An intelligent visual inspection system for workshops

Abstract

The present invention relates to the technical field of industrial visual image analysis, and in particular to an intelligent visual inspection system for a workshop. The present invention is provided with a visual module, a feature construction module, an intelligent analysis module and an early warning prompt module. A reference rectangle is constructed by the feature construction module, and whether a bolt installation position of a steel structure has a suspected risk feature is determined according to a comparison between the reference rectangle and a bolt distribution quadrilateral. An effect characterization parameter of stress interaction is calculated by the intelligent analysis module to determine the stress interaction category of the bolt installation position. An early warning mode is selected by the early warning prompt module. Furthermore, the degree of mutual stress influence of factors such as vibration on a steel structure connection position during equipment operation is quantified in a targeted manner according to structural differences, the stress interaction of the bolt installation position is effectively evaluated, and the timeliness of potential risk discovery is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial visual image analysis, and in particular to an intelligent visual inspection system for a workshop. Background Art

[0002] In workshop production, the connection quality of steel structures is of vital importance. Bolt connection is one of the common connection methods in steel structures, but the accuracy and reliability of the bolt installation position are often difficult to quickly and accurately judge through traditional detection methods. At present, the detection of the bolt installation position of steel structures mainly relies on manual inspection, which is not only inefficient, but also prone to missed detection and false detection. In addition, the existing detection methods are difficult to effectively evaluate the stress interaction of the bolt installation position and cannot detect potential risks in time. Therefore, there is a need for a method that can quickly and accurately detect the bolt installation position in the steel structure and evaluate its stress interaction to improve the connection quality and safety of steel structures in the workshop.

[0003] For example, Chinese Patent Publication No.: CN117764966A, the invention discloses a method for detecting bolt looseness based on machine vision, including: firstly, geometrically correcting the acquired bolt image to distinguish whether it belongs to the first type of front view angle image or the second type of side view angle image; when the bolt correction image belongs to the first type of front view angle image, using a target detection dual network model composed of a YOLOv8-pose and a YOLOv8-detect network model to respectively detect the bolt key points and prediction boxes in the bolt image, and preliminarily determine the loosening angle of the bolt by using the bolt key points and the prediction boxes respectively, and then finally determine the loosening angle of the bolt by combining the key point detection results and the prediction box detection results to improve the robustness and reliability of the automated bolt loosening angle detection; when the bolt correction image belongs to the second type of side view angle image, determining the number of remaining threads of the bolt by performing instance segmentation on the bolt correction image, and determining the bolt loosening angle by using the mapping relationship between the thread feature line and the bolt loosening angle, thereby realizing bolt loosening angle detection at different shooting angles.

[0004] The existing technology does not take into account the uneven stress distribution at the bolt positions of the steel structure caused by the difference in bolt distribution. The existing technology cannot specifically quantify the degree of mutual stress influence of factors such as vibration at the steel structure connection positions during equipment operation based on structural differences, and cannot effectively evaluate the stress interaction at the bolt installation position, affecting the timeliness of the discovery of potential risks. Summary of the invention

[0005] To this end, the present invention provides an intelligent visual inspection system for a workshop, so as to overcome the problem that the prior art cannot specifically quantify the degree of mutual stress influence of factors such as vibration at the steel structure connection position during equipment operation according to structural differences, and cannot effectively evaluate the stress interaction at the bolt installation position.

[0006] To achieve the above object, the present invention provides an intelligent visual inspection system for a workshop, comprising:

[0007] A visual module, which is used to obtain an image of a region of a bolt installation position in a steel structure, wherein the bolt installation position is a connection position of the steel structure;

[0008] a feature construction module, which is connected to the visual module and is used to construct a bolt distribution quadrilateral according to the bolt holes in the regional image, and to construct a reference rectangle based on each side of the bolt distribution quadrilateral, and to determine whether the bolt installation position of the steel structure has a suspected risk feature according to the comparison between the reference rectangle and the bolt distribution quadrilateral;

[0009] an intelligent analysis module, which is connected to the visual module and the feature construction module respectively, and is used to calculate the effect characterization parameter of the stress interaction based on the steel structure size parameter of the bolt installation position, so as to determine the stress interaction category of the bolt installation position;

[0010] An early warning prompt module, which is connected to the feature construction module and the intelligent analysis module respectively, is used to select an early warning method based on different stress interaction categories, including:

[0011] Determine the number of other bolt installation positions within a preset area based on the current bolt installation position, and determine whether to issue a warning prompt for the current bolt installation position according to the number;

[0012] Alternatively, the area values ​​of the reference rectangles at the current bolt installation position are determined, and according to the fluctuation of the area values ​​of the reference rectangles, it is determined whether to issue an early warning prompt for the current bolt installation position.

