Bolt connection wear prediction method and system based on visual data analysis

Abstract

The present invention discloses a method and system for predicting bolt connection wear based on visual data analysis, the method comprising: obtaining an infrared thermal imaging image of the connection of a target bolt when it is working; judging whether the target bolt has abnormal wear according to a neural network algorithm and the infrared thermal imaging image; obtaining component parameters and connection surface images of the target bolt when the target bolt has abnormal wear; calculating the excessive wear risk probability of the target bolt according to the component parameters and the connection surface image based on an image recognition algorithm and a component parameter relationship model; the excessive wear risk probability is used to be displayed in a visual interface. It can be seen that the present invention can achieve a more reasonable and accurate prediction of bolt wear, so as to improve the safety and stability of the overall equipment and reduce safety accidents caused by bolt wear.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and system for predicting bolt connection wear based on visual data analysis. Background Art

[0002] Bolt components are a very common locking connection structure and are widely used in many devices. In some devices that have been working for a long time, how to accurately judge or even predict the degree of wear of the connection of bolt components is crucial to judging the life of the entire equipment or maintenance plan. However, in the existing technology, the wear judgment of bolt connections is still mostly carried out by human eye recognition or manual inspection. This method has no way to accurately predict the degree of wear, consumes manpower and material resources, is very inefficient, and cannot effectively detect safety accident risks. It can be seen that the existing technology has defects that need to be solved urgently. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a method and system for predicting bolt connection wear based on visual data analysis, which can achieve more reasonable and accurate bolt wear prediction, so as to improve the safety and stability of the overall equipment and reduce safety accidents caused by bolt wear.

[0004] In order to solve the above technical problems, the first aspect of the present invention discloses a method for predicting bolt connection wear based on visual data analysis, the method comprising:

[0005] Acquire infrared thermal imaging images of the target bolt connection during operation;

[0006] According to the neural network algorithm and the infrared thermal imaging image, determining whether the target bolt has abnormal wear;

[0007] When the target bolt has abnormal wear, obtaining component parameters and a connection surface image of the target bolt;

[0008] According to the component parameters and the connection surface image, based on an image recognition algorithm and a component parameter relationship model, the excessive wear risk probability of the target bolt is calculated; the excessive wear risk probability is used to be displayed in a visualization interface.

[0009] As an optional implementation, in the first aspect of the present invention, the obtaining of component parameters and connection surface image of the target bolt includes:

[0010] Determine the component parameters of the target bolt according to the infrared thermal imaging image and the template database through a feature acquisition neural network; the component parameters include appearance features and model features; the model features include bolt model, bolt position, bolt device model and bolt device position;

[0011] Sending an image acquisition instruction including the component parameters to an operating device, so as to drive the operating device to acquire an image of a connection surface of the target bolt according to the component parameters;

[0012] The connection surface image sent by the operating device is received.

[0013] As an optional embodiment, in the first aspect of the present invention, the determining the component parameters of the target bolt according to the infrared thermal imaging image and the template database by using a feature acquisition neural network includes:

[0014] The infrared thermal imaging image is input into a trained RNN neural network to obtain a segmented shape image and shape features corresponding to the target bolt; the shape features include bolt diameter, bolt length and bolt volume; the RNN neural network is trained by a training data set including a plurality of training infrared thermal imaging images and corresponding bolt image region annotations and shape feature annotations;

[0015] Calculating a first similarity between the segmented shape image and each template image in a preset bolt template image library;

[0016] Sort all the template images from large to small according to the first similarity to obtain a first image sequence;

[0017] Screening out all the template images that are a first number before the first image sequence and whose first similarity is greater than a first threshold, to obtain a plurality of candidate template images;

[0018] Calculating a second similarity between an appearance feature parameter corresponding to any of the candidate template images and the appearance feature;

[0019] The model feature corresponding to the candidate template image with the second highest similarity is determined as the model feature corresponding to the target bolt.

[0020] As an optional embodiment, in the first aspect of the present invention, judging whether the target bolt has abnormal wear according to the neural network algorithm and the infrared thermal imaging image includes:

[0021] Based on the color recognition algorithm and the image segmentation algorithm, determine the high temperature area image that meets the preset color threshold rule in the infrared thermal imaging image;

[0022] Determine the position parameters of the high-heat area image in the infrared thermal imaging image;

[0023] The position parameter and the high-heat area image are input into a trained wear abnormality prediction neural network to obtain the wear abnormality parameter of the target bolt; the wear abnormality prediction neural network is trained by a training data set including a plurality of training high-heat area images and corresponding position parameters and wear or not labels;

[0024] It is determined whether the wear abnormality parameter is greater than a second threshold value. If so, it is determined that the target bolt has wear abnormality.

[0025] As an optional implementation, in the first aspect of the present invention, determining the position parameters of the high-heat area image in the infrared thermal imaging image includes:

[0026] Calculating the overall image area and center coordinates of the infrared thermal imaging image, and establishing a coordinate system with the center coordinates as the origin;

[0027] Calculating the image area and geometric center of the high-heat region image;

[0028] Calculate the coordinates of the geometric center in the coordinate system;

[0029] Calculate the distance between the geometric center and the origin;

[0030] Calculating a ratio of the image area to the overall image area;

[0031] The coordinates, the distance and the ratio are determined as position parameters.

