Main body steel structure anomaly detection method and device for plug-in sound barrier

Abstract

The invention discloses a main body steel structure anomaly detection method and device for a plug-in sound barrier, and relates to the technical field of sound barrier anomaly detection. Receiving a detection request sent by a target user; an inspection route is determined according to the position corresponding to the to-be-detected area, and the inspection route is sent to the intelligent robot so that the intelligent robot can move according to the inspection route; after determining that the intelligent robot arrives at the first position, receiving image data shot by the intelligent robot; processing the image data to obtain first monitoring data; when the first monitoring data is inconsistent with preset first monitoring data, determining that the first position is in an image abnormal state, and determining a fault reason according to the image abnormal state; and selecting a first processing scheme according to the fault reason, and sending the first processing scheme to the target user, so that the target user processes the first position according to the first processing scheme. By implementing the technical scheme provided by the invention, the problem existing in a current manual inspection mode is solved.

Description

Technical Field

[0001] This application relates to the technical field of abnormal detection of sound barriers, and particularly to a method and device for abnormal detection of the main steel structure of an insertable sound barrier. Background Art

[0002] In the process of road construction and maintenance, as an effective measure to reduce the impact of traffic noise on the quality of life of surrounding residents and the ecological environment, sound barriers are increasingly widely used. Compared with the continuous layout form of traditional vertical sound barriers, insertable sound barriers achieve spatial adaptability to existing buildings through modular design. Its segmented insertable connection structure effectively avoids the need for large-scale earthwork operations and site transformation, and is particularly suitable for the protection of noise-sensitive targets in complex urban environments.

[0003] However, when exposed to harsh environments for a long time, the main steel structure of insertable sound barriers is prone to problems such as corrosion and deformation, which in turn affect its sound insulation performance and structural safety. To ensure the safety of insertable sound barriers, it is necessary to conduct abnormal detection on their steel structures. The existing maintenance system mainly relies on the periodic assessment method of manual inspections, but manual inspections have limitations such as being time-consuming, laborious, and highly subjective, which easily lead to inaccurate detection results.

[0004] Therefore, there is an urgent need for a method and device for abnormal detection of the main steel structure of an insertable sound barrier that can solve the above technical problems. Summary of the Invention

[0005] This application provides a method and device for abnormal detection of the main steel structure of an insertable sound barrier. This method conducts inspections through the use of intelligent robots, and then conducts intelligent fault diagnosis on the insertable sound barrier, improving the detection efficiency and accuracy, reducing the subjectivity and time cost of manual inspections, and thus solving the problems existing in the current method relying on manual inspections.

[0006] First aspect, the present application provides a method for detecting abnormalities in the main steel structure of a plug-in sound barrier. The method includes: receiving a detection request sent by a target user, where the detection request is used to detect abnormalities in the steel structure of the area to be detected, and the area to be detected is the area corresponding to the plug-in sound barrier; determining an inspection route according to the position corresponding to the area to be detected, and sending the inspection route to an intelligent robot so that the intelligent robot moves according to the inspection route; after determining that the intelligent robot arrives at the first position, receiving the image data captured by the intelligent robot; processing the image data to obtain first monitoring data, where the first monitoring data includes crack values, rust area values, coating peeling values, and bolt hole alignment deviation values; determining whether the first monitoring data is consistent with the preset first monitoring data; when the first monitoring data is inconsistent with the preset first monitoring data, determining that the first position is in an image abnormal state, and determining the cause of the failure according to the image abnormal state; selecting a first treatment plan according to the cause of the failure, and sending the first treatment plan to the target user so that the target user processes the first position according to the first treatment plan.

[0007] By adopting the above technical solution, the inspection route is determined according to the position corresponding to the area to be detected and sent to the intelligent robot. The intelligent robot automatically moves along the established route for detection, eliminating the need for manual inspection at each location one by one, greatly saving labor and time costs, and avoiding the large amount of time and energy consumed during the movement between different areas in the manual inspection process. Moreover, the intelligent robot replaces manual labor to perform the detection task, enabling continuous and efficient work, thereby improving the overall efficiency of the detection; the intelligent robot moves along the preset inspection route and captures image data. The capture process follows fixed standards and rules. The image data captured by the intelligent robot is processed to obtain the first monitoring data. This process is based on objective algorithms and models, which can accurately extract key information such as crack values, rust area values, coating peeling values, and bolt hole alignment deviation values, avoiding the subjective deviation that may occur in manual judgment and making the detection results more accurate and reliable. Then, it is determined in real time whether the first monitoring data is consistent with the preset first monitoring data. When inconsistency is found, the image abnormal state is determined in a timely manner and the cause of the failure is found, and then the corresponding treatment plan is selected and sent to the target user. This timely response mechanism helps to handle problems at an early stage, prevent problems from deteriorating further, ensure the health and safety of the entire steel structure, and solve the problem that manual inspection cannot comprehensively reflect the structural health status.

[0008] Optionally, after determining whether the first monitoring data is consistent with the preset first monitoring data, the method further includes: when the first monitoring data is consistent with the preset first monitoring data, receiving second monitoring data sent by the intelligent robot, where the second monitoring data is data obtained by monitoring the first position with the target sensor, and the second monitoring data includes traffic vibration value, resonance frequency value, temperature, humidity, and wind speed value; determining whether the second monitoring data is less than the preset second monitoring data; when the second monitoring data is greater than or equal to the preset second monitoring data, determining that the first position is in an abnormal environmental state, determining a second processing plan according to the abnormal environmental state, and sending the second processing plan to the target user.

[0009] By adopting the above technical solution, on the basis of the first monitoring data (such as crack value, rust area value, etc., which are data on the structure's own condition) based on image data, the second monitoring data obtained by the target sensor is added, including environmental-related data such as traffic vibration value, resonance frequency value, temperature, humidity, and wind speed value. It is determined in real time whether the second monitoring data is less than the preset second monitoring data. When the second monitoring data is greater than or equal to the preset second monitoring data, it can be quickly determined that the first position is in an abnormal environmental state. This real-time warning mechanism can timely detect abnormal changes in environmental factors, gain time for subsequent processing, avoid further damage to the sound barrier structure caused by environmental factors, determine a second processing plan according to the abnormal environmental state, and send the plan to the target user, enabling a comprehensive understanding of the environmental conditions where the sound barrier is located, thus formulating a maintenance plan that better conforms to the actual situation and improving the effect and efficiency of the maintenance work.

[0010] Optionally, the method further includes: when the first monitoring data is inconsistent with the preset first monitoring data and the second monitoring data is greater than or equal to the preset second monitoring data, determining that the first position is in an abnormal image state and an abnormal environmental state; determining whether the priority of the abnormal image state is higher than the priority of the abnormal environmental state; when the priority of the abnormal image state is higher than the priority of the abnormal environmental state, determining to send the second processing plan to the intelligent robot first, so that the intelligent robot processes the first position according to the second processing plan.

[0011] By adopting the above technical solutions, in the operation and maintenance of the plug-in sound barrier, structural safety is of utmost importance. Abnormal image states often directly reflect problems existing in the sound barrier structure itself, such as cracks, rust, coating peeling, etc. If these problems are not handled in a timely manner, they may lead to a decrease in structural strength and even cause safety accidents. When the priority of the abnormal image state is higher than that of the environmental abnormal state, giving priority to handling the abnormal image state can ensure that limited resources are concentrated on solving the problems that pose the greatest threat to structural safety, eliminate potential safety hazards in a timely manner, guarantee the normal use of the sound barrier and the safety of passing pedestrians and vehicles. The intelligent robot can quickly take actions according to the priority handling plan, improving the handling efficiency.

[0012] Optionally, processing the image data to obtain the first monitoring data specifically includes: identifying the image data to obtain the monitoring area, where the monitoring area includes the sound barrier surface area, the column structure area, the connection component area, and the sound barrier panel area; retrieving the historical image data corresponding to the first position from the preset database according to the monitoring area; processing the image data and the historical image data to obtain the deviation data, and outputting the deviation data as the first monitoring data.

[0013] By adopting the above technical solutions, identifying the image data and clearly dividing different monitoring areas such as the sound barrier surface area, the column structure area, the connection component area, and the sound barrier panel area. This refined area division helps to more accurately focus on each key part of the sound barrier, avoiding indiscriminate processing of the entire image, and improving the pertinence and efficiency of monitoring. Retrieving the historical image data corresponding to the first position from the preset database according to the monitoring area provides a reliable comparison benchmark for the current image data. Processing the image data and the historical image data to obtain the deviation data quantifies the change situation of the structure. The deviation data can intuitively reflect the difference between the current structure and the historical state, enabling the maintenance personnel to more clearly understand the actual change degree of the structure.