[0013] Furthermore, the feature construction module is used to construct a reference rectangle, wherein:

[0014] The feature construction module uses each side of the bolt distribution quadrilateral as a reference side, and determines a rectangle whose side length is the same as the length of the reference side as the reference rectangle;

[0015] The reference rectangle and the bolt distribution quadrilateral have an overlapping area.

[0016] Furthermore, the feature construction module is used to determine the comparison between the reference rectangle and the bolt distribution quadrilateral, wherein:

[0017] The feature construction module is used to calculate the overlapping area value of each reference rectangle and the bolt distribution quadrilateral, and calculate the ratio of the overlapping area value to the area value of the bolt distribution quadrilateral, and determine the minimum ratio as the overlapping comparison parameter between the reference rectangle and the bolt distribution quadrilateral.

[0018] Furthermore, the feature construction module is also used to determine the bolt installation position of the steel structure whose comparison between the reference rectangle and the bolt distribution quadrilateral does not meet the coincidence comparison condition as having a suspected risk feature;

[0019] Among them, the overlap comparison condition is that the overlap comparison parameter exceeds the overlap comparison parameter threshold.

[0020] Furthermore, the effect characterization parameter calculated by the intelligent analysis module is positively correlated with the steel structure size parameter;

[0021] The steel structure size parameters include the maximum thickness difference, the maximum length difference and the maximum width difference of each interconnected substructure at the bolt installation position.

[0022] Further, the intelligent analysis module compares the effect characterization parameter with a stress interaction effect characterization threshold;

[0023] If the effect characterization parameter is less than or equal to the stress interaction effect characterization threshold, the intelligent analysis module determines that the bolt installation position is a weak performance category of stress interaction;

[0024] If the effect characterization parameter is greater than the stress interaction effect characterization threshold, the intelligent analysis module determines that the bolt installation position is a category with strong stress interaction performance.

[0025] Furthermore, the warning prompt module is used to select a warning method, wherein:

[0026] If the bolt installation position is a type of weak stress interaction, the early warning prompt module determines the number of other bolt installation positions in a preset area based on the current bolt installation position, and determines whether to issue an early warning prompt for the current bolt installation position according to the number;

[0027] If the bolt installation position is a category showing strong stress interaction, the early warning prompt module determines whether to issue an early warning prompt for the current bolt installation position according to fluctuations in the area values ​​of a plurality of reference rectangles.

[0028] Further, the early warning prompt module determines a circular area with a preset radius with the current bolt installation position as the center, and determines the number of bolt installation positions in the circular area except the current bolt installation position;

[0029] If the number does not exceed the preset number threshold, the early warning prompt module determines to issue an early warning prompt for the current bolt installation position.

[0030] Furthermore, the early warning module is used to determine the fluctuation of the area values ​​of several reference rectangles, wherein:

[0031] The early warning prompt module calculates the area value standard deviation according to the acquired area values ​​of each reference rectangle.

[0032] Further, the early warning prompt module is used to compare the area value standard deviation with a preset area value standard deviation threshold;

[0033] If the area value standard deviation is greater than the area value standard deviation threshold, the early warning prompt module determines to issue an early warning prompt for the current bolt installation position;

[0034] The area value standard deviation threshold is determined according to the average area value of several reference rectangles.

[0035] Compared with the prior art, the beneficial effect of the present invention lies in that the present invention sets a visual module, a feature construction module, an intelligent analysis module and an early warning prompt module, constructs a reference rectangle through the feature construction module, and determines whether the bolt installation position of the steel structure has a suspected risk feature according to the comparison between the reference rectangle and the bolt distribution quadrilateral, calculates the effect characterization parameter of the stress interaction through the intelligent analysis module to determine the stress interaction category of the bolt installation position, and selects an early warning mode through the early warning prompt module, including determining whether to issue an early warning prompt to the current bolt installation position according to the total number of bolt installation positions in the area where the current bolt installation position is located, or determining whether to issue an early warning prompt to the current bolt installation position according to the fluctuation of the area values ​​of several reference rectangles, thereby realizing the targeted quantification of the mutual influence of stresses of the steel structure connection position in the operation of the equipment due to factors such as vibration according to the structural differences, effectively evaluating the stress interaction of the bolt installation position, and improving the timeliness of potential risk discovery.