[0032] As an optional embodiment, in the first aspect of the present invention, the calculating the excessive wear risk probability of the target bolt according to the component parameters and the connection surface image based on an image recognition algorithm and a component parameter relationship model includes:

[0033] Determine the wear degree parameter corresponding to the connection surface image according to the image segmentation algorithm and the neural network algorithm;

[0034] Determine the application equipment and equipment location corresponding to the target bolt according to the component parameters;

[0035] Determine the working time corresponding to the application equipment;

[0036] The risk probability of excessive wear of the target bolt is calculated based on a preset correspondence model between working time, equipment position and wear degree, as well as the wear degree parameter, the working time and the equipment position.

[0037] As an optional implementation, in the first aspect of the present invention, determining the wear degree parameter corresponding to the connection surface image according to the image segmentation algorithm and the neural network algorithm includes:

[0038] Based on an image segmentation algorithm and a preset parameter threshold, the connection surface image is processed to obtain a worn area image and a non-worn area image corresponding to the connection surface image;

[0039] The worn area image and the non-worn area image are input into a trained wear degree prediction neural network to obtain the wear degree parameter corresponding to the connection surface image; the wear degree prediction neural network is trained by a training data set including a plurality of training wear images and corresponding wear degree annotations; each of the training wear images contains a pre-annotated wear area.

[0040] As an optional embodiment, in the first aspect of the present invention, the calculation of the excessive wear risk probability of the target bolt according to the preset correspondence model between the working time, the equipment position and the wear degree, and the wear degree parameter, the working time and the equipment position includes:

[0041] According to the application equipment, a corresponding relationship model between the working time corresponding to the application equipment and the normal wear degree of bolt components at different equipment positions is determined from a preset relationship database; the corresponding relationship model is established by performing polynomial fitting modeling on multiple historical collected data of the application equipment;

[0042] Inputting the working time and the equipment location into the corresponding relationship model to obtain a corresponding normal wear degree threshold;

[0043] calculating a numerical difference between the wear degree parameter and the normal wear degree threshold;

[0044] The product between the numerical difference and a preset probability weight is calculated to obtain the risk probability of excessive wear of the target bolt; the probability weight is proportional to the working time.

[0045] A second aspect of an embodiment of the present invention discloses a bolt connection wear prediction system based on visual data analysis, the system comprising:

[0046] A first acquisition module is used to acquire an infrared thermal imaging image of a connection of a target bolt when it is in operation;

[0047] A judgment module, used for judging whether the target bolt has abnormal wear according to a neural network algorithm and the infrared thermal imaging image;

[0048] A second acquisition module is used to acquire component parameters and a connection surface image of the target bolt when the target bolt has abnormal wear;

[0049] A calculation module is used to calculate the excessive wear risk probability of the target bolt according to the component parameters and the connection surface image, based on an image recognition algorithm and a component parameter relationship model; the excessive wear risk probability is used to be displayed in a visualization interface.

[0050] As an optional implementation, in the second aspect of the present invention, the specific manner in which the second acquisition module acquires the component parameters and the connection surface image of the target bolt includes:

[0051] Determine the component parameters of the target bolt according to the infrared thermal imaging image and the template database through a feature acquisition neural network; the component parameters include appearance features and model features; the model features include bolt model, bolt position, bolt device model and bolt device position;

[0052] Sending an image acquisition instruction including the component parameters to an operating device, so as to drive the operating device to acquire an image of a connection surface of the target bolt according to the component parameters;

[0053] The connection surface image sent by the operating device is received.

[0054] As an optional embodiment, in the second aspect of the present invention, the second acquisition module determines the specific manner of the component parameters of the target bolt according to the infrared thermal imaging image and the template database through a feature acquisition neural network, including:

[0055] The infrared thermal imaging image is input into a trained RNN neural network to obtain a segmented shape image and shape features corresponding to the target bolt; the shape features include bolt diameter, bolt length and bolt volume; the RNN neural network is trained by a training data set including a plurality of training infrared thermal imaging images and corresponding bolt image region annotations and shape feature annotations;

[0056] Calculating a first similarity between the segmented shape image and each template image in a preset bolt template image library;

[0057] Sort all the template images from large to small according to the first similarity to obtain a first image sequence;

[0058] Screening out all the template images that are a first number before the first image sequence and whose first similarity is greater than a first threshold, to obtain a plurality of candidate template images;

[0059] Calculating a second similarity between an appearance feature parameter corresponding to any of the candidate template images and the appearance feature;

[0060] The model feature corresponding to the candidate template image with the second highest similarity is determined as the model feature corresponding to the target bolt.

[0061] As an optional embodiment, in the second aspect of the present invention, the specific manner in which the judgment module judges whether the target bolt has abnormal wear according to the neural network algorithm and the infrared thermal imaging image includes:

[0062] Based on the color recognition algorithm and the image segmentation algorithm, determine the high temperature area image that meets the preset color threshold rule in the infrared thermal imaging image;

[0063] Determine the position parameters of the high-heat area image in the infrared thermal imaging image;

[0064] The position parameter and the high-heat area image are input into a trained wear abnormality prediction neural network to obtain the wear abnormality parameter of the target bolt; the wear abnormality prediction neural network is trained by a training data set including a plurality of training high-heat area images and corresponding position parameters and wear or not labels;

[0065] It is determined whether the wear abnormality parameter is greater than a second threshold value. If so, it is determined that the target bolt has wear abnormality.

[0066] As an optional implementation, in the second aspect of the present invention, the specific manner in which the judgment module determines the position parameters of the high-heat area image in the infrared thermal imaging image includes:

[0067] Calculating the overall image area and center coordinates of the infrared thermal imaging image, and establishing a coordinate system with the center coordinates as the origin;

[0068] Calculating the image area and geometric center of the high-heat region image;

[0069] Calculate the coordinates of the geometric center in the coordinate system;

[0070] Calculate the distance between the geometric center and the origin;

[0071] Calculating a ratio of the image area to the overall image area;

[0072] The coordinates, the distance and the ratio are determined as position parameters.

