Construction quality supervision method and system, medium and product

Abstract

The invention discloses a construction quality supervision method and system, a medium and a product, and relates to the field of quality management. The method comprises the following steps: acquiring real-time hydrological data of the underwater quality inspection robot in a preset area; determining the moving speed and the moving direction of the underwater quality inspection robot; controlling the underwater quality inspection robot to move according to the moving speed and the moving direction; when the real-time position of the underwater quality inspection robot is consistent with a target acquisition position in a preset moving path, acquiring surface image data of a target detection object; when it is detected that a covering exists on the surface of the target detection object and the covering can be removed by the underwater quality inspection robot, determining a removal scheme of the covering; controlling the underwater quality inspection robot to execute the removal scheme; when it is detected that the underwater quality inspection robot executes the removal scheme, target quality inspection data and target quality inspection image data of the target acquisition position are acquired; and determining a quality inspection result of the target acquisition position. By implementing the technical scheme, the accuracy of quality inspection results of quality inspection in water is improved.

Description

Technical Field

[0001] The present application relates to the field of quality management, and in particular to a construction quality supervision method, system, medium and product. Background Art

[0002] Dams are crucial infrastructure in water conservancy projects, and their construction quality plays a crucial role in achieving functions such as flood control, irrigation, and power generation. Dam construction involves multiple complex steps and a large amount of construction materials. Quality issues at any stage can have serious consequences. Therefore, efficient and accurate construction quality supervision is crucial to ensuring the smooth construction and long-term stable operation of dam projects.

[0003] Currently, commonly used methods for inspecting dam construction quality include traditional manual inspection and automated inspection technology. Automated inspection technology uses sensors, drones, remote sensing equipment, and other testing equipment to monitor the dam's structural status, material properties, and construction environment in real time.

[0004] However, when conducting quality inspections on underwater dam construction, the complex underwater environment often results in various aquatic organisms, sediment, algae, and other debris clinging to the surfaces of the inspection objects. These debris can interfere with the proper functioning of the inspection equipment, leading to inaccurate data collection and impacting the accuracy of underwater inspection results. Summary of the Invention

[0005] The present application provides a construction quality supervision method, system, medium and product, which can improve the accuracy of quality inspection results conducted in water.

[0006] In the first aspect, the present application provides a construction quality supervision method, which includes: obtaining real-time hydrological data within a preset area of an underwater quality inspection robot, the real-time hydrological data including water flow velocity, water flow direction and turbidity; determining the moving speed and moving direction of the underwater quality inspection robot according to the real-time hydrological data, the preset moving path of the underwater quality inspection robot and the real-time position of the underwater quality inspection robot, the preset moving path including one or more acquisition positions; controlling the underwater quality inspection robot to move according to the moving speed and the moving direction; when the real-time position of the underwater quality inspection robot is consistent with the target acquisition position in the preset moving path, collecting surface image data of the target detection object corresponding to the target acquisition position by the underwater quality inspection robot, the target acquisition position The position is one of all the acquisition positions in the preset moving path; when it is detected that there is a cover on the surface of the target detection object in the surface image data, and the cover can be removed by the underwater quality inspection robot, the removal plan of the cover is determined according to the type and coverage range of the cover, and the removal plan includes removal by a water spray device and removal by a robotic arm; the underwater quality inspection robot is controlled to execute the removal plan; when it is detected that the underwater quality inspection robot has completed the execution of the removal plan, the target quality inspection data and target quality inspection image data corresponding to the target acquisition position are collected by the underwater quality inspection robot, and there is no cover on the surface of the target detection object in the target quality inspection image data; according to the target quality inspection data and target quality inspection image data, the quality inspection result of the target acquisition position is determined.

[0007] By adopting the above technical solution, the movement speed and direction of the underwater quality inspection robot are dynamically adjusted according to real-time hydrological data, ensuring that the robot can accurately reach each collection location, avoiding detection position deviation caused by interference from factors such as water flow, and improving the reliability of data collection. When it is detected that there is a covering on the surface of the inspection object, and the covering can be removed by the underwater quality inspection robot, the underwater quality inspection robot removes the covering on the surface of the inspection object, and then collects the quality inspection data and quality inspection image data of the inspection object. Based on the quality inspection data and the quality inspection image data, the inspection object is quality inspected and the quality inspection results are generated. This avoids the misjudgment of the quality inspection results due to the influence of the covering, and improves the accuracy of the quality inspection results of the quality inspection conducted in water. At the same time, the fully automatic underwater quality inspection method optimizes the quality inspection process, improves the quality inspection efficiency, reduces the cost of manual intervention, and enhances the intelligence and automation level of underwater quality inspection operations.

[0008] In combination with some embodiments of the first aspect, in some embodiments, when it is detected that there is a cover on the surface of the target detection object in the surface image data and the cover can be removed by the underwater quality inspection robot, a plan for removing the cover is determined according to the type and coverage of the cover, specifically including: when it is detected that there is a cover on the surface of the target detection object in the surface image data and the cover can be removed by the underwater quality inspection robot, according to the surface image data, identifying the shape and coverage of the cover; according to the shape and the coverage, determining one or more cover collection positions; controlling the underwater quality inspection robot to move to the cover collection position to collect image data around the cover; according to the image data around the cover, identifying the distance between the cover and the surface of the detection object; and determining a plan for removing the cover according to the distance and the type of the cover.