[0014] Optionally, determining the inspection route according to the position corresponding to the area to be detected specifically includes: obtaining a plurality of detection points corresponding to the area to be detected, and obtaining a plurality of second positions corresponding to the plurality of detection points, where one second position corresponds to one detection point; obtaining a plurality of target heights, where the target height is the height interval between the second position and the ground, and one second position corresponds to one target height; sorting the plurality of second positions in ascending order according to the target height to obtain the initial planned sorting position; obtaining the initial position corresponding to the intelligent robot currently; inputting the initial position and the initial planned sorting position into the preset path database for processing to obtain the inspection route.

[0015] By adopting the above technical solutions, the second positions and the target heights corresponding to multiple detection points in the area to be detected are obtained, and the initial planned sorting positions are obtained by sorting the second positions from smallest to largest according to the target heights. The initial position and the initial planned sorting positions currently corresponding to the intelligent robot are input into a preset path database for processing to obtain an inspection route. The preset path database may contain rich path planning algorithms and empirical data, and can comprehensively consider the initial position of the robot, the positional relationship of the detection points, and the height information to generate an optimal or sub-optimal inspection route, ensuring that the robot can efficiently and smoothly complete the inspection task. Through scientific and reasonable route planning, the robot is prevented from taking detours or repeating routes during the inspection process, reducing unnecessary moving distances and time.

[0016] Optionally, before determining the inspection route according to the position corresponding to the area to be detected, the method further includes: obtaining a target image corresponding to the area to be detected; identifying the target image to obtain the sound board material, and the sound board material includes metal sound absorption board material, transparent sound absorption board material, and polycarbonate board material; determining monitoring parameters according to the sound board material, and the monitoring parameters include first monitoring parameters, second monitoring parameters, and third monitoring parameters. The first monitoring parameters include structural load-bearing parameters, deformation parameters, rust prevention parameters, and sound absorption layer parameters. The second monitoring parameters include wind resistance stability parameters, surface aging parameters, surface crack parameters, and vibration frequency parameters. The third monitoring parameters include temperature stress parameters, corrosion parameters, and impact resistance parameters; determining the position corresponding to the area to be detected based on the monitoring parameters.

[0017] By adopting the above technical solutions, different sound board materials have different characteristics and potential problems. By identifying the sound board material and determining the corresponding monitoring parameters, a dedicated monitoring plan can be developed for each material, improving the pertinence and accuracy of monitoring. Multiple groups of monitoring parameters are determined for each sound board material, and these parameters comprehensively cover the problems that may occur to the sound board under different environments and usage conditions, ensuring a comprehensive assessment of the sound board's health status. Determining the position corresponding to the area to be detected based on the monitoring parameters can avoid non-discriminatory comprehensive monitoring of the entire sound barrier and concentrate the monitoring resources on key positions and areas prone to problems.

[0018] Optionally, selecting a first treatment plan according to the cause of the failure specifically includes: obtaining the target duration corresponding to the first position, and the target duration is the duration when the first position is in an abnormal image state; determining whether the target duration is less than or equal to a preset duration; when the target duration is less than or equal to the preset duration, determining that the abnormal image state corresponds to a low risk, and generating a first treatment plan according to the low risk and the cause of the failure; when the target duration is greater than the preset duration, determining that the abnormal image state corresponds to a high risk, and generating a first treatment plan according to the high risk and the cause of the failure.

[0019] By adopting the above technical solution, the target duration corresponding to the abnormal state of the image at the first position is obtained and compared with the preset duration, so that the risk level of the abnormal state of the image can be clearly divided. When the target duration is less than or equal to the preset duration, it is determined as a low risk; when the target duration is greater than the preset duration, it is determined as a high risk. This risk assessment method based on duration is more objective and accurate, avoiding the subjectivity and one-sidedness of relying solely on the abnormal state itself for risk assessment. When it is determined as a low risk, a first treatment plan is generated according to the low risk and the cause of the failure. A low risk usually means that the problem may be in an early stage or have a relatively small impact. At this time, relatively mild and low-cost treatment measures can be taken.

[0020] In the second aspect of the present application, an abnormal detection device for the main steel structure of a plug-in sound barrier is provided. The device includes a receiving unit, a processing unit, and a sending unit; the receiving unit receives a detection request sent by a target user, and the detection request is used to detect the abnormal condition of the steel structure in the area to be detected, and the area to be detected is the area corresponding to the plug-in sound barrier; the processing unit determines an inspection route according to the position corresponding to the area to be detected and sends the inspection route to the intelligent robot so that the intelligent robot moves according to the inspection route; after determining that the intelligent robot arrives at the first position, it receives the image data captured by the intelligent robot; processes the image data to obtain first monitoring data, and the first monitoring data includes crack value, rust area value, coating peeling value, and bolt hole alignment deviation value; determines whether the first monitoring data is consistent with the preset first monitoring data; when the first monitoring data is inconsistent with the preset first monitoring data, it determines that the first position is in an abnormal image state and determines the cause of the failure according to the abnormal image state; the sending unit selects a first treatment plan according to the cause of the failure and sends the first treatment plan to the target user so that the target user can process the first position according to the first treatment plan.

[0021] Optionally, the receiving unit is used to receive the second monitoring data sent by the intelligent robot when the first monitoring data is consistent with the preset first monitoring data. The second monitoring data is the data obtained by monitoring the first position with the target sensor, and the second monitoring data includes traffic vibration value, resonance frequency value, temperature, humidity, and wind speed value; the processing unit is used to determine whether the second monitoring data is less than the preset second monitoring data; the sending unit is used to determine that the first position is in an abnormal environment state when the second monitoring data is greater than or equal to the preset second monitoring data, determine a second treatment plan according to the abnormal environment state, and send the second treatment plan to the target user.

[0022] Optionally, the processing unit is configured to determine that the first position is in an abnormal image state and an abnormal environment state when the first monitoring data is inconsistent with the preset first monitoring data and the second monitoring data is greater than or equal to the preset second monitoring data; determine whether the priority of the abnormal image state is higher than the priority of the abnormal environment state; the sending unit is configured to determine to preferentially send the second processing solution to the intelligent robot when the priority of the abnormal image state is higher than the priority of the abnormal environment state, so that the intelligent robot processes the first position according to the second processing solution.

[0023] Optionally, the processing unit is configured to identify the image data to obtain a monitoring area, where the monitoring area includes a sound barrier surface area, a column structure area, a connection member area, and a sound barrier board area; retrieve the historical image data corresponding to the first position from a preset database according to the monitoring area; process the image data and the historical image data to obtain deviation data, and output the deviation data as the first monitoring data.

[0024] Optionally, the receiving unit is configured to obtain a plurality of detection points corresponding to the area to be detected, and obtain a plurality of second positions corresponding to the plurality of detection points, where one second position corresponds to one detection point; obtain a plurality of target heights, where the target height is the height between the second position and the ground, and one second position corresponds to one target height; the processing unit is configured to sort the plurality of second positions in ascending order according to the target heights to obtain an initial planned sorting position; the receiving unit is configured to obtain the initial position corresponding to the intelligent robot currently; the processing unit is configured to input the initial position and the initial planned sorting position into a preset path database for processing to obtain an inspection route.

[0025] Optionally, the receiving unit is configured to obtain a target image corresponding to the area to be detected; the processing unit is configured to identify the target image to obtain a sound board material, where the sound board material includes a metal sound-absorbing board material, a transparent sound-absorbing board material, and a polycarbonate board material; determine monitoring parameters according to the sound board material, where the monitoring parameters include a first monitoring parameter, a second monitoring parameter, and a third monitoring parameter, the first monitoring parameter includes a structural load-bearing parameter, a deformation parameter, an anti-rust parameter, and a sound-absorbing layer parameter, the second monitoring parameter includes a wind resistance stability parameter, a surface aging parameter, a surface crack parameter, and a vibration frequency parameter, the third monitoring parameter includes a temperature stress parameter, a corrosion parameter, and an impact resistance parameter; determine the position corresponding to the area to be detected based on the monitoring parameters.

[0026] Optionally, the receiving unit is used to obtain the target duration corresponding to the first position, where the target duration is the duration when the first position is in the image abnormal state; the processing unit is used to determine whether the target duration is less than or equal to a preset duration; when the target duration is less than or equal to the preset duration, it is determined that the image abnormal state corresponds to a low risk, and a first processing solution is generated according to the low risk and the cause of the failure; when the target duration is greater than the preset duration, it is determined that the image abnormal state corresponds to a high risk, and a first processing solution is generated according to the high risk and the cause of the failure.