[0036] In particular, the present invention can clearly understand the distribution state of the bolts by constructing a bolt distribution quadrilateral and a reference rectangle. It can be understood that in order to ensure the uniformity of stress load distribution at the actual steel structure connection, the bolts are generally distributed in an evenly spaced state. The present invention constructs a bolt distribution quadrilateral with bolt holes as vertices and constructs a reference rectangle with each side of the bolt distribution quadrilateral as a reference, thereby quickly and clearly determining the quadrilateral at the actual bolt position and the quadrilateral with evenly spaced bolts under an ideal state.

[0037] In particular, the present invention determines whether the bolt installation of the current steel structure has a suspected stress risk characteristic by comparing the parameters of the overlap between the reference rectangle and the bolt distribution quadrilateral, and compares and calculates the area value of the quadrilateral at the actual bolt position with the quadrilateral with bolts evenly spaced in the ideal state, so as to quickly judge the degree of difference between the bolt distribution at the current bolt installation position and the regular rectangle in the ideal state. It can be understood by those skilled in the art that the greater the difference between the bolt distribution of the steel structure connection and the regular rectangle, the more likely it is to cause uneven distribution of stress during structural vibration. The present invention avoids stress concentration caused by factors such as vibration in the steel structure connection due to irregular distribution of bolt holes reserved in the steel structure by comparing and calculating the area value of the quadrilateral at the bolt position with the regular rectangle.

[0038] In particular, the present invention calculates the effect characterization parameters of stress interaction based on the steel structure size parameters. It can be understood that the greater the length difference, width difference and thickness difference of the steel structure connecting parts, the more likely the connection will be affected by stress interaction caused by mechanical vibration. Furthermore, it is possible to quantify the degree of stress interaction caused by factors such as vibration at the steel structure connection position during equipment operation in a targeted manner based on structural differences, effectively evaluate the stress interaction at the bolt installation position, and improve the timeliness of potential risk discovery.

[0039] In particular, under the general condition of stress interaction, the present invention determines whether to issue a warning prompt for the current bolt installation position according to the total number of bolt installation positions in the area where the current bolt installation position is located. It can be understood that each steel structure may reserve multiple positions for connection and installation with other steel structures. The more other bolt installation positions there are around the current bolt installation position on the steel structure, the more stability support is provided to the current steel structure. Conversely, the fewer other bolt installation positions are arranged around the current bolt installation position on the steel structure, the less stability support is provided to the current steel structure. Therefore, the stress interaction of the bolt installation positions is effectively evaluated, and the timeliness of the discovery of potential risks is improved.

[0040] In particular, under the condition that the influence of stress interaction is obvious, the present invention determines whether to issue a warning prompt for the current bolt installation position according to the fluctuation of the area values ​​of several reference rectangles. It can be understood that the closer the area values ​​of the reference rectangles of the bolt installation position of the steel structure are, the more uniform the bolt installation force representing the current bolt installation position is. On the contrary, the greater the difference in the area values ​​of the reference rectangles of the bolt installation position of the steel structure, the more irregular the bolt installation force representing the current bolt installation position is, which may lead to more obvious stress concentration of the steel structure connecting parts due to factors such as vibration during the operation of the equipment. Furthermore, it realizes the effective evaluation of the stress interaction of the bolt installation position and improves the timeliness of the discovery of potential risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 A system block diagram of an intelligent visual inspection system for a workshop according to an embodiment of the present invention;

[0042] Figure 2 A schematic diagram of a bolt distribution quadrilateral and a reference rectangle according to an embodiment of the present invention;

[0043] Figure 3 A logic flow chart of a feature construction module of an embodiment of the present invention for determining whether a bolt installation position of a steel structure has a suspected risk feature;

[0044] Figure 4 A logic flow chart of the intelligent analysis module for determining the stress interaction category of the bolt installation position according to an embodiment of the present invention;

[0045] In the figure, 1. bolt hole; 2. bolt distribution quadrilateral; 3. overlapping area; 4. reference rectangle. DETAILED DESCRIPTION