[0009] Using the above technical solution, after detecting a covering, the shape and coverage of the covering are first identified, providing a basis for subsequent removal operations, helping to more rationally plan the removal plan and avoid unnecessary damage to the target inspection object. By determining the location of the covering collection, the underwater quality inspection robot is guided to obtain image data around the covering, and then accurately identify the distance between the covering and the surface of the inspection object. Based on the actual spatial relationship between the covering and the inspection object and the covering type, the most suitable removal plan can be formulated, improving the compatibility of the removal plan with the covering and ensuring that the covering is removed thoroughly and efficiently.

[0010] In combination with some embodiments of the first aspect, in some embodiments, after the step of determining the quality inspection result of the target acquisition position based on the target quality inspection data and the target quality inspection image data, the method further includes: calculating the quality inspection credibility of the quality inspection result based on the turbidity of the target acquisition position and the image clarity of the target quality inspection image data; when the quality inspection credibility is lower than the preset credibility threshold, determining multiple new acquisition positions based on the image acquisition range of the underwater quality inspection robot and the preset image acquisition area of the target detection object, and the distance between the new acquisition position and the target detection object is less than the distance between the target acquisition position and the target detection object; collecting new quality inspection data and new quality inspection image data of the new acquisition position by the underwater quality inspection robot; and updating the quality inspection result based on the new quality inspection data and the new quality inspection image data.

[0011] The above technical solution calculates the quality inspection confidence level of the inspection results by comprehensively considering the turbidity at the target acquisition location and the image clarity of the target quality inspection image data, providing a quantitative basis for evaluating the quality of the inspection data. When the quality inspection confidence level falls below a preset threshold, multiple additional acquisition locations are precisely determined based on the underwater inspection robot's image acquisition range and the preset image acquisition area of the target inspection object. These additional acquisition locations are closer to the target inspection object, reducing the impact of environmental factors (such as turbidity) on image acquisition and data acquisition. This results in clearer and more accurate collected additional quality inspection data and additional quality inspection image data, thereby improving the accuracy of quality inspection results for underwater inspections.

[0012] In combination with some embodiments of the first aspect, in some embodiments, after the step of determining the quality inspection result of the target acquisition position based on the target quality inspection data and the target quality inspection image data, the method further includes: when the real-time position of the underwater quality inspection robot is consistent with the end position in the preset moving path, the quality inspection pass rate of the construction project corresponding to the preset moving path is calculated according to the quality inspection results of each acquisition position in the preset moving path; when the quality inspection pass rate is less than the preset threshold, the reason for the failure of the construction project is determined according to the abnormal quality inspection data and abnormal quality inspection image data corresponding to the unqualified acquisition position, the unqualified acquisition position is a acquisition position where the quality inspection result is unqualified, and the reason for the failure includes construction problems and design problems.

[0013] Using this technical solution, when the underwater quality inspection robot completes quality inspections at all collection locations along its preset movement path, it can intuitively assess the quality level of the entire construction project by calculating the quality inspection pass rate. When the quality inspection pass rate falls below a preset threshold, it indicates serious quality issues with the construction project. The cause of the failure can be determined based on the abnormal quality inspection data and image data corresponding to the unqualified collection locations. Construction parties can then make targeted improvements to the problems encountered during the construction process based on the reasons for the failure, such as adjusting construction techniques, replacing construction materials, or strengthening construction personnel training. Designers can also optimize the original design plan and improve design details based on feedback from design issues, thereby avoiding similar quality issues in subsequent construction. This approach not only effectively improves the quality of construction projects, but also reduces resource waste, lowers project costs, and improves the overall efficiency of construction projects.

[0014] In combination with some embodiments of the first aspect, in some embodiments, when the quality inspection pass rate is less than a preset threshold, after the step of determining the cause of failure of the construction project based on the abnormal quality inspection data and abnormal quality inspection image data corresponding to the unqualified collection position, the method further includes: determining the rework area and rework project based on the abnormal quality inspection data, abnormal quality inspection image data and the construction project corresponding to the unqualified collection position; when the construction machine corresponding to the rework project has a fault, determining the predicted rework time of the rework project based on the fault condition and the cause of failure of the construction machine; and adjusting the construction time of the remaining construction projects in the preset construction plan based on the predicted rework time.

[0015] Using the above technical solution, after determining the cause of a construction project's failure, the rework area and rework items can be accurately determined based on the abnormal quality inspection data and image data corresponding to the failed collection location, as well as the specific circumstances of the construction project. This clarifies the specific scope and content of the required rectification, making rework more targeted, avoiding blind rework, and improving rework efficiency. When the construction machine corresponding to the rework project malfunctions, the predicted rework duration is determined based on the machine's malfunction and the cause of the failure. This comprehensively considers the impact of equipment failure and quality issues on rework time, making the predicted rework duration more scientific and reasonable, and providing a reliable time reference for subsequent construction arrangements. Adjusting the construction time of the remaining construction items in the preset construction plan based on the predicted rework duration allows for timely and dynamic adjustments to the entire construction plan, rationally allocating resources and time, avoiding delays caused by rework, ensuring that the construction project can proceed in an orderly manner according to the new plan, and improving the flexibility and adaptability of the construction plan.