[0027] In a third aspect of the present application, an electronic device is provided. The electronic device includes a processor, a memory, a user interface, and a network interface. The memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory, so that an electronic device executes the method of any one of the above in the present application.

[0028] In a fourth aspect of the present application, a computer-readable storage medium is provided. The computer-readable storage medium stores instructions, and when the instructions are executed, the method of any one of the above in the present application is executed.

[0029] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. Determine the inspection route according to the position corresponding to the area to be detected, and send the route to the intelligent robot. The intelligent robot automatically moves along the established route for detection, eliminating the need for manual inspection of each location one by one, greatly saving labor and time costs, and avoiding the large amount of time and energy consumed during the movement between different areas in the manual inspection process. Moreover, the intelligent robot replaces manual labor to perform the detection task, and can work continuously and efficiently, thus improving the overall efficiency of the detection; the intelligent robot moves along the preset inspection route and captures image data. The capture process follows fixed standards and rules. The image data captured by the intelligent robot is processed to obtain the first monitoring data. This process is based on objective algorithms and models, and can accurately extract key information such as crack numerical values, rust area numerical values, coating peeling numerical values, and bolt hole alignment deviation numerical values, avoiding the subjective deviation that may occur in manual judgment, making the detection results more accurate and reliable. Then, it is judged in real time whether the first monitoring data is consistent with the preset first monitoring data. When it is found that they are inconsistent, the image abnormal state is determined in time and the cause of the failure is found, and then the corresponding processing solution is selected and sent to the target user. This timely response mechanism helps to handle problems at an early stage when they appear, prevent problems from deteriorating further, ensure the health and safety of the entire steel structure, and solve the problem that manual inspection cannot comprehensively reflect the structural health status.

[0030] 2. Obtain the second positions and target heights corresponding to multiple detection points in the area to be detected, sort the second positions in ascending order of the target height to obtain the initial planned sorting positions, and input the current initial position and the initial planned sorting positions of the intelligent robot into a preset path database for processing to obtain the inspection route. The preset path database may contain rich path planning algorithms and empirical data, which can comprehensively consider the initial position of the robot, the positional relationship of the detection points, and the height information to generate an optimal or sub-optimal inspection route, ensuring that the robot can efficiently and smoothly complete the inspection task. Through scientific and reasonable route planning, it avoids the robot taking detours or repeating routes during the inspection process, reducing unnecessary moving distances and time. Description of the Drawings

[0031] Figure 1 It is a schematic flowchart of a method for detecting abnormalities in the main steel structure of an insertable sound barrier provided by an embodiment of the present application; Figure 2 It is a schematic structural diagram of a device for detecting abnormalities in the main steel structure of an insertable sound barrier provided by an embodiment of the present application; Figure 3 It is a schematic structural diagram of an electronic device disclosed by an embodiment of the present application.

[0032] Description of the reference numerals: 201, receiving unit; 202, processing unit; 203, sending unit; 300, electronic device; 301, processor; 302, memory; 303, user interface; 304, network interface; 305, communication bus. Detailed Embodiments

[0033] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments.

[0034] In the description of the embodiments of the present application, words such as "for example" or "for instance" are used to represent examples, illustrations, or explanations. Any embodiment or design solution described as "for example" or "for instance" in the embodiments of the present application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Exactly speaking, using words such as "for example" or "for instance" aims to present relevant concepts in a specific manner.

[0035] In the description of the embodiments of the present application, the term "a plurality of" means two or more. For example, a plurality of systems means two or more systems, and a plurality of screen terminals means two or more screen terminals. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. The terms "include", "comprise", "have" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0036] In the process of road construction and maintenance, as a measure to effectively reduce the impact of traffic noise on the living quality of surrounding residents and the ecological environment, the application of sound barriers is becoming increasingly widespread. Compared with the continuous layout form of traditional vertical sound barriers, the insert type sound barrier realizes the spatial adaptability with existing buildings through modular design. Its segmented insert connection structure effectively avoids the need for large-scale earthwork operations and site transformation, and is especially suitable for the protection of noise-sensitive targets in urban complex environments.

[0037] However, when exposed to harsh environments for a long time, the main steel structure of the insert type sound barrier is prone to problems such as corrosion and deformation, which in turn affect its sound insulation performance and structural safety. To ensure the safety of the insert type sound barrier, it is necessary to conduct abnormal detection on its steel structure. The existing maintenance system mainly relies on the periodic evaluation method of manual inspection, but manual inspection has limitations such as time-consuming, laborious, and strong subjectivity, which easily lead to the accuracy of detection results.

[0038] Therefore, how to change the defects of the current reliance on manual inspection methods and improve the detection efficiency and accuracy is an urgent problem to be solved at present. An abnormal detection method for the main steel structure of an insert type sound barrier provided by the embodiments of the present application is applied to a server. The server of the present application can be a platform that provides steel structure detection services for sound barriers. Figure 1 It is a schematic flow chart of an abnormal detection method for the main steel structure of an insert type sound barrier provided by the embodiments of the present application. Refer to Figure 1 , and this method includes the following steps S101 - step S107.

[0039] S101: Receive a detection request sent by a target user. The detection request is used to perform abnormal detection on the steel structure of the area to be detected, and the area to be detected is the area corresponding to the insert type sound barrier.

[0040] In the above S101, since the sound barrier is long-term exposed to harsh environments, and the main steel structure of the plug-in sound barrier is prone to deformation or corrosion, which will affect the sound insulation performance of the sound barrier. Therefore, it is necessary to perform abnormal detection on the steel structure of the sound barrier. The existing detection methods rely on manual regular inspections. However, manual inspections not only take a long time but are also easily affected by subjective evaluations of personnel, resulting in inaccurate detection results. This application provides a method for abnormal detection of the main steel structure of the plug-in sound barrier, which can achieve abnormal detection of the steel structure of the plug-in sound barrier. Next, it will be explained in detail how to use an intelligent robot to detect the main steel structure. The target user inputs a detection request through the user interface, which can be a web-based terminal, a mobile terminal, or a client specifically for maintaining the sound barrier. The server receives the detection request sent by the target user. The detection request contains a general description of the area to be detected. Since the area to be detected mentioned in this application refers to the area corresponding to the plug-in sound barrier, the general description includes the specific location of the plug-in sound barrier (such as a specific section of a certain road, a specific part of a certain bridge, etc.), and the purpose of the detection (such as routine inspection, fault troubleshooting, etc.). For example, the user logs in to the system on the web-based terminal, fills in "detect the steel structure of the plug-in sound barrier on the section of a certain highway from K100 to K110" in the detection request form, and then clicks the "submit" button. The server will receive this request.

[0041] S102: Determine the inspection route according to the location corresponding to the area to be detected, and send the inspection route to the intelligent robot so that the intelligent robot can move according to the inspection route.

[0042] In the above S102, before determining the location corresponding to the area to be detected, it is necessary to pre-store the geographical information data of all plug-in sound barriers in the current area in advance, including the distribution location of the barriers, the surrounding terrain, the road directions, etc. These data can be managed and maintained through a Geographic Information System (GIS). After receiving the detection request, according to the location information of the area to be detected in the detection request, extract the relevant sound barrier location coordinates from the geographical information data, and then use a path planning algorithm, combined with the location coordinates of the sound barrier and the moving ability of the intelligent robot, to plan an optimal inspection route.

[0043] In addition, before determining the inspection route according to the position corresponding to the area to be detected, it is necessary to identify the material used for the sound board of the plug-in sound barrier. The detection focuses for sound boards of different materials are different, and the detection focus is crucial for subsequent route planning. Therefore, first determine the detection focus according to the material corresponding to the area to be detected, and then determine the detection position according to the detection focus. Specifically, it includes: obtaining the target image corresponding to the area to be detected; identifying the target image to obtain the sound board material, and the sound board material includes metal sound-absorbing board material, transparent sound-absorbing board material, and polycarbonate board material; determining the monitoring parameters according to the sound board material, and the monitoring parameters include the first monitoring parameter, the second monitoring parameter, and the third monitoring parameter. The first monitoring parameter includes the structural load-bearing parameter, deformation parameter, rust prevention parameter, and sound-absorbing layer parameter. The second monitoring parameter includes the wind resistance stability parameter, surface aging parameter, surface crack parameter, and vibration frequency parameter. The third monitoring parameter includes the temperature stress parameter, corrosion parameter, and impact resistance parameter; determining the position corresponding to the area to be detected based on the monitoring parameters.