[0073] As an optional implementation, in the second aspect of the present invention, the specific manner in which the calculation module calculates the excessive wear risk probability of the target bolt according to the component parameters and the connection surface image, based on an image recognition algorithm and a component parameter relationship model, includes:

[0074] Determine the wear degree parameter corresponding to the connection surface image according to the image segmentation algorithm and the neural network algorithm;

[0075] Determine the application equipment and equipment location corresponding to the target bolt according to the component parameters;

[0076] Determine the working time corresponding to the application equipment;

[0077] The risk probability of excessive wear of the target bolt is calculated based on a preset correspondence model between working time, equipment position and wear degree, as well as the wear degree parameter, the working time and the equipment position.

[0078] As an optional implementation, in the second aspect of the present invention, the specific manner in which the calculation module determines the wear degree parameter corresponding to the connection surface image according to the image segmentation algorithm and the neural network algorithm includes:

[0079] Based on an image segmentation algorithm and a preset parameter threshold, the connection surface image is processed to obtain a worn area image and a non-worn area image corresponding to the connection surface image;

[0080] The worn area image and the non-worn area image are input into a trained wear degree prediction neural network to obtain the wear degree parameter corresponding to the connection surface image; the wear degree prediction neural network is trained by a training data set including a plurality of training wear images and corresponding wear degree annotations; each of the training wear images contains a pre-annotated wear area.

[0081] As an optional embodiment, in the second aspect of the present invention, the specific manner in which the calculation module calculates the excessive wear risk probability of the target bolt according to the preset correspondence model between the working time, the equipment position and the wear degree, the wear degree parameter, the working time and the equipment position includes:

[0082] According to the application equipment, a corresponding relationship model between the working time corresponding to the application equipment and the normal wear degree of bolt components at different equipment positions is determined from a preset relationship database; the corresponding relationship model is established by performing polynomial fitting modeling on multiple historical collected data of the application equipment;

[0083] Inputting the working time and the equipment location into the corresponding relationship model to obtain a corresponding normal wear degree threshold;

[0084] calculating a numerical difference between the wear degree parameter and the normal wear degree threshold;

[0085] The product between the numerical difference and a preset probability weight is calculated to obtain the risk probability of excessive wear of the target bolt; the probability weight is proportional to the working time.

[0086] The third aspect of the present invention discloses another bolt connection wear prediction system based on visual data analysis, the system comprising:

[0087] A memory storing executable program code;

[0088] a processor coupled to the memory;

[0089] The processor calls the executable program code stored in the memory to execute part or all of the steps in the bolt connection wear prediction method based on visual data analysis disclosed in the first aspect of the present invention.

[0090] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute part or all of the steps in the bolt connection wear prediction method based on visual data analysis disclosed in the first aspect of the present invention.

[0091] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0092] The present invention can use the infrared thermal imaging image of the bolt and the neural network algorithm to first determine whether there is an abnormality, and then accurately predict the probability of excessive wear of the bolt through component parameters and connection surface images when an abnormality exists, thereby achieving more reasonable and accurate bolt wear prediction, thereby improving the safety and stability of the overall equipment and reducing safety accidents caused by bolt wear. BRIEF DESCRIPTION OF THE DRAWINGS

[0093] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0094] Figure 1 It is a flow chart of a method for predicting bolt connection wear based on visual data analysis disclosed in an embodiment of the present invention.

[0095] Figure 2 It is a structural schematic diagram of a bolt connection wear prediction system based on visual data analysis disclosed in an embodiment of the present invention.

[0096] Figure 3 It is a structural schematic diagram of another bolt connection wear prediction system based on visual data analysis disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0097] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0098] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or equipment that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or equipment.

[0099] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0100] The present invention discloses a bolt connection wear prediction method and system based on visual data analysis, which can use infrared thermal imaging images of bolts and neural network algorithms to first determine whether there is an abnormality, and then accurately predict the probability of excessive wear of the bolts through component parameters and connection surface images when an abnormality exists, thereby achieving more reasonable and accurate bolt wear prediction, thereby improving the safety and stability of the overall equipment and reducing safety accidents caused by bolt wear. The following are detailed descriptions.

[0101] Embodiment 1

[0102] See also Figure 1 , Figure 1: is a flow chart of a bolt connection wear prediction method based on visual data analysis disclosed in an embodiment of the present invention. Figure 1 The bolt connection wear prediction method based on visual data analysis described above can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 1 As shown, the bolt connection wear prediction method based on visual data analysis may include the following operations:

[0103] 101. Obtain an infrared thermal imaging image of the connection of the target bolt when it is in operation.

[0104] 102. Based on the neural network algorithm and infrared thermal imaging images, determine whether the target bolt has abnormal wear.

[0105] 103. When the target bolt has abnormal wear, obtain component parameters and connection surface images of the target bolt.

[0106] 104. According to the component parameters and the connection surface image, based on the image recognition algorithm and the component parameter relationship model, the excessive wear risk probability of the target bolt is calculated.

[0107] Optionally, the excessive wear risk probability is used for presentation in the visualization interface.