[0016] In combination with some embodiments of the first aspect, in some embodiments, when the construction machine corresponding to the rework project has a fault, the predicted rework time of the rework project is determined according to the fault condition and the reason for the failure of the construction machine, specifically including: when the construction machine corresponding to the rework project has a fault, according to the fault condition of the construction machine and the hydrological data of the rework area, determining the degree of influence of the fault condition on the construction quality of the rework project, the influence degree including slight and severe; when the influence degree is severe, determining one or more construction substitutes according to the working information of idle construction machines, information of idle construction personnel, the rework project and the hydrological data of the rework area. replacement plan; determine the first rework time estimated to be required for rework according to the construction replacement plan based on the construction replacement plan, the rework project and the rework area; determine the second rework time of the construction machine based on the failure condition of the construction machine, the rework project, the rework area and the rework efficiency of the construction machine, the second rework time being the sum of the maintenance time of the construction machine and the rework time required for rework using the construction machine; determine the predicted rework time of the rework project based on the failure reason, the shortest first rework time, the maintenance time and the second rework time, the shortest first rework time being the shortest among all first rework times.

[0017] By adopting the above technical solution, when it is detected that the use of a faulty construction machine for construction will have a serious impact on the construction quality of the rework project, a construction replacement plan is formulated based on the idle construction machines and idle construction personnel. Even if the construction machine required by the original construction plan fails, the rework project can be carried out according to the construction replacement plan. While ensuring the construction quality, the impact of the construction machine failure on the construction progress of the rework project is reduced.

[0018] In combination with some embodiments of the first aspect, in some embodiments, the predicted rework duration of the rework project is determined based on the reason for failure, the shortest first rework duration, the maintenance duration and the second rework duration, specifically including: when the reason for failure is a construction problem, the shorter of the shortest first rework duration and the second rework duration is used as the predicted rework duration of the rework project; when the reason for failure is a design problem, the redesign duration of the rework area is determined based on the preset design schedule, the rework project and the rework area; when the redesign duration is greater than or equal to the maintenance duration, the second rework duration is used as the predicted rework duration; when the redesign duration is less than the maintenance duration, the shorter of the shortest first rework duration and the third rework duration is used as the predicted rework duration, and the third rework duration is the difference between the second rework duration and the redesign duration.

[0019] By adopting the above technical solution, the predicted rework duration of the rework project is determined based on the reason for non-conformity, the shortest first rework duration, the maintenance duration and the second rework duration, and the shortest rework duration is dynamically selected as the predicted rework duration. This enables the construction party to make decisions quickly based on a comprehensive consideration of resource utilization efficiency and time cost, give priority to rework methods that take a shorter time, minimize construction delays, and improve construction efficiency.

[0020] In the second aspect, an embodiment of the present application provides a construction quality supervision system, including an underwater quality inspection robot, a sensor and a server, the underwater quality inspection robot and the sensor are respectively communicated with the server, and the sensor is connected to the underwater quality inspection robot, wherein the server includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the construction quality supervision system to execute the method described in the first aspect and any possible implementation method of the first aspect.

[0021] In a third aspect, an embodiment of the present application provides a computer-readable storage medium comprising instructions. When the instructions are executed on a construction quality supervision system, the construction quality supervision system executes the method described in the first aspect and any possible implementation method of the first aspect.

[0022] In a fourth aspect, the present application provides a computer program product, which, when executed on a construction quality supervision system, enables the construction quality supervision system to execute the method described in the first aspect and any possible implementation of the first aspect.

[0023] It is understood that the construction quality supervision system provided in the second aspect, the storage medium provided in the third aspect, and the computer program product provided in the fourth aspect are all used to execute the method provided in this application. Therefore, the beneficial effects achievable by these methods can be referenced to the beneficial effects of the corresponding methods and will not be further elaborated here.

[0024] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages: 1. This application dynamically adjusts the movement speed and direction of the underwater quality inspection robot based on real-time hydrological data to ensure that the robot can accurately reach each collection location, avoids detection position deviations caused by interference from factors such as water flow, and improves the reliability of data collection. At the same time, when it is detected that there is a covering on the surface of the inspection object, and the covering can be removed by the underwater quality inspection robot, the underwater quality inspection robot removes the covering on the surface of the inspection object, and then collects the quality inspection data and quality inspection image data of the inspection object. Based on the quality inspection data and the quality inspection image data, the inspection object is quality inspected and quality inspection results are generated, avoiding misjudgment of the quality inspection results due to the influence of the covering, and improving the accuracy of the quality inspection results of the quality inspection conducted in water.

[0025] 2. This application calculates the quality inspection credibility of the quality inspection results by comprehensively considering the turbidity of the target acquisition location and the image clarity of the target quality inspection image data, providing a quantitative basis for evaluating the quality of the quality inspection data. When the quality inspection credibility falls below a preset threshold, multiple new acquisition locations are accurately determined based on the image acquisition range of the underwater quality inspection robot and the preset image acquisition area of the target inspection object. These new acquisition locations are closer to the target inspection object, which can reduce the impact of environmental factors (such as turbidity) on image acquisition and data acquisition, making the new quality inspection data and new quality inspection image data collected clearer and more accurate, thereby improving the accuracy of the quality inspection results of the underwater quality inspection.