[0044] Specifically, a shooting device can be carried by a drone to conduct on-site shooting of the sound barrier area to be detected. During the shooting process, it is necessary to ensure that the image acquisition can accurately cover this area. For the shooting device, a suitable camera should be selected, such as a high-resolution digital camera, an industrial camera, etc. For situations where it is necessary to clearly identify the sound board material, a camera with a higher pixel and good color restoration ability should be chosen. During the shooting process, it is necessary to ensure that the camera is stable to reduce image blurring. In order to comprehensively obtain information on the area to be detected, the monitoring area is photographed from different angles (such as the front, side, elevation angle, depression angle, etc.). Multiple photos are taken at each angle to cover the entire monitoring area. Appropriate lighting conditions are selected for shooting to avoid direct strong light or excessive shadows affecting the image quality. Shooting can be carried out on cloudy days or during periods with uniform light, or fill lights can be used to adjust the lighting. The collected images are stored in a database and corresponding relationships are established with the positions of the areas to be detected for subsequent searching and management. Image denoising algorithms (such as Gaussian filtering, median filtering, etc.) are used to remove noise in the images and improve the image quality. Methods such as histogram equalization and contrast stretching are adopted to enhance the contrast of the images, making the features of the sound board more obvious. According to the scope of the monitoring area, the images are cropped to remove irrelevant areas and reduce the amount of calculation. The color features of the sound board in the images are extracted, such as RGB values, HSV values, etc. Sound boards of different materials may have different color features. For example, metal sound-absorbing boards may appear silver-gray, and transparent sound-absorbing boards have transparent or semi-transparent characteristics. Texture analysis algorithms (such as gray-level co-occurrence matrix, wavelet transform, etc.) are used to extract the texture features of the sound board. The textures of sound boards of different materials may be different. For example, polycarbonate boards may have relatively smooth textures. The shape features of the sound board are extracted, such as edge contours, corner points, etc. The edge information of the sound board can be obtained through edge detection algorithms (such as Canny edge detection). Machine learning algorithms (such as decision trees, convolutional neural networks, etc.) are used to classify and identify the extracted features. When training the classification model, a large number of labeled image data of sound boards of different materials are required for training. During the training process, methods such as cross-validation are used to evaluate the model, and the model is optimized according to the evaluation results to improve the accuracy of classification and recognition. The target image to be recognized is input into the trained model, and the model outputs the recognition result to determine the material of the sound board, such as metal sound-absorbing board material, transparent sound-absorbing board material, and polycarbonate board material. After determining the material corresponding to the sound board in the area to be detected, the monitoring focus is then determined according to the sound board material. At this time, the monitoring focus is on the monitoring parameters. For example, metal sound-absorbing boards are easily affected by rust, so anti-rust parameters need to be monitored; transparent sound-absorbing boards need to focus on surface aging and crack conditions, while polycarbonate sound-absorbing boards need to focus on temperature and corrosion conditions. The monitoring parameters include the first monitoring parameter, the second monitoring parameter, and the third monitoring parameter, and one monitoring parameter corresponds to one material.When the area to be detected is made of metal sound-absorbing board, determine the first monitoring parameter. The first monitoring parameter includes structural load-bearing parameters (such as bearing capacity, deformation amount, etc.), deformation parameters (such as bending deformation, torsional deformation, etc.), anti-rust parameters (such as rust area, rust depth, etc.), and sound-absorbing layer parameters (such as sound absorption coefficient, sound-absorbing layer thickness, etc.). When the area to be detected is made of transparent sound-absorbing board, determine the second monitoring parameter. The second monitoring parameter includes wind resistance stability parameters (such as wind pressure resistance ability, wind vibration coefficient, etc.), surface aging parameters (such as surface yellowing degree, glossiness change, etc.), surface crack parameters (such as crack length, crack width, etc.), and vibration frequency parameters (such as natural frequency, vibration amplitude, etc.). When the area to be detected is made of polycarbonate board, determine the third monitoring parameter. The third monitoring parameter includes temperature stress parameters (such as thermal expansion coefficient, temperature deformation amount, etc.), corrosion parameters (such as chemical corrosion degree, acid and alkali resistance performance, etc.), and impact resistance parameters (such as impact strength, impact toughness, etc.). Then analyze the historical monitoring data to find the sound barrier positions corresponding to the anomalies of different monitoring parameters. For example, when the structural load-bearing parameter is abnormal, it may correspond to certain support structure positions of the sound barrier; when the surface crack parameter is abnormal, it may correspond to a specific area of the sound board. Then, combined with the structural characteristics of the sound barrier, analyze the relationship between different monitoring parameters and the sound barrier positions. For example, the connection parts of the sound barrier are more likely to have deformation and cracks, so these parts need to be focused on when determining the monitoring positions. According to the correlation analysis results of parameters and positions, determine the high-risk areas, that is, the areas where the monitoring parameters are likely to be abnormal. For example, for metal sound-absorbing boards, in the positions near the sea or industrial pollution areas, the anti-rust parameters are more likely to be abnormal, so these areas are determined as key monitoring positions. The key parts of the sound barrier, such as the connection between the column and the sound board, the top and bottom of the sound barrier, etc., also need to be used as key monitoring positions because the structural integrity of these parts is crucial to the safety of the entire sound barrier. Mark the determined key monitoring positions on the actual structure of the sound barrier for subsequent inspection route planning based on the key monitoring positions.

[0045] Furthermore, determine the inspection route according to the position corresponding to the area to be detected, specifically including: obtaining a plurality of detection points corresponding to the area to be detected, and obtaining a plurality of second positions corresponding to the plurality of detection points, where one second position corresponds to one detection point; obtaining a plurality of target heights, where the target height is the height between the second position and the ground, and one second position corresponds to one target height; sorting the plurality of second positions in ascending order according to the target height to obtain the initial planned sorting position; obtaining the current initial position corresponding to the intelligent robot; inputting the initial position and the initial planned sorting position into a preset path database for processing to obtain the inspection route.

[0046] Specifically, within the area to be detected, multiple detection points are generated in a uniformly distributed manner. The grid division method can be used to divide the area into several small grids, and the center point of each grid is used as a detection point. For example, for an area to be detected with a size of 10m×10m, it can be divided into small grids of 1m×1m, generating 100 detection points. After the sound board material corresponding to the area to be detected has been identified, the monitoring parameters are determined based on the sound board material, and then the monitoring key points are determined according to the monitoring parameters. The detection points can be appropriately densified based on these monitoring key points to improve the detection accuracy. That is, in addition to using the center of each divided grid as a detection point, it is also necessary to determine the monitoring parameters based on the sound board material of the current area to be detected, determine the specific positions or parts of the monitoring parameters in the sound barrier, and use these positions and parts as detection points as well. For each detection point, obtain its coordinates in the three-dimensional space, and this coordinate is the second position. Measuring devices such as laser rangefinders and total stations can be used, or the positioning system of an intelligent robot can be utilized for measurement. Record the coordinate information of each second position for subsequent use. The recording format can adopt common coordinate representation methods, such as (x, y, z), where x and y represent the plane coordinates and z represents the height coordinate. Methods such as level measurement and GPS height measurement can be used to measure the height between the ground of the area to be detected and the second position. The level determines the ground height by measuring the height difference between different points, and GPS height measurement uses satellite signals to obtain the elevation information of ground points. Integrate the measured ground height data to form a ground height model. Geographic Information System (GIS) software can be used to represent the ground height data in the form of grids or vectors. For each second position, calculate the height difference between it and the corresponding ground point, and this height difference is the target height. The target height can be obtained by subtracting the height value of the corresponding point in the ground height model from the z coordinate of the second position. Associate each target height with the corresponding second position to ensure that each second position has a unique target height. Common sorting algorithms, such as bubble sort and selection sort, can be used to sort multiple target heights. Although the time complexity of these algorithms is relatively high, they are feasible for sorting a small number of second positions. Combine each second position and its corresponding target height into a data pair, for example, (coordinates of the second position, target height). Sort the data pairs according to the target height, and the order of the second positions in the data pairs after sorting the target height is the initial planning sorting position. That is, sort multiple data pairs in ascending order of the target height to obtain the initial planning sorting position, where the one with the lowest target height is ranked first and the one with the highest target height is ranked last. Intelligent robots are usually equipped with built-in positioning systems, such as GPS and Inertial Navigation System (INS). By reading the data of the positioning system, the current plane coordinates (x, y) and height coordinate (z) of the robot can be obtained. Obtain the initial position coordinates of the robot from the positioning system and record them.The recording format is consistent with the coordinate format of the second position for subsequent processing. In the preset path database, multiple path planning algorithms are pre-stored, such as the A* algorithm, Dijkstra algorithm, etc. These algorithms can generate the optimal inspection route according to different scenarios and requirements. The database also stores the map data of the area to be detected, including the obstacle positions, terrain information, etc. These data will be used for collision detection and path optimization during the path planning process. The data formats of the initial position and the initial planned sorting position are converted into the formats recognizable by the database. The database performs path planning calculations based on the stored path planning algorithms and map data. During the path planning process, factors such as the movement performance and energy consumption of the robot are considered to optimize the generated path. For example, high-energy-consuming actions such as sharp turns and climbing slopes of the robot are avoided. The database outputs the generated inspection route, and the inspection route contains a series of path points, and each path point corresponds to a second position or an intermediate point that the robot needs to pass through. The output format can be a sequence of path point coordinates, or a detailed path description containing path point coordinates, movement directions, speeds, etc. For example, if the area to be detected is a straight highway and the sound barriers are evenly distributed on both sides of the road, an inspection route that passes through each sound barrier along the road in turn can be planned to avoid the robot making frequent round trips.