[0108] In a specific implementation, a monitoring system for different components in large equipment is implemented, wherein the system adopts the solution of the present invention for the part of the bolt monitoring in the equipment. The system uses continuously placed infrared cameras to monitor different components in the large equipment, including bolts, and uses a background neural network algorithm to continuously determine whether there is abnormal wear of specific bolt components. This is mainly based on the difference in heat conduction in bolts with different connection tightness. After the abnormality is found, the bolt is further spirally operated by an automatic robot arm, and the connection surface image of the bolt and some component parameters are obtained through the camera, and the risk probability is further calculated. When a specific risk exists, an alarm message is generated to notify relevant personnel.

[0109] It can be seen that the above-mentioned embodiment of the invention can use the infrared thermal imaging image of the bolt and the neural network algorithm to first determine whether there is an abnormality, and then accurately predict the probability of excessive wear of the bolt through component parameters and connection surface images when an abnormality exists, thereby achieving more reasonable and accurate bolt wear prediction, thereby improving the safety and stability of the overall equipment and reducing safety accidents caused by bolt wear.

[0110] As an optional embodiment, in the above step, obtaining component parameters and connection surface images of the target bolt includes:

[0111] By using a feature acquisition neural network, the component parameters of the target bolt are determined according to the infrared thermal imaging image and the template database; optionally, the component parameters include appearance features and model features; the model features include bolt model, bolt position, bolt-to-equipment model and bolt-to-equipment position;

[0112] Sending an image acquisition instruction including component parameters to the operating device to drive the operating device to acquire an image of the connection surface of the target bolt according to the component parameters;

[0113] Receive the connection surface image sent by the operating device.

[0114] It can be seen that through the above optional embodiments, the component parameters and connection surface images of the target bolt can be acquired through feature acquisition neural networks and acquisition instructions, wherein the operating device can also be operated by an operator or through automated equipment to operate the bolts corresponding to the component parameters to achieve image acquisition, so as to accurately acquire the relevant parameters and images of the bolts, and also help to execute complex parameter and image acquisition steps after determining that there is an abnormality, reduce execution costs, and thus assist in achieving more reasonable and accurate bolt wear prediction, so as to improve the safety and stability of the overall equipment and reduce safety accidents caused by bolt wear.

[0115] As an optional embodiment, in the above steps, determining the component parameters of the target bolt by using a feature acquisition neural network according to the infrared thermal imaging image and the template database includes:

[0116] Inputting the infrared thermal imaging image into the trained RNN neural network to obtain the segmented shape image and shape features corresponding to the target bolt; optionally, the shape features include bolt diameter, bolt length and bolt volume; the RNN neural network is trained by a training data set including a plurality of training infrared thermal imaging images and corresponding bolt image region annotations and shape feature annotations;

[0117] Calculating a first similarity between the segmented shape image and each template image in a preset bolt template image library;

[0118] Sort all template images from large to small according to the first similarity to obtain a first image sequence;

[0119] Screening out all template images that are a first number before the first image sequence and whose first similarity is greater than a first threshold, to obtain a plurality of candidate template images;

[0120] Calculate the second similarity between the appearance feature parameter and the appearance feature corresponding to any candidate template image;

[0121] The model feature corresponding to the candidate template image with the second highest similarity is determined as the model feature corresponding to the target bolt.

[0122] It can be seen that through the above-mentioned optional embodiments, the component parameters of the target bolt can be determined through the RNN neural network and the bolt template image library, and the component parameters can be determined directly according to the infrared thermal imaging image without the need for manual search and determination. In the big data scenario, especially when it is necessary to monitor the wear risk of multiple bolts at the same time, parameter determination can be performed more automatically and accurately, thereby assisting in achieving a more reasonable and accurate prediction of bolt wear, so as to improve the safety and stability of the overall equipment and reduce safety accidents caused by bolt wear.

[0123] As an optional embodiment, in the above steps, judging whether the target bolt has abnormal wear according to the neural network algorithm and the infrared thermal imaging image includes:

[0124] Based on the color recognition algorithm and the image segmentation algorithm, the high-temperature area image that meets the preset color threshold rule in the infrared thermal imaging image is determined;

[0125] Determine the position parameters of the high-heat area image in the infrared thermal imaging image;

[0126] Input the position parameters and the high-heat area image into a trained wear abnormality prediction neural network to obtain the wear abnormality parameters of the target bolt; optionally, the wear abnormality prediction neural network is trained by a training data set including a plurality of training high-heat area images and corresponding position parameters and wear or not labels;

[0127] It is determined whether the wear abnormality parameter is greater than a second threshold value. If so, it is determined that the target bolt has wear abnormality.

[0128] It can be seen that through the above-mentioned optional embodiments, it is possible to cut out the high-heat area image in the infrared thermal imaging image through the color recognition algorithm and the image segmentation algorithm, and then identify its position parameters, so as to more accurately predict the abnormal wear parameters of the bolt through the trained wear abnormality prediction neural network. In practice, the wear condition can be more accurately predicted through the position parameters and the high-heat area image, thereby achieving a more reasonable and accurate prediction of bolt wear, so as to improve the safety and stability of the overall equipment and reduce safety accidents caused by bolt wear.

[0129] As an optional embodiment, in the above step, determining the position parameters of the high-heat area image in the infrared thermal imaging image includes:

[0130] Calculate the overall image area and center coordinates of the infrared thermal imaging image, and establish a coordinate system with the center coordinates as the origin;

[0131] Calculate the image area and geometric center of the high-heat region image;

[0132] Calculate the coordinates of the geometric center in the coordinate system;

[0133] Calculate the distance between the geometric center and the origin;

[0134] Calculate the ratio of the image area to the overall image area;

[0135] Determine the coordinates, distances and ratios as location parameters.