[0046] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0047] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0048] It should be noted that, in the description of the present invention, terms such as "upper", "lower", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is only for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0049] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installation" and "connection" 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 an indirect connection through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0050] See also Figures 1 to 4 As shown, Figure 1 is a system block diagram of an intelligent visual inspection system for a workshop according to an embodiment of the present invention, Figure 2 Schematic diagram of a bolt distribution quadrilateral and a reference rectangle according to an embodiment of the present invention. Figure 3 This is a logic flow chart of the feature construction module of the embodiment of the present invention for determining whether the bolt installation position of the steel structure has a suspected risk feature. Figure 4 The present invention is a logic flow chart of an intelligent analysis module for determining the stress interaction category of a bolt installation position according to an embodiment of the present invention. The present invention is an intelligent visual inspection system for a workshop, comprising:

[0051] A visual module, which is used to obtain an image of a region of a bolt installation position in a steel structure, wherein the bolt installation position is a connection position of the steel structure;

[0052] a feature construction module, which is connected to the visual module, and is used to construct a bolt distribution quadrilateral 2 according to the bolt holes 1 in the regional image, and to construct a reference rectangle 4 based on each side of the bolt distribution quadrilateral 2, and to determine whether the bolt installation position of the steel structure has a suspected risk feature according to the comparison between the reference rectangle 4 and the bolt distribution quadrilateral 2;

[0053] an intelligent analysis module, which is connected to the visual module and the feature construction module respectively, and is used to calculate the effect characterization parameter of the stress interaction based on the steel structure size parameter of the bolt installation position, so as to determine the stress interaction category of the bolt installation position;

[0054] An early warning prompt module, which is connected to the feature construction module and the intelligent analysis module respectively, is used to select an early warning method based on different stress interaction categories, including:

[0055] Determine the number of other bolt installation positions within a preset area based on the current bolt installation position, and determine whether to issue a warning prompt for the current bolt installation position according to the number;

[0056] Or, the area values ​​of the reference rectangles 4 at the current bolt installation position are determined, and according to the fluctuation of the area values ​​of the reference rectangles 4 , it is determined whether to issue an early warning prompt for the current bolt installation position.

[0057] Specifically, the present invention does not limit the specific structure of the visual module. Preferably, the visual module can be an inspection robot carrying a high-definition camera. Inspection robots are widely used in workshop production, industrial manufacturing and other fields, which will not be described in detail here.

[0058] Specifically, the present invention does not limit the specific structure of the feature construction module, which can be a processor that pre-stores relevant image algorithms. The algorithms for bolt contour recognition and quadrilateral construction are existing technologies and will not be repeated here.

[0059] Specifically, the present invention does not limit the specific structure of the intelligent analysis module, which itself can be constructed using logic components. The logic components can be programmable logic components, microprocessors, processors used in computers, etc., which will not be repeated here.

[0060] Specifically, the present invention does not limit the specific structure of the early warning prompt module, which can be a programmable logic component and a display connected to the programmable logic component. The display can display the early warning prompt content for the bolt installation position, for example, it can display the spacing distance between the bolt installation position and either end of the current steel structure.

[0061] The feature construction module is used to construct a reference rectangle 4, wherein:

[0062] The feature construction module uses each side of the bolt distribution quadrilateral 2 as a reference side, and determines a rectangle whose side length is the same as the length of the reference side as the reference rectangle 4;

[0063] The reference rectangle 4 and the bolt distribution quadrilateral 2 have an overlapping area 3 .

[0064] Please continue reading Figure 2 As shown, bolt hole 1 is used as the vertex to construct bolt distribution quadrilateral 2, and each side a, b, c and d of bolt distribution quadrilateral 2 is used as reference side to construct a rectangle with the same side length as the reference side, as shown in FIG. Figure 2 As shown, a rectangle with the same side length as the reference side a is constructed with side a as the reference side, and the rectangle is determined as the reference rectangle 4.

[0065] Specifically, the present invention can clearly understand the distribution state of the bolts by constructing a bolt distribution quadrilateral and a reference rectangle 4. It can be understood that in order to ensure the uniformity of stress load distribution at the actual steel structure connection, the bolts are generally distributed in an equidistant state. The present invention constructs a bolt distribution quadrilateral with the bolt hole 1 as the vertex and constructs a reference rectangle 4 with each side of the bolt distribution quadrilateral as a reference, thereby quickly and clearly determining the quadrilateral at the actual bolt position and the quadrilateral with equidistant bolt distribution under an ideal state.