[0047] Furthermore, in addition to path planning by height, the single inspection area that the intelligent robot can cover at one time can be obtained, and then the area to be detected is divided according to the inspection area to obtain multiple sub-areas to be detected. Then, an inspection route is generated based on the positions of the multiple sub-areas to be detected and the initial position of the intelligent robot. For example, the single inspection area that the intelligent robot can cover at one time is 0.8 m², and the area of the area to be detected is known to be 50 m². It is also necessary to judge the composition shape of the area to be detected. If the area to be detected consists of three rectangles, where the areas of two rectangles are both 20 m² and the area of the other rectangle is 10 m², at this time, the three rectangles are divided in turn according to the single inspection area that the intelligent robot can cover at one time, and then multiple sub-areas to be detected are obtained. Then, an inspection route is planned based on the multiple sub-areas to be detected and the initial position.

[0048] In addition, after generating the inspection route according to the position of the area to be detected, a communication connection is established with the intelligent robot in advance. The communication method can be wireless communication (such as Wi-Fi, Bluetooth, 4G / 5G, etc.) or wired communication (such as Ethernet). The planned inspection route data is encapsulated in a format recognizable by the intelligent robot, such as the JSON format. The encapsulated route data is sent to the intelligent robot through the communication interface. After receiving the data, the intelligent robot will parse and store it for subsequent movement according to this route.

[0049] S103: After determining that the intelligent robot arrives at the first position, receive the image data captured by the intelligent robot.

[0050] In the above S103, the intelligent robot is equipped with positioning sensors (such as GPS, lidar, etc.) and can obtain its own position information in real time. When the robot moves to the first position, the positioning sensor will trigger a signal to notify the robot to start taking pictures. At this time, the first position refers to the start position specified by the inspection route that the intelligent robot has reached. The robot uses the built-in camera to take pictures of the first position according to the preset shooting parameters (such as resolution, focal length, shooting angle, etc.) to obtain image data. After the shooting is completed, the robot sends the image data back to the system through the communication interface. After receiving the image data, the system stores and backs it up for subsequent processing. For example, when the intelligent robot moves to the first sound barrier position, after accurate GPS positioning, the robot automatically activates the camera to take pictures of the steel structure at this position, and then sends the image data back to the server through Wi-Fi.

[0051] S104: Process the image data to obtain the first monitoring data, and the first monitoring data includes crack values, rust area values, coating peeling values, and bolt hole alignment deviation values.

[0052] In the above S104, after obtaining the image data, an image processing algorithm is used to process the received image data. First, image preprocessing is performed, including operations such as denoising and enhancing contrast to improve the image quality. Object detection algorithms (such as YOLO, Faster R-CNN, etc.) are used to identify steel structure components in the image, such as cracks, rust areas, coating peeling parts, and bolt holes.

[0053] In addition, the image data is processed to obtain the first monitoring data, which specifically includes: identifying the image data to obtain the monitoring area, where the monitoring area includes the sound barrier surface area, the column structure area, the connection part area, and the sound barrier panel area; retrieving the historical image data corresponding to the first position from the preset database according to the monitoring area; processing the image data and the historical image data to obtain the deviation data, and outputting the deviation data as the first monitoring data. Specifically, the image data captured by the intelligent robot may have problems such as noise and uneven light, and thus needs to be preprocessed first. The server receives the image data sent by the intelligent robot, which is usually stored in common image formats (such as JPEG, PNG, etc.). Image denoising algorithms, such as Gaussian filtering and median filtering, are used to remove the noise in the image. For example, Gaussian filtering smooths the image and reduces noise interference by performing weighted averaging on each pixel in the image and its neighboring pixels. Methods such as histogram equalization and contrast stretching are used to enhance the contrast of the image, making the target area in the image more obvious. Histogram equalization adjusts the gray histogram of the image to make the gray distribution of the image more uniform, thereby improving the contrast of the image. Image processing techniques are used to extract features in the image, such as edges, corners, textures, etc. For example, the Canny edge detection algorithm is used to detect the edge information in the image, and this edge information can help identify different areas of the sound barrier. Template images of the sound barrier surface area, the column structure area, the connection part area, and the sound barrier panel area are prepared in advance. The template images are matched with the preprocessed images, and the position of the target area is determined by calculating the similarity. For example, the normalized cross-correlation algorithm is used to calculate the similarity between the template image and each sub-area in the image, and the area with the highest similarity is the matched target area. A machine learning model (such as a convolutional neural network CNN) is trained using a large number of labeled sound barrier image data. The model learns the feature patterns of different areas, and then classifies the input images to identify the sound barrier surface area, the column structure area, the connection part area, and the sound barrier panel area. According to the results of the target area identification, the specific positions of the sound barrier surface area, the column structure area, the connection part area, and the sound barrier panel area are marked in the image, and these marked areas are the monitoring areas. The relevant information of the first position is extracted from the obtained monitoring area information. The first position usually refers to the corresponding area in the currently captured image. According to the division of the monitoring area, the area type (such as the sound barrier surface, column, etc.) and the specific position coordinates where the first position is located are determined. A large number of sound barrier image data taken at different positions and different times are stored in the preset database, and each image data is associated with information such as the shooting position and the shooting time. The corresponding historical image data is queried from the preset database according to the first position, and the historical image data refers to the image data corresponding to the first position at the most recent time.Compare the currently captured image data with the retrieved historical image data, that is, determine whether there are differences between the historical image data and the image data. If there are differences, calculate the differences to obtain a monitoring value, and then output the monitoring value as the first monitoring data. At this time, the monitoring value refers to the deviation data. If any differences such as cracks, rust, coating peeling areas, and bolt holes are found when comparing the historical image data with the image data, calculations need to be performed separately for different situations. For cracks, use an edge detection algorithm (such as the Canny algorithm) to extract the contour of the crack and calculate the length and width values of the crack. For the rust area, based on the color and texture features of the image, use an image segmentation algorithm (such as threshold segmentation, region growing, etc.) to determine the scope of the rust area and calculate the rust area value. For the coating peeling area, identify the peeling area by comparing the image features of the normal coating and the peeling area, and calculate the area value of the coating peeling. For bolt holes, use a template matching algorithm to determine the positions of the bolt holes and calculate the alignment deviation value between the bolt holes.

[0054] For example, after preprocessing the captured sound barrier image, use the YOLO algorithm to identify the cracks in the image, and use the Canny algorithm to calculate that the length of the crack is 5 cm and the width is 0.2 cm. At the same time, use the threshold segmentation algorithm to determine that the rust area is 10 cm².

[0055] S105: Determine whether the first monitoring data is consistent with the preset first monitoring data.

[0056] In the above S105, after obtaining the first monitoring data corresponding to the first position, then obtain the preset first monitoring data corresponding to the first position. The preset first monitoring data is the normal value range determined according to the design standards of the sound barrier, historical detection data, and industry specifications. Compare each value in the first monitoring data with the corresponding value range in the preset first monitoring data. If all values are within the normal range, it is determined to be consistent; if any one value exceeds the normal range, it is determined to be inconsistent. For example, the normal range of the crack value is set to less than 0.1 cm, and the normal range of the rust area value is set to less than 5 cm², etc. The crack value in the first monitoring data is 5 cm, while the normal range of the crack value in the preset first monitoring data is less than 0.1 cm, so it is determined that the first monitoring data is inconsistent with the preset first monitoring data.

[0057] S106: When the first monitoring data is inconsistent with the preset first monitoring data, determine that the first position is in an abnormal image state, and determine the cause of the failure according to the abnormal image state.