[0026] 3. When it is detected that the use of faulty construction machines for construction will have a serious impact on the construction quality of the rework project, this application formulates a construction replacement plan based on idle construction machines and idle construction personnel. Even if the construction machine required by the original construction plan fails, the rework project can be carried out according to the construction replacement plan. While ensuring the construction quality, the impact of the construction machine failure on the construction progress of the rework project is reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 This is a structural diagram of a system architecture to which the construction quality supervision method in the embodiment of the present application can be applied; Figure 2 This is a flow chart of the construction quality supervision method in the embodiment of the present application; Figure 3 This is another flowchart of the construction quality supervision method in the embodiment of the present application; Figure 4 It is a schematic diagram of an exemplary hardware structure of the construction quality supervision system in the embodiment of the present application. DETAILED DESCRIPTION

[0028] The terms used in the following examples of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the specification and appended claims of this application, the singular expressions "a," "an," "said," "above," "the," and "this" are intended to include plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in this application refers to any or all possible combinations comprising one or more of the listed items.

[0029] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood to imply or suggest relative importance or implicitly indicate the number of the technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of this application, unless otherwise specified, "plurality" means two or more.

[0030] Figure 1 It is a structural diagram of a system architecture to which the construction quality supervision method in the embodiment of the present application can be applied.

[0031] See also Figure 1 ,The construction quality supervision system includes underwater quality inspection robots, ,sensors and servers.

[0032] The server, the system's core component, receives quality inspection data and image data from the underwater inspection robot, processes and analyzes the data to generate inspection results, and sends control commands to the robot. The robot receives control commands from the server and, based on these commands, performs operations such as movement, collecting and transmitting inspection data. Sensors connected to the robot collect hydrological data surrounding the robot and transmit this data to the server.

[0033] Through the above system architecture, the construction quality supervision system can collect quality inspection data and quality inspection image data of underwater construction buildings through underwater quality inspection robots, and perform automated quality inspection on underwater construction buildings based on the quality inspection data and quality inspection image data to obtain quality inspection results.

[0034] Commonly used methods for inspecting dam construction quality include traditional manual inspection and automated testing techniques. Automated testing uses sensors, drones, remote sensing equipment, and other testing equipment to monitor the dam's structural condition, material properties, and construction environment in real time. However, when inspecting underwater dam construction, the complex underwater environment often results in various aquatic organisms, sediment, algae, and other debris clinging to the surface of the inspection object. These debris can interfere with the proper functioning of the testing equipment, leading to inaccurate data collection and compromising the accuracy of underwater inspection results.

[0035] However, by adopting the construction quality supervision method in the embodiment of the present application, when it is detected that there is a covering on the surface of the inspection object and the covering can be removed by an underwater quality inspection robot, the underwater quality inspection robot removes the covering on the surface of the inspection object, and then collects quality inspection data and quality inspection image data of the inspection object. Based on the quality inspection data and the quality inspection image data, the inspection object is quality inspected and a quality inspection result is generated, which can improve the accuracy of the quality inspection results of the quality inspection performed in water.

[0036] The following combination Figure 2 To illustrate the method of the embodiment of the present application.

[0037] See also Figure 2 , which is a flow chart of the construction quality supervision method in an embodiment of the present application.

[0038] S201: Acquire real-time hydrological data within a preset area of the underwater quality inspection robot.

[0039] Real-time hydrological data around the underwater quality inspection robot is collected through sensors installed on the outside of the underwater quality inspection robot.

[0040] The real-time hydrological data includes water velocity, water direction, and turbidity. Sensors include water velocity sensors, water direction sensors, and turbidity sensors.

[0041] S202. Determine the moving speed and moving direction of the underwater quality inspection robot according to the real-time hydrological data, the preset moving path of the underwater quality inspection robot, and the real-time position of the underwater quality inspection robot.

[0042] The preset moving path includes one or more collection locations.

[0043] Specifically, the underwater inspection robot's built-in positioning device obtains its real-time location. Based on the real-time location and the path information of the preset movement path, the underwater inspection robot's preset movement direction is determined. The water flow direction and the movement direction are compared to determine whether they are consistent. The path information includes the specific location information of each collection location and the movement direction of the underwater inspection robot.

[0044] If the direction of the water flow is the same as the preset moving direction, determine whether the water flow speed is less than the preset threshold. If so, it means that the water flow has a small pushing effect on the underwater quality inspection robot and will not significantly interfere with the movement of the robot. The moving speed of the underwater quality inspection robot is determined to be the current moving speed, and the moving direction is determined to be the preset moving direction. If not, it means that the water flow has a large pushing effect on the underwater quality inspection robot, which will cause the underwater quality inspection robot to move too fast. Obtain the adjustment speed value corresponding to the water flow speed in the preset speed adjustment table. Subtract the adjustment speed value from the current moving speed to obtain the adjusted speed. If the adjusted speed is less than or equal to zero, determine that the moving speed of the underwater quality inspection robot is the preset minimum moving speed, and the moving direction is the preset moving direction; if the adjusted speed is greater than zero, determine that the moving speed of the underwater quality inspection robot is the adjusted speed, and the moving direction is the preset moving direction.