[0066] Specifically, the feature construction module is used to determine the comparison between the reference rectangle and the bolt distribution quadrilateral 2, wherein:

[0067] The feature construction module is used to calculate the overlapping area value of each reference rectangle and the bolt distribution quadrilateral 2, and calculate the ratio of the overlapping area value to the area value of the bolt distribution quadrilateral 2, and determine the minimum ratio as the overlapping comparison parameter between the reference rectangle 4 and the bolt distribution quadrilateral 2.

[0068] Please continue reading Figure 3 As shown, the feature construction module determines that the bolt installation position of the steel structure whose comparison between the reference rectangle and the bolt distribution quadrilateral does not meet the coincidence comparison condition has a suspected risk feature;

[0069] The feature construction module determines that the bolt installation position of the steel structure, where the comparison between the reference rectangle and the bolt distribution quadrilateral meets the coincidence comparison condition, does not have a suspected risk feature;

[0070] Among them, the overlap comparison condition is that the overlap comparison parameter Cr exceeds the overlap comparison parameter threshold Cr0.

[0071] In an embodiment, the value range of the overlap comparison parameter threshold Cr0 is [90%, 93%].

[0072] Specifically, the present invention determines whether the bolt installation of the current steel structure has a suspected stress risk characteristic by comparing the parameters of the overlap between the reference rectangle and the bolt distribution quadrilateral 2, and compares and calculates the area value of the quadrilateral at the actual bolt position with the quadrilateral with bolts evenly spaced in the ideal state, so as to quickly judge the degree of difference between the bolt distribution at the current bolt installation position and the regular rectangle in the ideal state. It can be understood by those skilled in the art that the greater the difference between the bolt distribution of the steel structure connection and the regular rectangle, the more likely it is to cause uneven distribution of stress during structural vibration. The present invention avoids stress concentration caused by vibration and other factors in the steel structure connection due to the irregular distribution of the bolt holes 1 reserved in the steel structure during equipment operation by comparing and calculating the area value of the quadrilateral at the bolt position with the regular rectangle.

[0073] Specifically, the effect characterization parameter calculated by the intelligent analysis module is positively correlated with the steel structure size parameter;

[0074] The steel structure size parameters include the maximum thickness difference, the maximum length difference and the maximum width difference of each interconnected substructure at the bolt installation position.

[0075] For example, the effect characterization parameter can be calculated as follows:

[0076] Effect characterization parameter = (maximum thickness difference / preset thickness difference reference value) × thickness parameter factor + (maximum length difference / preset length difference reference value) × length parameter factor + (maximum width difference / preset width difference reference value) × width parameter factor.

[0077] Thickness parameter factor + length parameter factor + width parameter factor = 1. The preset thickness difference reference value, the preset length difference reference value and the preset width difference reference value can be determined based on the average thickness values, average length values ​​and average width values ​​of several substructures in the historical data. The average thickness value is determined as the preset thickness difference reference value, the average length value is determined as the preset length difference reference value, and the average width value is determined as the preset width difference reference value.

[0078] Specifically, the present invention calculates the effect characterization parameters of stress interaction based on the steel structure size parameters. It can be understood that the greater the length difference, width difference and thickness difference of the steel structure connecting parts, the more likely the connection will be affected by stress interaction caused by mechanical vibration. Furthermore, it is possible to quantify the degree of stress interaction caused by factors such as vibration at the steel structure connection position during equipment operation in a targeted manner based on structural differences, effectively evaluate the stress interaction at the bolt installation position, and improve the timeliness of potential risk discovery.

[0079] For more details, please refer to Figure 4 As shown, the intelligent analysis module compares the effect characterization parameter with the stress interaction effect characterization threshold;

[0080] If the effect characterization parameter is less than or equal to the stress interaction effect characterization threshold, the intelligent analysis module determines that the bolt installation position is a weak performance category of stress interaction;

[0081] If the effect characterization parameter is greater than the stress interaction effect characterization threshold, the intelligent analysis module determines that the bolt installation position is a category with strong stress interaction performance.