[0058] In the above S106, when the first monitoring data is inconsistent with the preset first monitoring data, it is determined that the first position is in an abnormal image state. According to the characteristics of the abnormal numerical values in the first monitoring data, combined with historical failure cases and the sound board material of the area to be detected, possible failure causes are analyzed. For example, if the crack value is large, it may be caused by reasons such as structural fatigue and external force impact; if the rust area is large, it may be caused by reasons such as high environmental humidity and inadequate anti-corrosion measures.

[0059] S107: Select the first treatment plan according to the failure cause and send the first treatment plan to the target user so that the target user can process the first position according to the first treatment plan.

[0060] In the above S107, according to the determined cause of the fault, a suitable first treatment plan is selected from a preset treatment plan library. The treatment plan library contains treatment methods corresponding to various common faults, such as crack repair methods, rust treatment measures, etc. Selecting the first treatment plan according to the cause of the fault specifically includes: obtaining the target duration corresponding to the first position, where the target duration is the duration during which the first position is in an abnormal image state; determining whether the target duration is less than or equal to a preset duration; when the target duration is less than or equal to the preset duration, determining that the abnormal image state corresponds to a low risk, and generating a first treatment plan based on the low risk and the cause of the fault; when the target duration is greater than the preset duration, determining that the abnormal image state corresponds to a high risk, and generating a first treatment plan based on the high risk and the cause of the fault. Specifically, after determining that the first position is in an abnormal image state, obtain the most recent detection result corresponding to the first position, and determine whether the detection result is in an abnormal state. If the detection result is in a normal state, but at this time the first position is in an abnormal state, so the time when the abnormal state occurred is analyzed to be between the most recent detection and this detection. Therefore, obtain the most recent detection time of the first position, then obtain this detection time, and then calculate the most recent detection time and this detection time to obtain the target duration. At this time, the target duration refers to the duration during which the first position is in an abnormal image state. For example, the most recent detection time is 12:00 on March 4th, and this detection time is 12:00 on March 14th. At this time, the target duration is 240 hours. Then determine whether the target duration is less than or equal to the preset duration. The preset duration is determined comprehensively based on factors such as historical data, industry experience, and equipment characteristics. The preset duration can also be dynamically adjusted according to the actual situation. Compare the calculated target duration with the preset duration numerically. When the target duration is less than or equal to the preset duration, determine that the abnormal image state corresponds to a low risk. Then perform correlation analysis on the abnormal state of the first position and relevant fault data. For example, check information such as the equipment operation status and environmental parameters before and after the abnormality at this position to find out the possible causes of the abnormality. Based on the low risk and the cause of the fault, formulate a first treatment plan. The treatment plan should follow the principles of minimizing impact and rapid recovery. For example, if the cause of the fault is slight contamination of the lens, the treatment plan can be to arrange personnel to clean the lens. When the target duration is greater than the preset duration, determine that the abnormal image state corresponds to a high risk. This is because a long-term abnormal state may mean the existence of serious equipment failures or safety hazards. In the case of high risk, a more comprehensive analysis of the cause of the fault is required. In addition to checking the equipment operation status and environmental parameters, it may also be necessary to conduct a more in-depth inspection and testing of the equipment. Analyze from multiple dimensions, such as hardware failures, software failures, network failures, etc., to find out the root cause of the abnormality. The treatment plan in the case of high risk should follow the principle of emergency response and take measures as soon as possible to prevent the problem from deteriorating further. For example, if the cause of the fault is damage to a key component of the equipment, the treatment plan may be to immediately shut down the equipment for repair or replace the component.After determining the first treatment plan, the selected first treatment plan is encapsulated into a report in a clear and understandable manner and sent to the user through the user interface or by email, text message, etc. The report should include information such as treatment steps, required materials and tools, precautions, etc. When detecting abnormalities in the steel structures at other positions in the inspection route, the method of abnormal monitoring of the first position described above can be referred to, so as to complete the abnormal monitoring of the steel structures in the entire area to be detected.

[0061] In addition, when the first monitoring data is consistent with the preset first monitoring data, the second monitoring data sent by the intelligent robot is received. The second monitoring data is the data obtained by monitoring the first location with the target sensor, and the second monitoring data includes traffic vibration value, resonance frequency value, temperature, humidity, and wind speed value. Determine whether the second monitoring data is less than the preset second monitoring data. When the second monitoring data is greater than or equal to the preset second monitoring data, it is determined that the first location is in an abnormal environmental state, a second processing plan is determined according to the abnormal environmental state, and the second processing plan is sent to the target user. Specifically, continuously compare the first monitoring data with the preset first monitoring data. When it is detected that all the first monitoring data (such as crack value, rust area value, coating peeling value, and bolt hole alignment deviation value) are within the normal range specified by the preset first monitoring data, it is determined that the two are consistent. After the intelligent robot completes the acquisition and processing of the image data and confirms that the first monitoring data is normal, it will activate the target sensor to collect the second monitoring data. The intelligent robot encapsulates the second monitoring data (traffic vibration value, resonance frequency value, temperature, humidity, and wind speed value) obtained by monitoring the first location with the target sensor (such as vibration sensor, temperature sensor, humidity sensor, wind speed sensor, etc.) according to the predetermined communication protocol, and then sends it to the server. Compare the obtained second monitoring data with the preset second monitoring data. The preset second monitoring data is the normal value range determined according to the design requirements of the plug-in sound barrier, the use environment standard, and the relevant industry specifications. For example, the normal range of the traffic vibration value may be less than 8 m / s², the normal range of the resonance frequency value may be less than 15 Hz, the normal range of the temperature may be -20°C - 60°C, the normal range of the humidity may be 0% - 80%, and the normal range of the wind speed may be less than 10 m / s. Compare each value in the received second monitoring data with the corresponding value range in the preset second monitoring data one by one. If each value in the second monitoring data is less than the corresponding upper limit value in the preset second monitoring data, it is determined that the second monitoring data is less than the preset second monitoring data. If any one value is greater than or equal to the preset upper limit value, it is determined that the second monitoring data is greater than or equal to the preset second monitoring data. When it is determined that there is at least one value in the second monitoring data that is greater than or equal to the corresponding upper limit value in the preset second monitoring data, trigger the environmental abnormal state determination mechanism. The server will record the specific items and values of the abnormal data for subsequent analysis of the fault cause. Mark the status of the first location as an abnormal environmental state and associate the relevant second monitoring data for convenient subsequent query and processing. Mark the status of the first location as an abnormal environmental state and associate the relevant second monitoring data for convenient subsequent query and processing. Select a suitable second processing plan from the preset processing plan library according to the analyzed fault cause.The second processing solution library contains processing methods corresponding to various common environmental anomalies, such as adjusting the sound barrier structure to avoid the resonance frequency, strengthening the wind protection measures of the sound barrier, improving the heat insulation and moisture-proof performance of the sound barrier, etc. The above solutions can further analyze the environmental monitoring data when the image monitoring data is normal, timely detect the abnormal environmental state, and provide corresponding processing solutions for users.