[0045] If the water flow direction is different from the preset movement direction, calculate the angle between the water flow direction and the preset movement direction. Obtain the water flow direction angle value detected by the water flow direction sensor. This angle value is the actual direction angle converted based on the direction of the force exerted by the water flow on the sensing element by the sensor's internal algorithm. Simultaneously, obtain the preset movement direction angle value for the current segment of the underwater inspection robot's preset movement path. This angle value is determined based on the specific location information of each collection location in the preset movement path and the underwater inspection robot's movement direction information. Calculate the difference between the two angle values to obtain the angle θ between the water flow direction and the preset movement direction.

[0046] The moving speed and direction of the underwater quality inspection robot are determined based on the calculated angle and water flow velocity, so that the actual moving direction of the underwater quality inspection robot when moving at this moving speed and this moving direction is the preset moving direction. First, a mathematical model is established based on the principles of fluid mechanics and kinematics. This model takes into account the force of the water flow on the underwater quality inspection robot and the robot's own power system. For example, the thrust generated by the power system of the underwater quality inspection robot is F robot , the force of water flow on the robot is F water , where F water The size of the water flow velocity v water Related, can be expressed as F water =k×v water (k is a coefficient related to the robot's shape, size, and the physical properties of water.) Then, the water flow force F is calculated based on the angle θ between the water flow direction and the preset movement direction. water The force component in the preset moving direction and perpendicular to the preset moving direction. The force component F in the preset moving direction parallel =F water × cosθ, the component force F perpendicular to the preset moving direction perpendicular=F water × sinθ. Next, based on the current robot's power system parameters and the additional power required to offset the component force perpendicular to the preset moving direction, the power value ΔF that needs to be increased or decreased is calculated. Then, based on the preset relationship between power and speed, the adjusted moving speed is calculated as the moving speed of the underwater quality inspection robot. Finally, based on the angle θ and the water flow velocity, the correction angle α is calculated according to the preset calculation method. The calculation method of the correction angle α can be based on a trigonometric function relationship. The preset moving direction angle value is added to the correction angle to obtain a new moving direction angle value, and the moving direction of the underwater quality inspection robot is determined based on the moving direction angle value.

[0047] S203: Control the underwater quality inspection robot to move according to the moving speed and moving direction.

[0048] According to the moving speed and moving direction, the corresponding control instruction is determined and sent to the underwater quality inspection robot. After receiving the control instruction, the underwater quality inspection robot moves according to the moving speed and moving direction in the control instruction.

[0049] S204: When the real-time position of the underwater quality inspection robot is consistent with the target acquisition position in the preset moving path, the underwater quality inspection robot collects surface image data of the target inspection object corresponding to the target acquisition position.

[0050] The target collection position is one of all collection positions in the preset moving path.

[0051] Specifically, the real-time position of the underwater quality inspection robot is obtained, and the real-time position is compared with the target collection position in the preset movement path to determine whether the real-time position of the underwater quality inspection robot is consistent with the target collection position.

[0052] When the real-time position of the underwater quality inspection robot is consistent with the target acquisition position in the preset moving path, the surface image data of the target inspection object corresponding to the target acquisition position is obtained by shooting with the built-in camera of the underwater quality inspection robot.

[0053] When the real-time position of the underwater quality inspection robot is consistent with the target collection position in the preset moving path, the real-time position is continued to be compared with the target collection position in the preset moving path.

[0054] S205: When it is detected that there is a covering on the surface of the target detection object in the surface image data, and the covering can be removed by the underwater quality inspection robot, a covering removal plan is determined according to the type and coverage of the covering.

[0055] Among them, removal solutions include water spray device removal, robotic arm removal, etc.

[0056] Specifically, the surface image data collected by the underwater quality inspection robot is analyzed and processed to determine whether there is any covering on the surface of the target object. First, an image recognition algorithm is used to identify the surface image data of the target object to detect any covering on the surface. This image recognition algorithm can employ deep learning-based object detection algorithms, such as the YOLO (You Only Look Once) series of algorithms and Faster R-CNN. By training the algorithm with a large amount of image data labeled with coverings, the algorithm can accurately identify different types of coverings. The surface image data is input into the algorithm, which extracts and analyzes features. If an object matching the covering characteristics is identified, the presence of covering is determined. The algorithm also compares the extracted features with pre-stored covering features to determine the specific type of covering. If no covering is identified, the absence of covering is determined.

[0057] When the presence of a covering object on the surface of the target object is detected, the size, shape, position, and degree of adhesion of the covering object to the surface of the target object are determined.

[0058] To determine the size of the covered object, image segmentation techniques, such as semantic segmentation or instance segmentation, are used to separate the covered object from the background of the target object. Semantic segmentation, for example, classifies each pixel in the image and labels those belonging to the covered object. By statistically analyzing these pixels, the area of the covered object is calculated, thereby determining its size.

[0059] For shape detection, edge detection algorithms, such as the Canny edge detection algorithm, are used to extract the edge contours of the covering. Shape features are then described for this edge contour, such as calculating contour perimeter, circularity, aspect ratio, and other characteristic parameters. Based on these parameters, the approximate shape of the covering, such as circle, ellipse, or irregular shape, is determined.