[0082] In an embodiment, the stress interaction effect characterization threshold is used to distinguish stress interaction categories. The larger the value of the stress interaction effect characterization threshold is, the smaller the number of bolt installation positions that are judged to be categories with strong stress interaction performance is. Preferably, the stress interaction effect characterization threshold can be [1.1, 1.2].

[0083] The early warning prompt module is used to select an early warning method, wherein:

[0084] If the bolt installation position is a type of weak stress interaction, the early warning prompt module determines the number of other bolt installation positions in a preset area based on the current bolt installation position, and determines whether to issue an early warning prompt for the current bolt installation position according to the number;

[0085] If the bolt installation position is a category showing strong stress interaction, the early warning prompt module determines whether to issue an early warning prompt for the current bolt installation position according to fluctuations in the area values ​​of a plurality of reference rectangles.

[0086] Specifically, the early warning prompt module determines a circular area with a preset radius with the current bolt installation position as the center, and determines the number of bolt installation positions in the circular area except the current bolt installation position;

[0087] If the number exceeds a preset number threshold, the early warning prompt module determines not to issue an early warning prompt for the current bolt installation position;

[0088] If the number does not exceed the preset number threshold, the early warning prompt module determines to issue an early warning prompt for the current bolt installation position.

[0089] In implementation, the preset radius of the circular area ranges from [1.5, 3], and the interval unit is m. Here, a preset radius and a preset quantity threshold value are provided. Under the condition that the preset radius is 2m, the value of the preset quantity threshold can be 2.

[0090] Specifically, under the general condition of stress interaction influence, the present invention determines whether to issue a warning prompt for the current bolt installation position according to the total number of bolt installation positions in the area where the current bolt installation position is located. It can be understood that each steel structure may reserve multiple positions for connection and installation with other steel structures. The more other bolt installation positions there are around the current bolt installation position on the steel structure, the more stability support is provided to the current steel structure. On the contrary, the fewer other bolt installation positions are arranged around the current bolt installation position on the steel structure, the less stability support is provided to the current steel structure. Therefore, the stress interaction of the bolt installation positions is effectively evaluated, and the timeliness of the discovery of potential risks is improved.

[0091] Specifically, the early warning module is used to determine the fluctuation of the area values ​​of several reference rectangles, wherein:

[0092] The early warning prompt module calculates the area value standard deviation according to the acquired area values ​​of each reference rectangle.

[0093] Specifically, the early warning prompt module is used to compare the area value standard deviation with a preset area value standard deviation threshold;

[0094] If the area value standard deviation S is less than or equal to the area value standard deviation threshold S0, the early warning prompt module determines not to issue an early warning prompt for the current bolt installation position;

[0095] If the area value standard deviation S is greater than the area value standard deviation threshold S0, the early warning prompt module determines to issue an early warning prompt for the current bolt installation position;

[0096] The area value standard deviation threshold S0 is based on the average area value S of several reference rectangles. av Sure.

[0097] Area value standard deviation threshold S0 = threshold value factor × area average S av , preferably, the value of the threshold value factor is 0.1.

[0098] Specifically, under the condition that the influence of stress interaction is obvious, the present invention determines whether to issue a warning prompt for the current bolt installation position according to the fluctuation of the area values ​​of several reference rectangles. It can be understood that the closer the area values ​​of the reference rectangles of the bolt installation position of the steel structure are, the more uniform the bolt installation force representing the current bolt installation position is. On the contrary, the greater the difference in the area values ​​of the reference rectangles of the bolt installation position of the steel structure, the more irregular the bolt installation force representing the current bolt installation position is, which may lead to more obvious stress concentration on the steel structure connecting parts due to factors such as vibration during the operation of the equipment. Furthermore, it realizes the effective evaluation of the stress interaction of the bolt installation position and improves the timeliness of the discovery of potential risks.