[0136] It can be seen that through the above-mentioned optional embodiments, the position parameter characteristics of the high-heat area image can be more accurately mined by calculating the coordinates of the high-heat area image, the distance from the center and the overall area ratio, so as to assist in the subsequent prediction of bolt wear, thereby assisting in achieving more reasonable and accurate bolt wear prediction, so as to improve the safety and stability of the overall equipment and reduce safety accidents caused by bolt wear.

[0137] As an optional embodiment, in the above steps, calculating the excessive wear risk probability of the target bolt according to the component parameters and the connection surface image based on the image recognition algorithm and the component parameter relationship model includes:

[0138] Determine the wear degree parameter corresponding to the connection surface image according to the image segmentation algorithm and the neural network algorithm;

[0139] According to the component parameters, determine the application equipment and equipment location corresponding to the target bolt;

[0140] Determine the working hours corresponding to the application equipment;

[0141] The risk probability of excessive wear of the target bolt is calculated based on the preset correspondence model between working time, equipment position and wear degree, as well as the wear degree parameters, working time and equipment position.

[0142] It can be seen that through the above optional embodiments, the degree of wear can be predicted by image segmentation algorithm and neural network algorithm, and the probability of excessive wear risk can be further calculated more accurately according to the equipment, location and working hours, so as to achieve more reasonable and accurate bolt wear prediction, so as to improve the safety and stability of the overall equipment and reduce safety accidents caused by bolt wear.

[0143] As an optional embodiment, in the above steps, determining the wear degree parameter corresponding to the connection surface image according to the image segmentation algorithm and the neural network algorithm includes:

[0144] Based on the image segmentation algorithm and the preset parameter threshold, the connection surface image is processed to obtain the wear area image and the non-wear area image corresponding to the connection surface image;

[0145] The worn area image and the non-worn area image are input into a trained wear degree prediction neural network to obtain wear degree parameters corresponding to the connection surface image; optionally, the wear degree prediction neural network is trained by a training data set including multiple training wear images and corresponding wear degree annotations; each training wear image contains a pre-annotated wear area.

[0146] It can be seen that through the above optional embodiments, the worn area and the normal area in the connection surface image can be first determined through the image segmentation algorithm, which can be specifically achieved through the threshold of specific image feature parameters and the image segmentation algorithm, and then the wear degree can be further predicted more accurately through the wear degree prediction neural network. In practice, the accuracy of the wear degree prediction can be effectively improved, thereby achieving a more reasonable and accurate bolt wear prediction, thereby improving the safety and stability of the overall equipment and reducing safety accidents caused by bolt wear.

[0147] As an optional embodiment, in the above steps, the excessive wear risk probability of the target bolt is calculated according to the preset correspondence model between the working time, the equipment position and the wear degree, as well as the wear degree parameter, the working time and the equipment position, including:

[0148] According to the application equipment, a corresponding relationship model between the working time corresponding to the application equipment and the normal wear degree of bolt components at different equipment positions is determined from a preset relationship database; optionally, the corresponding relationship model is established by performing polynomial fitting modeling on multiple historical collected data of the application equipment;

[0149] Input the working hours and the equipment location into the corresponding relationship model to obtain the corresponding normal wear degree threshold;

[0150] calculating a numerical difference between the wear degree parameter and a normal wear degree threshold;

[0151] The product between the numerical difference and the preset probability weight is calculated to obtain the risk probability of excessive wear of the target bolt; the probability weight is proportional to the working time.

[0152] It can be seen that through the above-mentioned optional embodiments, a mathematical relationship model corresponding to the application equipment can be established by collecting historical data for polynomial fitting to predict the current working time and the normal wear degree corresponding to the target bolt, and then the probability of excessive wear risk can be calculated based on the numerical difference and weight algorithm to more accurately evaluate the possibility of excessive wear. In practice, the accuracy of monitoring excessive wear can be effectively improved, thereby achieving a more reasonable and accurate prediction of bolt wear, thereby improving the safety and stability of the overall equipment and reducing safety accidents caused by bolt wear.

[0153] Embodiment 2

[0154] See also Figure 2 , Figure 2 : is a schematic diagram of a bolt connection wear prediction system based on visual data analysis disclosed in an embodiment of the present invention. Figure 2 The bolt connection wear prediction system based on visual data analysis described above can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 2 As shown, the bolt connection wear prediction system based on visual data analysis may include:

[0155] The first acquisition module 201 is used to acquire an infrared thermal imaging image of the connection of the target bolt when it is in operation.

[0156] The judgment module 202 is used to judge whether the target bolt has abnormal wear according to the neural network algorithm and the infrared thermal imaging image.

[0157] The second acquisition module 203 is used to acquire component parameters and connection surface images of the target bolt when the target bolt has abnormal wear.

[0158] The calculation module 204 is used to calculate the excessive wear risk probability of the target bolt according to the component parameters and the connection surface image, based on the image recognition algorithm and the component parameter relationship model.

[0159] Optionally, the excessive wear risk probability is used for presentation in the visualization interface.

[0160] It can be seen that the above-mentioned embodiment of the invention can use the infrared thermal imaging image of the bolt and the neural network algorithm to first determine whether there is an abnormality, and then accurately predict the probability of excessive wear of the bolt through component parameters and connection surface images when an abnormality exists, thereby achieving more reasonable and accurate bolt wear prediction, thereby improving the safety and stability of the overall equipment and reducing safety accidents caused by bolt wear.