[0060] Regarding position, the image coordinate system is used to determine the position of the covering on the target object's surface. Since the images captured by the underwater inspection robot contain certain coordinate information, after detecting the covering using an image recognition algorithm, the covering's coordinate range in the image, such as the coordinate values of the upper left and lower right corners, can be obtained. Combining the target object's position information in the image with the underwater inspection robot's position and posture information (obtained through the robot's positioning device and posture sensor), the covering's coordinates in the image are converted into relative position information on the target object's actual surface, thereby determining the covering's actual position range.

[0061] The tightness of adhesion can be determined by analyzing the features of the transition area between the edge of the covering and the surface of the target object. Image recognition technology is used to extract the texture features and color information of the area where the covering and the target surface meet. Texture features are analyzed, and texture similarity and continuity parameters are calculated using a texture analysis algorithm. If the parameters show high texture similarity and continuity, the two textures are well integrated; otherwise, the integration is poor. A quantitative analysis of color information is performed, comparing the color difference between the covering and the target surface. If the difference is within a small, pre-set range, the color transition is natural; if the difference is outside the range, the color transition is unnatural. Based on the combined texture and color analysis results, if the texture integration is good and the color transition is natural, the adhesion is considered tight; if the texture integration is poor and the color difference is significant, the adhesion is considered loose.

[0062] In some embodiments, the degree of adhesion can be determined using auxiliary information from the underwater inspection robot. For example, the force feedback from the force sensor on the robot's robotic arm, when attempting to lightly touch the covering (by controlling the robot's robotic arm to perform a light touch operation), can be used. A smaller feedback force indicates a weak adhesion between the covering and the target surface; a larger feedback force indicates a strong adhesion. The degree of adhesion can also be determined by combining information about the covering type (determined in the previous image recognition process). Different covering types typically have different adhesion characteristics.

[0063] The robot then determines whether the covering can be removed based on its characteristics. Regarding the size of the covering, if the area exceeds the effective coverage of the robot's water jets and the reach of its robotic arm (performance parameters such as the effective coverage of the robot's water jets and the reach of its robotic arm are pre-stored in the system), the robot determines that the covering cannot be removed. If the area is within the effective coverage of the water jets or the reach of the robotic arm, the robot proceeds to the next step.

[0064] Regarding the shape of the covering, if it is irregular and has sharp edges, it may cause damage to the robotic arm or water spray device of the underwater quality inspection robot (for example, sharp edges may scratch the protective layer of the robotic arm or block the nozzle of the water spray device). If the system determines based on pre-stored rules that the shape cannot be safely removed through existing operations, it will be determined that it cannot be removed; if the shape is relatively conventional, such as circular, elliptical, etc., and is within the processing range of the robotic arm and the water spray device, the next step of judgment will be entered.

[0065] Regarding the position of the covering, if the covering is located at some special positions on the surface of the target inspection object, such as positions that the underwater quality inspection robot's robotic arm cannot reach due to its own structural limitations (these position information can be determined by the underwater quality inspection robot's positioning device and the motion range parameters of the robotic arm), or positions where the water flow of the water spraying device cannot be effectively sprayed (which can be determined based on the spraying angle and direction parameters of the water spraying device), then it is determined that the covering cannot be removed; if the covering is located at a position that can be reached by the robotic arm and sprayed by the water spraying device, then the next step of judgment is entered.

[0066] Regarding the degree of adhesion, if the degree of adhesion is high, and according to the pre-stored rules, the robotic arm of the underwater quality inspection robot cannot provide sufficient force to remove the covering, or the water flow impact force of the water spray device is not enough to wash away the covering (parameters such as the maximum force of the robotic arm and the maximum water flow impact force of the water spray device have been pre-stored in the system), then it is judged that the covering cannot be removed; if the degree of adhesion is low, the robotic arm and the water spray device are capable of removing the covering, then it is judged that the covering can be removed by the underwater quality inspection robot.

[0067] If it's determined that the covering can be removed by the underwater inspection robot, a removal plan is determined based on the covering's characteristics. If the covering is loosely adhered, small in area, and relatively regular in shape, the electronics will use a water jet to remove it. By controlling the direction and size of the water flow, the electronics will use the appropriate force to flush the covering away. If the covering is tightly adhered or irregular in shape, the electronics will use a robotic arm to remove it. Based on the location and shape of the covering, the robotic arm's movement path is planned and controlled to grab or remove the covering.

[0068] S206: Control the underwater quality inspection robot to execute the removal plan.

[0069] According to the removal plan, a corresponding control instruction is determined and sent to the underwater quality inspection robot. After receiving the control instruction, the underwater quality inspection robot removes the covering on the surface of the target inspection object according to the control instruction.

[0070] S207: When it is detected that the underwater quality inspection robot has completed executing the removal plan, the underwater quality inspection robot collects target quality inspection data and target quality inspection image data corresponding to the target collection position.

[0071] There is no covering on the surface of the target inspection object in the target quality inspection image data.

[0072] Specifically, the trained image recognition algorithm is used to identify the re-collected surface image data of the target inspection object. If no covering object is identified, it is determined that the underwater quality inspection robot has completed the removal plan.