[0099] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0100] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. 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. An intelligent visual inspection system for a workshop, characterized in that: include: A visual module, which is used to obtain an image of a region of a bolt installation position in a steel structure, wherein the bolt installation position is a connection position of the steel structure; a feature construction module, which is connected to the visual module and is used to construct a bolt distribution quadrilateral according to the bolt holes in the regional image, and to construct a reference rectangle based on each side of the bolt distribution quadrilateral, and to determine whether the bolt installation position of the steel structure has a suspected risk feature according to the comparison between the reference rectangle and the bolt distribution quadrilateral; an intelligent analysis module, which is connected to the visual module and the feature construction module respectively, and is used to calculate the effect characterization parameter of the stress interaction based on the steel structure size parameter of the bolt installation position, so as to determine the stress interaction category of the bolt installation position; An early warning prompt module, which is connected to the feature construction module and the intelligent analysis module respectively, is used to select an early warning method based on different stress interaction categories, including: Determine the number of other bolt installation positions within a preset area based on the current bolt installation position, and determine whether to issue a warning prompt for the current bolt installation position according to the number; Alternatively, the area values ​​of the reference rectangles at the current bolt installation position are determined, and according to the fluctuation of the area values ​​of the reference rectangles, it is determined whether to issue an early warning prompt for the current bolt installation position.

2. The intelligent visual inspection system for workshops according to claim 1, characterized in that: The feature construction module is used to construct a reference rectangle, wherein: The feature construction module uses each side of the bolt distribution quadrilateral as a reference side, and determines a rectangle whose side length is the same as the length of the reference side as the reference rectangle; The reference rectangle and the bolt distribution quadrilateral have an overlapping area.

3. The intelligent visual inspection system for workshops according to claim 2 is characterized in that: The feature construction module is used to determine the comparison between the reference rectangle and the bolt distribution quadrilateral, wherein: The feature construction module is used to calculate the overlapping area value of each reference rectangle and the bolt distribution quadrilateral, and calculate the ratio of the overlapping area value to the area value of the bolt distribution quadrilateral, and determine the minimum ratio as the overlapping comparison parameter between the reference rectangle and the bolt distribution quadrilateral.

4. The intelligent visual inspection system for workshops according to claim 3 is characterized in that: The feature construction module is also used to determine the bolt installation position of the steel structure whose comparison between the reference rectangle and the bolt distribution quadrilateral does not meet the coincidence comparison condition as having a suspected risk feature; Among them, the overlap comparison condition is that the overlap comparison parameter exceeds the overlap comparison parameter threshold.

5. The intelligent visual inspection system for workshops according to claim 4 is characterized in that: The effect characterization parameter calculated by the intelligent analysis module is positively correlated with the steel structure size parameter; The steel structure size parameters include the maximum thickness difference, the maximum length difference and the maximum width difference of each interconnected substructure at the bolt installation position.

6. The intelligent visual inspection system for workshops according to claim 5, characterized in that: The intelligent analysis module compares the effect characterization parameter with the stress interaction effect characterization threshold; If the effect characterization parameter is less than or equal to the stress interaction effect characterization threshold, the intelligent analysis module determines that the bolt installation position is a weak performance category of stress interaction; If the effect characterization parameter is greater than the stress interaction effect characterization threshold, the intelligent analysis module determines that the bolt installation position is a category with strong stress interaction performance.

7. The intelligent visual inspection system for workshops according to claim 6, characterized in that: The warning prompt module is used to select a warning method, wherein: If the bolt installation position is a type of weak stress interaction, the early warning prompt module determines the number of other bolt installation positions in a preset area based on the current bolt installation position, and determines whether to issue an early warning prompt for the current bolt installation position according to the number; If the bolt installation position is a category showing strong stress interaction, the early warning prompt module determines whether to issue an early warning prompt for the current bolt installation position according to fluctuations in the area values ​​of a plurality of reference rectangles.

8. The intelligent visual inspection system for workshops according to claim 7, characterized in that: The early warning prompt module determines a circular area with a preset radius with the current bolt installation position as the center, and determines the number of bolt installation positions in the circular area except the current bolt installation position; If the number does not exceed the preset number threshold, the early warning prompt module determines to issue an early warning prompt for the current bolt installation position.

9. The intelligent visual inspection system for workshops according to claim 7, characterized in that: The early warning module is used to determine the fluctuation of the area values ​​of several reference rectangles, wherein: The early warning prompt module calculates the area value standard deviation according to the acquired area values ​​of each reference rectangle.

10. The intelligent visual inspection system for workshops according to claim 9, characterized in that: The early warning prompt module is used to compare the area value standard deviation with a preset area value standard deviation threshold; If the area value standard deviation is greater than the area value standard deviation threshold, the early warning prompt module determines to issue an early warning prompt for the current bolt installation position; The area value standard deviation threshold is determined according to the average area value of several reference rectangles.

Images