[0161] As an optional embodiment, the specific manner in which the second acquisition module acquires the component parameters and the connection surface image of the target bolt includes:

[0162] By using a feature acquisition neural network, the component parameters of the target bolt are determined according to the infrared thermal imaging image and the template database; optionally, the component parameters include appearance features and model features; the model features include bolt model, bolt position, bolt-to-equipment model and bolt-to-equipment position;

[0163] Sending an image acquisition instruction including component parameters to the operating device to drive the operating device to acquire an image of the connection surface of the target bolt according to the component parameters;

[0164] Receive the connection surface image sent by the operating device.

[0165] It can be seen that through the above optional embodiments, the component parameters and connection surface images of the target bolt can be acquired through feature acquisition neural networks and acquisition instructions, wherein the operating device can also be operated by an operator or through automated equipment to operate the bolts corresponding to the component parameters to achieve image acquisition, so as to accurately acquire the relevant parameters and images of the bolts, and also help to execute complex parameter and image acquisition steps after determining that there is an abnormality, reduce execution costs, and thus assist in achieving more reasonable and accurate bolt wear prediction, so as to improve the safety and stability of the overall equipment and reduce safety accidents caused by bolt wear.

[0166] As an optional embodiment, the second acquisition module determines the specific method of the component parameters of the target bolt according to the infrared thermal imaging image and the template database through the feature acquisition neural network, including:

[0167] Inputting the infrared thermal imaging image into the trained RNN neural network to obtain the segmented shape image and shape features corresponding to the target bolt; optionally, the shape features include bolt diameter, bolt length and bolt volume; the RNN neural network is trained by a training data set including a plurality of training infrared thermal imaging images and corresponding bolt image region annotations and shape feature annotations;

[0168] Calculating a first similarity between the segmented shape image and each template image in a preset bolt template image library;

[0169] Sort all template images from large to small according to the first similarity to obtain a first image sequence;

[0170] Screening out all template images that are a first number before the first image sequence and whose first similarity is greater than a first threshold, to obtain a plurality of candidate template images;

[0171] Calculate the second similarity between the appearance feature parameter and the appearance feature corresponding to any candidate template image;

[0172] The model feature corresponding to the candidate template image with the second highest similarity is determined as the model feature corresponding to the target bolt.

[0173] It can be seen that through the above-mentioned optional embodiments, the component parameters of the target bolt can be determined through the RNN neural network and the bolt template image library, and the component parameters can be determined directly according to the infrared thermal imaging image without the need for manual search and determination. In the big data scenario, especially when it is necessary to monitor the wear risk of multiple bolts at the same time, parameter determination can be performed more automatically and accurately, thereby assisting in achieving a more reasonable and accurate prediction of bolt wear, so as to improve the safety and stability of the overall equipment and reduce safety accidents caused by bolt wear.

[0174] As an optional embodiment, the specific manner in which the judgment module judges whether the target bolt has abnormal wear according to the neural network algorithm and the infrared thermal imaging image includes:

[0175] Based on the color recognition algorithm and the image segmentation algorithm, the high-temperature area image that meets the preset color threshold rule in the infrared thermal imaging image is determined;

[0176] Determine the position parameters of the high-heat area image in the infrared thermal imaging image;

[0177] Input the position parameters and the high-heat area image into a trained wear abnormality prediction neural network to obtain the wear abnormality parameters of the target bolt; optionally, the wear abnormality prediction neural network is trained by a training data set including a plurality of training high-heat area images and corresponding position parameters and wear or not labels;

[0178] It is determined whether the wear abnormality parameter is greater than a second threshold value. If so, it is determined that the target bolt has wear abnormality.

[0179] It can be seen that through the above-mentioned optional embodiments, it is possible to cut out the high-heat area image in the infrared thermal imaging image through the color recognition algorithm and the image segmentation algorithm, and then identify its position parameters, so as to more accurately predict the abnormal wear parameters of the bolt through the trained wear abnormality prediction neural network. In practice, the wear condition can be more accurately predicted through the position parameters and the high-heat area image, thereby achieving a more reasonable and accurate prediction of bolt wear, so as to improve the safety and stability of the overall equipment and reduce safety accidents caused by bolt wear.

[0180] As an optional embodiment, the specific method in which the judgment module determines the position parameters of the high-heat area image in the infrared thermal imaging image includes:

[0181] Calculate the overall image area and center coordinates of the infrared thermal imaging image, and establish a coordinate system with the center coordinates as the origin;

[0182] Calculate the image area and geometric center of the high-heat region image;

[0183] Calculate the coordinates of the geometric center in the coordinate system;

[0184] Calculate the distance between the geometric center and the origin;

[0185] Calculate the ratio of the image area to the overall image area;

[0186] Determine the coordinates, distances and ratios as location parameters.

[0187] It can be seen that through the above-mentioned optional embodiments, the position parameter characteristics of the high-heat area image can be more accurately mined by calculating the coordinates of the high-heat area image, the distance from the center and the overall area ratio, so as to assist in the subsequent prediction of bolt wear, thereby assisting in achieving more reasonable and accurate bolt wear prediction, so as to improve the safety and stability of the overall equipment and reduce safety accidents caused by bolt wear.

[0188] As an optional embodiment, the specific manner in which the calculation module calculates the excessive wear risk probability of the target bolt according to the component parameters and the connection surface image, based on the image recognition algorithm and the component parameter relationship model, includes:

[0189] Determine the wear degree parameter corresponding to the connection surface image according to the image segmentation algorithm and the neural network algorithm;

[0190] According to the component parameters, determine the application equipment and equipment location corresponding to the target bolt;

[0191] Determine the working hours corresponding to the application equipment;

[0192] The risk probability of excessive wear of the target bolt is calculated based on the preset correspondence model between working time, equipment position and wear degree, as well as the wear degree parameters, working time and equipment position.