[0062] In a possible implementation, when the first monitoring data is inconsistent with the preset first monitoring data and the second monitoring data is greater than or equal to the preset second monitoring data, it is determined that the first position is in an image abnormal state and an environmental abnormal state; it is judged whether the priority of the image abnormal state is higher than the priority of the environmental abnormal state; when the priority of the image abnormal state is higher than the priority of the environmental abnormal state, it is determined to preferentially send the second processing plan to the intelligent robot so that the intelligent robot processes the first position according to the second processing plan. Specifically, continuously receive the first monitoring data sent by the intelligent robot, which includes crack numerical values, rust area numerical values, coating peeling numerical values, bolt hole alignment deviation numerical values, etc. Compare each item of the first monitoring data with the corresponding normal numerical range in the preset first monitoring data. If at least one numerical value in the first monitoring data exceeds the preset normal range, it is determined that the first position is in an image abnormal state. After the comparison between the first monitoring data and the preset first monitoring data is completed, if there is an inconsistency (i.e., image abnormality), the second monitoring data sent by the intelligent robot will continue to be received, including traffic vibration numerical values, resonance frequency numerical values, temperature, humidity, and wind speed numerical values, etc. Compare each item of the second monitoring data with the corresponding normal numerical range in the preset second monitoring data. If at least one numerical value in the second monitoring data is greater than or equal to the preset upper limit value, it is determined that the first position is in an environmental abnormal state. When the first monitoring data is inconsistent with the preset first monitoring data (image abnormality) and the second monitoring data is greater than or equal to the preset second monitoring data (environmental abnormality), it is comprehensively determined that the first position is simultaneously in an image abnormal state and an environmental abnormal state. Analyze the degree of influence of the image abnormal state (such as cracks, rust, etc.) on the safety of the plug-in sound barrier structure. For example, larger cracks may cause a decrease in the strength of the sound barrier structure, seriously threatening the structural safety; while minor coating peeling may have a relatively small impact on the structural safety. Consider the development trend of the image abnormal state. If the abnormal state is in a rapid development stage, such as cracks continuously expanding and the rust area rapidly increasing, its priority should be higher; while the abnormal state with slow development or tending to be stable has a relatively lower priority. Evaluate the controllability of the environmental abnormal state (such as traffic vibration, harsh climate, etc.). If the environmental factors can be easily improved through certain measures (such as adjusting traffic flow, strengthening protective measures, etc.), its priority is relatively lower; while the abnormal state caused by uncontrollable environmental factors has a higher priority. According to the above evaluation indicators, quantitatively score the image abnormal state and the environmental abnormal state. For example, set different weights and scoring criteria for each indicator, and calculate the total scores of the image abnormal state and the environmental abnormal state. Compare the total scores of the two states, and the state with the higher score has a higher priority. If the total score of the image abnormal state is higher than the total score of the environmental abnormal state, it is determined that the priority of the image abnormal state is higher than the priority of the environmental abnormal state.For example, for the abnormal image state, the crack value is large and in a rapid development stage, which has a high impact on structural safety, and the evaluation score is 80 points. For the abnormal environment state, the traffic vibration value exceeds the standard but can be improved by adjusting the traffic flow, and the environmental factors are highly controllable, and the evaluation score is 60 points. Since 80 points>60 points, the priority of determining the abnormal image state is higher than the priority of the abnormal environment state. When the priority of determining the abnormal image state is higher than the priority of the abnormal environment state, although the system determines that the first position has both image abnormality and environmental abnormality, it gives priority to processing the image abnormality. Select a second processing solution for the image abnormality from the preset processing solution library. Encapsulate the selected second processing solution in a format that the intelligent robot can recognize, such as JSON format. The solution contains detailed information such as processing steps, required tools and materials, and operating parameters. Send the encapsulated second processing solution to the intelligent robot through the communication interface. After receiving the second processing solution, the intelligent robot parses the solution and extracts key information such as processing steps, required tools and materials, and operating parameters. According to the parsed solution, the intelligent robot plans specific processing tasks, including moving paths, operation sequences, etc. For example, if the plan requires crack repair, the robot needs to plan tasks such as moving to the crack location and preparing grouting equipment and materials. The intelligent robot uses its own tools and materials to process the image anomaly at the first location in accordance with the planned task sequence. During the processing, the robot collects processing data (such as grouting pressure, processing time, etc.) in real time and feeds the data back to the server. After the processing is completed, the intelligent robot collects processing result data, such as the width of the crack after repair and the area after rust treatment. The processing result data is sent to the server through the communication interface. After receiving the processing result data, it is compared with the preset processing effect standard to evaluate whether the processing result meets the expectations. If the processing result meets the requirements, the image anomaly at the location is marked as processed; if the processing result is not ideal, the server readjusts the processing plan and sends it to the intelligent robot for processing again.

[0063] The present application also provides a device for detecting abnormalities in the main steel structure of an insertable sound barrier. Figure 2 This is a schematic diagram of a main steel structure abnormality detection device for an insertable sound barrier provided in an embodiment of the present application, with reference to Figure 2 The device includes a receiving unit 201, a processing unit 202 and a sending unit 203.

[0064] The receiving unit 201 receives a detection request sent by a target user, where the detection request is used to perform abnormality detection on a steel structure in an area to be detected, where the area to be detected is an area corresponding to the inserted sound barrier.

[0065] The processing unit 202 determines an inspection route according to the position corresponding to the area to be detected, and sends the inspection route to the intelligent robot so that the intelligent robot moves according to the inspection route; after determining that the intelligent robot arrives at the first position, it receives the image data captured by the intelligent robot; processes the image data to obtain first monitoring data, and the first monitoring data includes crack values, rust area values, coating peeling values, and bolt hole alignment deviation values; determines whether the first monitoring data is consistent with the preset first monitoring data; when the first monitoring data is inconsistent with the preset first monitoring data, it determines that the first position is in an abnormal image state, and determines the cause of the failure according to the abnormal image state.

[0066] The sending unit 203 selects a first processing solution according to the cause of the failure and sends the first processing solution to the target user so that the target user processes the first position according to the first processing solution.

[0067] In a possible implementation manner, the receiving unit 201 is configured to receive second monitoring data sent by the intelligent robot when the first monitoring data is consistent with the preset first monitoring data. The second monitoring data is data obtained by monitoring the first position with a target sensor, and the second monitoring data includes traffic vibration values, resonance frequency values, temperature, humidity, and wind speed values; the processing unit 202 is configured to determine whether the second monitoring data is less than the preset second monitoring data; the sending unit 203 is configured to determine that the first position is in an abnormal environment state when the second monitoring data is greater than or equal to the preset second monitoring data, determine a second processing solution according to the abnormal environment state, and send the second processing solution to the target user.

[0068] In a possible implementation manner, the processing unit 202 is configured to determine that the first position is in an abnormal image state and an abnormal environment state when the first monitoring data is inconsistent with the preset first monitoring data and the second monitoring data is greater than or equal to the preset second monitoring data; determine whether the priority of the abnormal image state is higher than the priority of the abnormal environment state; the sending unit 203 is configured to determine that the second processing solution is preferentially sent to the intelligent robot when the priority of the abnormal image state is higher than the priority of the abnormal environment state so that the intelligent robot processes the first position according to the second processing solution.

[0069] In a possible implementation manner, the processing unit 202 is configured to identify the image data to obtain a monitoring area, and the monitoring area includes a sound barrier surface area, a column structure area, a connecting member area, and a sound barrier board area; retrieve historical image data corresponding to the first position from a preset database according to the monitoring area; process the image data and the historical image data to obtain deviation data, and output the deviation data as the first monitoring data.

[0070] In a possible implementation manner, the receiving unit 201 is configured to obtain a plurality of detection points corresponding to the area to be detected, and obtain a plurality of second positions corresponding to the plurality of detection points, where one second position corresponds to one detection point; obtain a plurality of target heights, where the target height is the height between the second position and the ground, and one second position corresponds to one target height; the processing unit 202 is configured to sort the plurality of second positions in ascending order according to the target height to obtain an initial planned sorting position; the receiving unit 201 is configured to obtain the initial position corresponding to the intelligent robot currently; the processing unit 202 is configured to input the initial position and the initial planned sorting position into a preset path database for processing to obtain an inspection route.

[0071] In a possible implementation manner, the receiving unit 201 is configured to obtain a target image corresponding to the area to be detected; the processing unit 202 is configured to identify the target image to obtain the sound board material, where the sound board material includes a metal sound absorption board material, a transparent sound absorption board material, and a polycarbonate board material; determine monitoring parameters according to the sound board material, where the monitoring parameters include a first monitoring parameter, a second monitoring parameter, and a third monitoring parameter, the first monitoring parameter includes a structural load-bearing parameter, a deformation parameter, an anti-rust parameter, and a sound absorption layer parameter, the second monitoring parameter includes a wind resistance stability parameter, a surface aging parameter, a surface crack parameter, and a vibration frequency parameter, the third monitoring parameter includes a temperature stress parameter, a corrosion parameter, and an impact resistance parameter; determine the position corresponding to the area to be detected based on the monitoring parameters.

[0072] In a possible implementation manner, the receiving unit 201 is configured to obtain a target duration corresponding to the first position, where the target duration is the duration when the first position is in an image abnormal state; the processing unit 202 is configured to determine whether the target duration is less than or equal to a preset duration; when the target duration is less than or equal to the preset duration, determine that the image abnormal state corresponds to a low risk, and generate a first processing plan according to the low risk and the cause of the fault; when the target duration is greater than the preset duration, determine that the image abnormal state corresponds to a high risk, and generate a first processing plan according to the high risk and the cause of the fault.

[0073] It should be noted that: when the device provided in the above embodiments realizes its functions, only the above-mentioned division of each functional module is used for illustration. In actual applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be seen in the method embodiments, which will not be repeated here.

[0074] This application also discloses an electronic device. Refer to Figure 3 , Figure 3This embodiment of the present application provides a schematic structural diagram of an electronic device. The electronic device 300 may include: at least one processor 301, at least one network interface 304, a user interface 303, a memory 302, and at least one communication bus 305.

[0075] Among them, the communication bus 305 is used to realize the connection and communication between these components.

[0076] Among them, the user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may further include a standard wired interface and a wireless interface.

[0077] Among them, the network interface 304 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).