[0073] When the underwater quality inspection robot detects that it has completed the removal plan, the target quality inspection data corresponding to the target collection position is collected through the built-in sensor of the underwater quality inspection robot. The acoustic sensor uses the principle of acoustics to detect whether there are defects inside the target inspection object. By emitting ultrasonic waves and receiving reflected waves, the internal condition is judged based on the characteristics of the reflected waves. The electronic equipment receives and processes the analysis data. The electrochemical sensor is used to detect the chemical properties and corrosion conditions of the surface of the target inspection object. The degree of corrosion is determined by measuring parameters such as potential and current. The electronic equipment collects and analyzes the data to understand the surface chemical state. The pressure sensor detects the pressure distribution on the surface of the target inspection object. The water pressure is different at different locations underwater. The sensor collects data in real time, and the electronic equipment processes the data to determine whether the pressure is uniform and whether there are any abnormal areas, thereby discovering potential structural problems.

[0074] At the same time, the underwater inspection robot's built-in camera collects image data from the target collection location. To ensure image quality and comprehensiveness, the robot automatically adjusts its position and posture based on the shape and structure of the target object, capturing images from multiple angles to avoid blind spots and fully reflect the target's surface condition. Due to the dim and uneven lighting conditions underwater, the robot is equipped with lighting equipment that automatically compensates for the effects of light during image capture, adjusting brightness and angle based on the ambient light intensity and distribution to ensure clear, bright images that accurately reflect surface details.

[0075] S208: Determine the quality inspection result of the target acquisition position according to the target quality inspection data and the target quality inspection image data.

[0076] Specifically, for the data collected by the acoustic sensor, if the reflected wave characteristics show abnormal reflected signals or abnormal signal attenuation, it means that there may be defects inside the target inspection object. The type, location and severity of the defect can be further determined based on parameters such as the intensity and frequency of the reflected wave.

[0077] For the data collected by the electrochemical sensor, the measured potential, current and other parameters are compared with the preset standard values. If the parameters deviate from the standard value range, it is determined that corrosion exists on the surface of the target detection object, and the severity of the corrosion is determined based on the degree of deviation.

[0078] For the data collected by the pressure sensor, the pressure values at various locations on the surface of the target object are analyzed and the uniformity of the pressure distribution is calculated. If the uniformity is lower than the preset threshold, it is determined that there is uneven pressure distribution on the surface of the target object, and the location and range of the abnormal pressure area are determined.

[0079] For target quality inspection image data, image enhancement algorithms are used to process the collected images to improve image contrast and clarity, making the surface details of the target inspection object more obvious. Then, image recognition algorithms are used to identify surface features in the images, such as the presence of surface defects such as cracks, holes, and wear. The impact of defects on the performance and safety of the target inspection object is assessed based on their size, shape, and number.

[0080] Finally, the above results are combined to determine the quality inspection result of the target acquisition location. If the target object has internal defects, surface corrosion, uneven pressure distribution, or obvious surface defect characteristics, the quality inspection result of the target acquisition location is judged to be unqualified. If the target object has no internal defects, no surface corrosion or low corrosion severity, uniform pressure distribution, and no obvious surface defect characteristics, the quality inspection result of the target acquisition location is judged to be qualified.

[0081] In the embodiments of the present application, the movement speed and direction of the underwater quality inspection robot are dynamically adjusted based on real-time hydrological data to ensure that the robot can accurately reach each collection location, avoid detection position deviations caused by interference from factors such as water flow, and improve the reliability of data collection. When it is detected that there is a covering on the surface of the inspection object and the covering can be removed by the underwater quality inspection robot, the underwater quality inspection robot removes the covering on the surface of the inspection object and then collects quality inspection data and quality inspection image data of the inspection object. Based on the quality inspection data and the quality inspection image data, the inspection object is quality inspected and quality inspection results are generated, thereby improving the accuracy of the quality inspection results of the underwater inspection.

[0082] The following combination Figure 3 To further illustrate the method of the embodiment of the present application.

[0083] See also Figure 3 , is another flow chart of the construction quality supervision method in the embodiment of the present application.

[0084] S301: Acquire real-time hydrological data within a preset area of the underwater quality inspection robot.

[0085] S302: Determine the moving speed and moving direction of the underwater quality inspection robot.

[0086] S303: Control the underwater quality inspection robot to move according to the moving speed and moving direction.

[0087] S304: When the real-time position of the underwater quality inspection robot is consistent with the target acquisition position in the preset moving path, the underwater quality inspection robot collects surface image data of the target inspection object corresponding to the target acquisition position.

[0088] S305: When it is detected that there is a covering on the surface of the target detection object in the surface image data, and the covering can be removed by the underwater quality inspection robot, identify the shape and coverage of the covering.

[0089] Steps S301-S305 and Figure 2 In the illustrated embodiment, steps S201 to S205 are similar, and reference may be made to the description of steps S201 to S204 , which will not be repeated here.

[0090] S306: Determine one or more covering object collection locations based on the shape and coverage.

[0091] Specifically, based on the shape of the covering, a 3D modeling algorithm is used to construct an approximate 3D model of the covering. If the covering is approximately rectangular, a cuboid model is constructed; if it is circular, a cylindrical model is constructed. For irregular shapes, models are constructed using polygonal mesh approximation. The covering's position and coverage information are mapped onto the 3D model to determine its exact position and range in underwater space. For example, given the covering's position and range on the target object's surface, the position of the covering's 3D model in the global coordinate system can be determined based on the target object's underwater posture.

