between adjacent images; According to the transformation relationship, the matched images are stitched into a panoramic image using an image fusion technology, wherein the image fusion technology includes one or more of a weighted average method, multi-band fusion or a Laplacian pyramid fusion; The stitched panoramic image is post-processed to obtain a panoramic image to be analyzed corresponding to the rotor journal to be monitored for defect damage, wherein the post-processing includes color balance adjustment and edge smoothing.

3. The method for monitoring turbine rotor journal defects according to claim 1, characterized in that: When analyzing all electromagnetic induction intensities and calculating the suspected defect damage factor of the rotor journal to be monitored for defect damage based on the analysis results, it includes: Acquire a plurality of preset electromagnetic induction intensities corresponding to the electromagnetic induction points, and if all the electromagnetic induction intensities are equal to the preset electromagnetic induction intensities, determine that the rotor journal to be monitored for defect damage does not have defect damage; If there is one or more electromagnetic induction intensities that are not equal to the preset electromagnetic induction intensity, it is determined that there is a suspected defect damage in the rotor journal to be monitored for defect damage; Marking all sub-panoramic image regions whose electromagnetic induction strength is not equal to the preset electromagnetic induction strength as suspected; Extracting all electromagnetic induction intensities of the sub-panoramic image area carrying the suspected marker; Extracting the same electromagnetic induction intensity from all electromagnetic induction intensities and obtaining a plurality of electromagnetic induction intensity sequences; Counting the first quantity of the electromagnetic induction intensity sequence; Extracting one electromagnetic induction intensity from all electromagnetic induction intensity sequences respectively, and calculating a first electromagnetic induction intensity and value; Acquire a preset electromagnetic induction intensity, eliminate all electromagnetic induction intensity sequences that are less than the preset electromagnetic induction intensity, and count a second number of remaining electromagnetic induction intensity sequences; Extracting one electromagnetic induction intensity from the remaining electromagnetic induction intensity sequences respectively, and calculating a second electromagnetic induction intensity and value; The sub-suspected factor of the rotor journal to be monitored for defective damage is calculated according to the first number, the second number, the first electromagnetic induction intensity sum value and the second electromagnetic induction intensity sum value.

4. The method for monitoring turbine rotor journal defects according to claim 3, characterized in that: When all electromagnetic induction intensities are analyzed and the suspected defect damage factor of the rotor journal to be monitored for defect damage is calculated based on the analysis results, it also includes: All the suspected sub-factors are sorted by numerical size, and combined based on the large-small principle to obtain multiple suspected sub-factor combinations; Calculate the sub-suspected factor difference of each sub-suspected factor combination, and calculate the average of all sub-suspected factor differences; Generate a first mark for all sub-suspected factor combinations corresponding to sub-suspected factor differences greater than the average value; generating a second mark for all sub-suspected factor combinations corresponding to the sub-suspected factor differences that are equal to the average value; generating a third mark for all sub-suspected factor combinations corresponding to sub-suspected factor differences that are smaller than the average value; Counting a first quantity of the first mark, a second quantity of the second mark, and a third quantity of the third mark; A suspected defect damage factor of the rotor journal to be monitored for defect damage is calculated based on the first number, the second number, and the third number.

5. The method for monitoring turbine rotor journal defects according to claim 1, characterized in that: When judging whether the rotor journal to be monitored for defect damage has defect damage according to the suspected defect damage factor, it includes: Judging whether the rotor journal to be monitored for defect damage has defect damage according to the relationship between the suspected defect damage factor and a preset suspected defect damage factor; When the suspected defect damage factor is less than the preset suspected defect damage factor, it is determined that the rotor journal to be monitored for defect damage does not have defect damage; When the suspected defect damage factor is greater than or equal to the preset suspected defect damage factor, it is determined that the rotor journal to be monitored for defect damage has defect damage.

6. A turbine rotor journal defect damage monitoring system, characterized in that: include: The first module is used to shoot the rotor journal to be monitored for defective damage at multiple angles to obtain multiple multi-angle images, and pre-process and splice the multi-angle images to obtain a panoramic image to be analyzed corresponding to the rotor journal to be monitored for defective damage; The second module is used to divide the panoramic image to be analyzed into regions to obtain multiple sub-panoramic image regions, and deploy multiple electromagnetic induction points for each sub-panoramic image region; The third module is used to send electromagnetic induction waves to the electromagnetic induction points corresponding to each sub-panoramic image area and collect the corresponding electromagnetic induction intensity; The fourth module is used to analyze all electromagnetic induction intensities, and calculate the suspected defect damage factor of the rotor shaft journal to be monitored for defect damage based on the analysis results, and determine whether the rotor shaft journal to be monitored for defect damage has defect damage according to the suspected defect damage factor.