[0078] Among them, the processor 301 may include one or more processing cores. The processor 301 connects various parts within the entire server through various interfaces and lines. By running or executing instructions, programs, code sets, or instruction sets stored in the memory 302, and by calling the data stored in the memory 302, the processor 301 executes various functions of the server and processes data. Optionally, the processor 301 may be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). The processor 301 may integrate a combination of one or more of a central processing unit (CPU), a graphics processing unit (GPU), and a modem, etc. Among them, the CPU mainly processes operating systems, user interfaces, and application requests, etc.; the GPU is responsible for the rendering and drawing of the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301 and may be implemented separately by a single chip.

[0079] Among them, the memory 302 may include a Random Access Memory (RAM), or may also include a Read-Only Memory. Optionally, the memory 302 includes a non-transitory computer-readable storage medium. The memory 302 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 302 may include a program storage area and a data storage area. Among them, the program storage area can store instructions for implementing the operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-mentioned method embodiments, etc.; the data storage area can store the data involved in the above-mentioned method embodiments. Optionally, the memory 302 may also be at least one storage device located far from the aforementioned processor 301.

[0080] As Figure 3 shown, in the memory 302 as a computer storage medium, it may include an operating system, a network communication module, a user interface module, and an application program for detecting abnormalities in the main steel structure of the plug-in sound barrier.

[0081] In Figure 3 the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user to obtain the data input by the user; and the processor 301 can be used to call the application program stored in the memory 302 for detecting abnormalities in the main steel structure of the plug-in sound barrier. When executed by one or more processors, the electronic device is caused to execute the method as described in one or more of the above embodiments.

[0082] It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that this application is not limited by the described action sequence, because according to this application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0083] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0084] In several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling, direct coupling, or communication connection between each other can be through some service interfaces. The indirect coupling or communication connection of the device or unit can be in an electrical or other form.

[0085] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0086] In addition, in each embodiment of the present application, each functional unit can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0087] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present application. The aforementioned memory includes various media such as USB flash drives, mobile hard disks, magnetic disks, or optical discs that can store program codes.

[0088] The above are only exemplary embodiments of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, all equivalent changes and modifications made in accordance with the teachings of the present disclosure still fall within the scope covered by the present disclosure. Those skilled in the art will easily think of other implementation schemes of the present disclosure after considering the specification and the disclosure of the practical truth. The present application aims to cover any variations, uses, or adaptive changes of the present disclosure, and these variations, uses, or adaptive changes follow the general principles of the present disclosure and include the common general knowledge or conventional technical means in the technical field not recorded in the present disclosure.

Claims

1. A method for detecting abnormalities in the main steel structure of an insertable sound barrier, characterized in that: The method comprises: Receive a detection request sent by a target user, where the detection request is used to perform abnormality detection on a steel structure in a detection area, where the detection area is an area corresponding to the inserted sound barrier; Determine an inspection route according to the position corresponding to the area to be inspected, and send the inspection route to the intelligent robot so that the intelligent robot moves according to the inspection route; After determining that the intelligent robot has arrived at the first position, receiving image data captured by the intelligent robot; Processing the image data to obtain first monitoring data, wherein the first monitoring data includes a crack value, a rust area value, a coating shedding value, and a bolt hole alignment deviation value; Determining whether the first monitoring data is consistent with the preset first monitoring data; When the first monitoring data is inconsistent with the preset first monitoring data, determining that the first position is in an image abnormality state, and determining a fault cause according to the image abnormality state; A first processing solution is selected according to the fault cause, and the first processing solution is sent to the target user so that the target user processes the first position according to the first processing solution.

2. The method according to claim 1, characterized in that After determining whether the first monitoring data is consistent with the preset first monitoring data, the method further includes: When the first monitoring data is consistent with the preset first monitoring data, receiving second monitoring data sent by the intelligent robot, the second monitoring data is data obtained by monitoring the first position with the aid of a target sensor, and the second monitoring data includes traffic vibration value, resonance frequency value, temperature, humidity and wind speed value; Determining whether the second monitoring data is less than a preset second monitoring data; When the second monitoring data is greater than or equal to the preset second monitoring data, it is determined that the first location is in an abnormal environmental state, a second processing solution is determined according to the abnormal environmental state, and the second processing solution is sent to the target user.

3. The method according to claim 2, characterized in that The method further comprises: When the first monitoring data is inconsistent with the preset first monitoring data, and the second monitoring data is greater than or equal to the preset second monitoring data, determining that the first position is in the image abnormal state and the environment abnormal state; Determining whether the priority of the image abnormal state is higher than the priority of the environment abnormal state; When the priority of the abnormal image state is higher than the priority of the abnormal environment state, it is determined to preferentially send the second processing solution to the intelligent robot so that the intelligent robot processes the first position according to the second processing solution.

4. The method according to claim 1, characterized in that: The processing of the image data to obtain the first monitoring data specifically includes: Identify the image data to obtain a monitoring area, wherein the monitoring area includes a sound barrier surface area, a column structure area, a connector area, and a sound barrier board area; Retrieving historical image data corresponding to the first position from a preset database according to the monitoring area; The image data and the historical image data are processed to obtain deviation data, and the deviation data is output as the first monitoring data.

5. The method according to claim 1, characterized in that The step of determining the inspection route according to the position corresponding to the area to be inspected specifically includes: Acquire a plurality of detection points corresponding to the area to be detected, and acquire a plurality of second positions corresponding to the plurality of detection points, wherein one second position corresponds to one detection point; Acquire multiple target heights, where the target height is the distance between the second position and the ground, and one second position corresponds to one target height; Sort the plurality of second positions from small to large according to the target height to obtain an initial planned sorted position; Obtaining the current initial position of the intelligent robot; The initial position and the initial planned sorting position are input into a preset path database for processing to obtain the inspection route.

6. The method according to claim 1, characterized in that Before determining the inspection route according to the position corresponding to the area to be inspected, the method further includes: Acquire a target image corresponding to the area to be detected; Identify the target image to obtain a sound board material, wherein the sound board material includes a metal sound absorbing board material, a transparent sound absorbing board material, and a polycarbonate board material; Determine monitoring parameters according to the material of the sound board, the monitoring parameters include a first monitoring parameter, a second monitoring parameter and a third monitoring parameter, the first monitoring parameter includes a structural load-bearing parameter, a deformation parameter, an anti-rust parameter and a sound-absorbing layer parameter, the second monitoring parameter includes a wind resistance stability parameter, a surface aging parameter, a surface crack parameter and a vibration frequency parameter, and the third monitoring parameter includes a temperature stress parameter, a corrosion parameter and an impact resistance parameter; A position corresponding to the area to be detected is determined based on the monitoring parameters.

7. The method according to claim 1, characterized in that The selecting a first processing solution according to the fault cause specifically includes: Acquire a target duration corresponding to the first position, where the target duration is a duration corresponding to when the first position is in the image abnormal state; Determine whether the target duration is less than or equal to a preset duration; When the target duration is less than or equal to the preset duration, determining that the image abnormal state corresponds to a low risk, and generating the first processing solution according to the low risk and the fault cause; When the target duration is greater than the preset duration, it is determined that the abnormal image state corresponds to a high risk, and the first processing solution is generated according to the high risk and the cause of the fault.

8. A device for detecting abnormalities in the main steel structure of an insertable sound barrier, characterized in that: The device comprises a receiving unit (201), a processing unit (202) and a sending unit (203); The receiving unit (201) receives a detection request sent by a target user, wherein the detection request is used to perform abnormality detection on a steel structure in a detection area, wherein the detection area is an area corresponding to the inserted sound barrier; The processing unit (202) determines an inspection route according to the position corresponding to the area to be inspected, and sends the inspection route to the intelligent robot so that the intelligent robot moves according to the inspection route; After determining that the intelligent robot has arrived at the first position, receiving image data taken by the intelligent robot; processing the image data to obtain first monitoring data, the first monitoring data including a crack value, a rust area value, a coating shedding value, and a bolt hole alignment deviation value; judging whether the first monitoring data is consistent with the preset first monitoring data; when the first monitoring data is inconsistent with the preset first monitoring data, determining that the first position is in an image abnormality state, and determining the cause of the fault according to the image abnormality state; The sending unit (203) selects a first processing solution according to the fault cause, and sends the first processing solution to the target user, so that the target user processes the first position according to the first processing solution.

9. An electronic device, characterized in that: The electronic device (300) comprises a processor (301), a memory (302), a user interface (303) and a network interface (304), wherein the memory (302) is used to store instructions, the user interface (303) and the network interface (304) are used to communicate with other devices, and the processor (301) is used to execute the instructions stored in the memory (302) so that the electronic device (300) executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 7 is executed.

Images