[0193] It can be seen that through the above optional embodiments, the degree of wear can be predicted by image segmentation algorithm and neural network algorithm, and the probability of excessive wear risk can be further calculated more accurately according to the equipment, location and working hours, so as to achieve more reasonable and accurate bolt wear prediction, so as to improve the safety and stability of the overall equipment and reduce safety accidents caused by bolt wear.

[0194] As an optional embodiment, the calculation module determines the specific manner of the wear degree parameter corresponding to the connection surface image according to the image segmentation algorithm and the neural network algorithm, including:

[0195] Based on the image segmentation algorithm and the preset parameter threshold, the connection surface image is processed to obtain the wear area image and the non-wear area image corresponding to the connection surface image;

[0196] The worn area image and the non-worn area image are input into a trained wear degree prediction neural network to obtain wear degree parameters corresponding to the connection surface image; optionally, the wear degree prediction neural network is trained by a training data set including multiple training wear images and corresponding wear degree annotations; each training wear image contains a pre-annotated wear area.

[0197] It can be seen that through the above optional embodiments, the worn area and the normal area in the connection surface image can be first determined through the image segmentation algorithm, which can be specifically achieved through the threshold of specific image feature parameters and the image segmentation algorithm, and then the wear degree can be further predicted more accurately through the wear degree prediction neural network. In practice, the accuracy of the wear degree prediction can be effectively improved, thereby achieving a more reasonable and accurate bolt wear prediction, thereby improving the safety and stability of the overall equipment and reducing safety accidents caused by bolt wear.

[0198] As an optional embodiment, the calculation module calculates the specific method of excessive wear risk probability of the target bolt according to the preset correspondence model between working time, equipment position and wear degree, as well as wear degree parameter, working time and equipment position, including:

[0199] According to the application equipment, a corresponding relationship model between the working time corresponding to the application equipment and the normal wear degree of bolt components at different equipment positions is determined from a preset relationship database; optionally, the corresponding relationship model is established by performing polynomial fitting modeling on multiple historical collected data of the application equipment;

[0200] Input the working hours and the equipment location into the corresponding relationship model to obtain the corresponding normal wear degree threshold;

[0201] calculating a numerical difference between the wear degree parameter and a normal wear degree threshold;

[0202] The product between the numerical difference and the preset probability weight is calculated to obtain the risk probability of excessive wear of the target bolt; the probability weight is proportional to the working time.

[0203] It can be seen that through the above-mentioned optional embodiments, a mathematical relationship model corresponding to the application equipment can be established by collecting historical data for polynomial fitting to predict the current working time and the normal wear degree corresponding to the target bolt, and then the probability of excessive wear risk can be calculated based on the numerical difference and weight algorithm to more accurately evaluate the possibility of excessive wear. In practice, the accuracy of monitoring excessive wear can be effectively improved, thereby achieving a more reasonable and accurate prediction of bolt wear, thereby improving the safety and stability of the overall equipment and reducing safety accidents caused by bolt wear.

[0204] Embodiment 3

[0205] See also Figure 3 , Figure 3 It is another bolt connection wear prediction system based on visual data analysis disclosed in an embodiment of the present invention. Figure 3 The described bolt connection wear prediction system based on visual data analysis is applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 3 As shown, the bolt connection wear prediction system based on visual data analysis may include:

[0206] A memory 301 storing executable program codes;

[0207] a processor 302 coupled to the memory 301;

[0208] The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the bolt connection wear prediction method based on visual data analysis described in the first embodiment.

[0209] Embodiment 4

[0210] An embodiment of the present invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the method for predicting bolt connection wear based on visual data analysis described in the first embodiment.

[0211] Embodiment 5

[0212] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the bolt connection wear prediction method based on visual data analysis described in Example 1.

[0213] The above describes specific embodiments of the present specification, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily have to be performed in the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0214] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0215] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0216] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may be in the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the embodiments of this specification may be in the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0217] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0218] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0219] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0220] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0221] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0222] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0223] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0224] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0225] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0226] Finally, it should be noted that the bolt connection wear prediction method and system based on visual data analysis disclosed in the embodiment of the present invention discloses only the preferred embodiment of the present invention, which is only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A bolt connection wear prediction method based on visual data analysis, characterized in that: The method comprises: Acquire infrared thermal imaging images of the target bolt connection during operation; According to the neural network algorithm and the infrared thermal imaging image, determining whether the target bolt has abnormal wear; When the target bolt has abnormal wear, obtaining component parameters and a connection surface image of the target bolt; According to the component parameters and the connection surface image, based on an image recognition algorithm and a component parameter relationship model, the excessive wear risk probability of the target bolt is calculated, including: Based on an image segmentation algorithm and a preset parameter threshold, the connection surface image is processed to obtain a worn area image and a non-worn area image corresponding to the connection surface image; Inputting the worn area image and the non-worn area image into a trained wear degree prediction neural network to obtain a wear degree parameter corresponding to the connection surface image; the wear degree prediction neural network is trained by a training data set including a plurality of training wear images and corresponding wear degree annotations; each of the training wear images contains a pre-annotated wear area; Determine the application equipment and equipment location corresponding to the target bolt according to the component parameters; Determine the working time corresponding to the application equipment; According to the application equipment, a corresponding relationship model between the working time corresponding to the application equipment and the normal wear degree of bolt components at different equipment positions is determined from a preset relationship database; the corresponding relationship model is established by performing polynomial fitting modeling on multiple historical collected data of the application equipment; Inputting the working time and the equipment location into the corresponding relationship model to obtain a corresponding normal wear degree threshold; calculating a numerical difference between the wear degree parameter and the normal wear degree threshold; The product between the numerical difference and a preset probability weight is calculated to obtain the excessive wear risk probability of the target bolt; the probability weight is proportional to the working time; the excessive wear risk probability is used to be displayed in a visualization interface.