7. The steam turbine rotor journal defect damage monitoring system according to claim 6, wherein the first module is used for: The first module is used to pre-process the multi-angle image, wherein: The preprocessing includes image enhancement, denoising and geometric correction; The first module is used to extract key feature points from the preprocessed multi-angle image using a feature extraction algorithm, wherein the feature extraction algorithm includes one or more of a scale-invariant feature transform, an accelerated robust feature, or an oriented gradient histogram; The first module is used to match the extracted key feature points using feature matching technology to determine the transformation relationship between adjacent images; The first module is used to stitch the matched images into a panoramic image using image fusion technology according to the transformation relationship, wherein the image fusion technology includes one or more of weighted averaging, multi-band fusion or Laplacian pyramid fusion; The first module is used to post-process the stitched panoramic image to obtain the panoramic image to be analyzed corresponding to the rotor journal to be monitored for defect damage, wherein the post-processing includes color balance adjustment and edge smoothing.

8. The steam turbine rotor journal defect damage monitoring system according to claim 6, characterized in that: The fourth module is used for: The fourth module is used to obtain a plurality of preset electromagnetic induction intensities corresponding to the electromagnetic induction points, and if all the electromagnetic induction intensities are equal to the preset electromagnetic induction intensities, it is determined that the rotor journal to be monitored for defect damage does not have defect damage; The fourth module is used to determine whether there is a suspected defect damage in the rotor journal to be monitored for defect damage if there is one or more electromagnetic induction intensities that are not equal to the preset electromagnetic induction intensity; The fourth module is used to mark all sub-panoramic image areas whose electromagnetic induction intensity is not equal to the preset electromagnetic induction intensity as suspected; The fourth module is used to extract all electromagnetic induction intensities of the sub-panoramic image area carrying the suspected mark; The fourth module is used to extract the same electromagnetic induction intensity from all electromagnetic induction intensities and obtain multiple electromagnetic induction intensity sequences; The fourth module is used to count the first number of electromagnetic induction intensity sequences; The fourth module is used to extract an electromagnetic induction intensity from all electromagnetic induction intensity sequences respectively, and calculate the first electromagnetic induction intensity and value; The fourth module is used to obtain a preset electromagnetic induction intensity, eliminate all electromagnetic induction intensity sequences that are less than the preset electromagnetic induction intensity, and count the second number of remaining electromagnetic induction intensity sequences; The fourth module is used to extract one electromagnetic induction intensity from the remaining electromagnetic induction intensity sequence respectively, and calculate the second electromagnetic induction intensity and value; The fourth module is used to calculate the sub-suspected factor of the rotor journal to be monitored for defect damage according to the first number, the second number, the first electromagnetic induction intensity sum value and the second electromagnetic induction intensity sum value.

9. The steam turbine rotor journal defect damage monitoring system according to claim 8, characterized in that: The fourth module is used for: The fourth module is used to sort all the sub-suspected factors by numerical value and combine them based on the large-small principle to obtain multiple sub-suspected factor combinations; The fourth module is used to calculate the sub-suspected factor difference of each sub-suspected factor combination, and calculate the average value of all sub-suspected factor differences; The fourth module is used to generate a first mark for the sub-suspected factor combination corresponding to all sub-suspected factor differences greater than the average value; The fourth module is used to generate a second mark for the sub-suspected factor combination corresponding to all sub-suspected factor differences equal to the average value; The fourth module is used to generate a third mark for the sub-suspected factor combination corresponding to all sub-suspected factor differences that are smaller than the average value; The fourth module is used to count a first quantity of the first mark, a second quantity of the second mark, and a third quantity of the third mark; The fourth module is used to calculate the suspected defect damage factor of the rotor journal to be monitored for defect damage based on the first number, the second number and the third number.

10. The steam turbine rotor journal defect damage monitoring system according to claim 6, characterized in that: The fourth module is used for: The fourth module is used to determine whether the rotor journal to be monitored for defect damage has defect damage according to the relationship between the suspected defect damage factor and the preset suspected defect damage factor; The fourth module is used to determine that there is no defect damage in the rotor journal to be monitored for defect damage when the suspected defect damage factor is less than the preset suspected defect damage factor; The fourth module is used to determine whether the rotor journal to be monitored for defect damage has defect damage when the suspected defect damage factor is greater than or equal to the preset suspected defect damage factor.

Images