2. The bolt connection wear prediction method based on visual data analysis according to claim 1 is characterized in that: The obtaining of the component parameters and the connection surface image of the target bolt includes: Determine the component parameters of the target bolt according to the infrared thermal imaging image and the template database through a feature acquisition neural network; the component parameters include appearance features and model features; the model features include bolt model, bolt position, bolt device model and bolt device position; Sending an image acquisition instruction including the component parameters to an operating device, so as to drive the operating device to acquire an image of a connection surface of the target bolt according to the component parameters; The connection surface image sent by the operating device is received.

3. The bolt connection wear prediction method based on visual data analysis according to claim 2 is characterized in that: The feature acquisition neural network determines the component parameters of the target bolt according to the infrared thermal imaging image and the template database, including: The infrared thermal imaging image is input into a trained RNN neural network to obtain a segmented shape image and shape features corresponding to the target bolt; the shape features include bolt diameter, bolt length and bolt volume; the RNN neural network is trained by a training data set including a plurality of training infrared thermal imaging images and corresponding bolt image region annotations and shape feature annotations; Calculating a first similarity between the segmented shape image and each template image in a preset bolt template image library; Sort all the template images from large to small according to the first similarity to obtain a first image sequence; Screening out all the template images that are a first number before the first image sequence and whose first similarity is greater than a first threshold, to obtain a plurality of candidate template images; Calculating a second similarity between an appearance feature parameter corresponding to any of the candidate template images and the appearance feature; The model feature corresponding to the candidate template image with the second highest similarity is determined as the model feature corresponding to the target bolt.

4. The bolt connection wear prediction method based on visual data analysis according to claim 1 is characterized in that: The determining whether the target bolt has abnormal wear according to the neural network algorithm and the infrared thermal imaging image includes: Based on the color recognition algorithm and the image segmentation algorithm, determine the high temperature area image that meets the preset color threshold rule in the infrared thermal imaging image; Determine the position parameters of the high-heat area image in the infrared thermal imaging image; The position parameter and the high-heat area image are input into a trained wear abnormality prediction neural network to obtain the wear abnormality parameter of the target bolt; the wear abnormality prediction neural network is trained by a training data set including a plurality of training high-heat area images and corresponding position parameters and wear or not labels; It is determined whether the wear abnormality parameter is greater than a second threshold value. If so, it is determined that the target bolt has wear abnormality.

5. The bolt connection wear prediction method based on visual data analysis according to claim 4 is characterized in that: The step of determining the position parameters of the high-heat area image in the infrared thermal imaging image includes: Calculating the overall image area and center coordinates of the infrared thermal imaging image, and establishing a coordinate system with the center coordinates as the origin; Calculating the image area and geometric center of the high-heat region image; Calculate the coordinates of the geometric center in the coordinate system; Calculate the distance between the geometric center and the origin; Calculating a ratio of the image area to the overall image area; The coordinates, the distance and the ratio are determined as position parameters.

6. A bolt connection wear prediction system based on visual data analysis, characterized in that: The system comprises: A first acquisition module is used to acquire an infrared thermal imaging image of a connection of a target bolt when it is in operation; A judgment module, used for judging whether the target bolt has abnormal wear according to a neural network algorithm and the infrared thermal imaging image; A second acquisition module is used to acquire component parameters and a connection surface image of the target bolt when the target bolt has abnormal wear; A calculation module is used to calculate the excessive wear risk probability of the target bolt according to the component parameters and the connection surface image based on an image recognition algorithm and a component parameter relationship model, including: Based on an image segmentation algorithm and a preset parameter threshold, the connection surface image is processed to obtain a worn area image and a non-worn area image corresponding to the connection surface image; Inputting the worn area image and the non-worn area image into a trained wear degree prediction neural network to obtain a wear degree parameter corresponding to the connection surface image; the wear degree prediction neural network is trained by a training data set including a plurality of training wear images and corresponding wear degree annotations; each of the training wear images contains a pre-annotated wear area; Determine the application equipment and equipment location corresponding to the target bolt according to the component parameters; Determine the working time corresponding to the application equipment; According to the application equipment, a corresponding relationship model between the working time corresponding to the application equipment and the normal wear degree of bolt components at different equipment positions is determined from a preset relationship database; the corresponding relationship model is established by performing polynomial fitting modeling on multiple historical collected data of the application equipment; Inputting the working time and the equipment location into the corresponding relationship model to obtain a corresponding normal wear degree threshold; calculating a numerical difference between the wear degree parameter and the normal wear degree threshold; The product between the numerical difference and a preset probability weight is calculated to obtain the excessive wear risk probability of the target bolt; the probability weight is proportional to the working time; the excessive wear risk probability is used to be displayed in a visualization interface.

7. A bolt connection wear prediction system based on visual data analysis, characterized in that: The system comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the bolt connection wear prediction method based on visual data analysis as described in any one of claims 1-5.

Images