[0092] For relatively regular-shaped coverings, such as circles or ellipses, the covering's geometric center is used as the reference point. Based on the covering's position on the target surface and the viewing angle of the underwater inspection robot's image acquisition device (this viewing angle parameter is pre-stored in the system), multiple equally spaced locations around this reference point are determined as covering acquisition locations. For example, if the underwater inspection robot's image acquisition device has a viewing angle of 360 degrees horizontally and 180 degrees vertically, covering acquisition locations can be determined at regular intervals (e.g., 60 degrees) to allow the robot to capture images of different sides of the covering at these locations.

[0093] For irregularly shaped covers, the edge contour of the cover is first analyzed to identify characteristic points, such as protrusions and depressions. Then, focusing on these characteristic points and taking into account the field of view of the underwater inspection robot's image acquisition equipment, multiple cover acquisition locations are determined around the cover to ensure that the images captured from these locations cover all characteristic parts of the cover.

[0094] S307 , controlling the underwater quality inspection robot to move to the cover collection position to collect image data around the cover.

[0095] Specifically, based on the current position of the underwater quality inspection robot, the path for the robot to reach each cover collection location is planned. First, an underwater environment map is established. Combined with detection means such as the underwater quality inspection robot's sonar equipment, map information of the target detection object and the environment around the target detection object, including information such as the location and shape of obstacles, is obtained to construct an underwater environment map containing the target detection object and the cover. This map is based on the global coordinate system and records the position information of each object. Then, a path planning algorithm, such as the A* algorithm or the Dijkstra algorithm, is used to plan the optimal path from the robot's current position to each collection location based on the underwater environment map, the robot's current position, and the coordinate information of each cover collection location. If an obstacle is found during the planning process and the robot cannot bypass these obstacles to reach the location, the location is determined to be unreachable, and the location is marked as an abnormal cover collection location, and image collection at this location is not performed.

[0096] Based on the paths of each cover collection location, corresponding control commands are sent to the underwater inspection robot in sequence. Upon receiving the corresponding control commands, the underwater inspection robot moves from its current position to the cover collection location along the path specified in the control command. After collecting image data of the cover, it returns to its current position according to the path. After the underwater inspection robot moves along the paths of each cover collection location in sequence and collects multiple cover images, it obtains image data of the surrounding cover.

[0097] S308: Identify the distance between the covering and the surface of the inspection object based on the image data surrounding the covering.

[0098] Specifically, first, the image data around the covering is preprocessed, including image denoising, contrast enhancement and other operations to improve image quality.

[0099] Then, monocular vision combined with depth estimation is used to calculate the distance between the covering and the surface of the object being inspected. Using a pre-trained deep learning-based monocular depth estimation model (such as MiDaS or DenseDepth), the model is trained with a large amount of image-depth data, enabling it to learn the mapping relationship between visual cues and depth information in the image. The system inputs preprocessed image data surrounding the covering into the trained model. Based on its internal algorithm and the learned mapping relationship, the model analyzes and processes the input image, outputting a depth prediction value for each pixel in the image. Based on their position in the image, the system extracts the depth values for the corresponding areas on the covering and the object being inspected from the depth prediction results. By calculating the difference between the depth values of these two corresponding areas, the distance between the covering and the object's surface is determined.

[0100] S309: Determine a plan for removing the covering according to the spacing and the type of covering.

[0101] Among them, removal solutions include water spray device removal, robotic arm removal, etc.

[0102] Specifically, if the covering type belongs to the preset first type (such as algae, some small floating objects, etc.), and the distance between the covering and the surface of the detection object is greater than the preset first threshold, it means that the water flow of the water spray device has sufficient space and range to impact the covering, and the removal plan is determined to be removal by the water spray device.

[0103] If the covering object type belongs to the preset first type (such as algae, some small floating objects, etc.), and the distance between the covering object and the surface of the detection object is less than the preset first threshold, it means that the water spray device may not be able to completely remove the covering object. The removal plan is determined to be removal by the water spray device. If the covering object is not removed within the preset time, it is removed by a robotic arm.

[0104] If the cover type belongs to the preset second type (such as shell attachments, some solid sediments, etc.), the removal plan is determined to be robotic arm removal.

[0105] S310: Control the underwater quality inspection robot to execute the removal plan.

[0106] S311 . When it is detected that the underwater quality inspection robot has completed executing the removal plan, target quality inspection data and target quality inspection image data corresponding to the target collection position are collected.

[0107] S312: Determine the quality inspection result of the target acquisition position according to the target quality inspection data and the target quality inspection image data.

[0108] Steps S310-S312 and Figure 2 Steps S206 to S208 in the illustrated embodiment are similar, and reference may be made to the description of steps S206 to S208 , which will not be repeated here.

[0109] S313: Calculate the quality inspection reliability of the quality inspection result according to the turbidity of the target acquisition position and the image clarity of the target quality inspection image data.

[0110] Specifically, sensors are used to obtain real-time turbidity at the target collection location. Turbidity reflects the content of suspended particles in the underwater environment. Higher turbidity has a greater impact on the accuracy of data collected by specific sensors and the clarity of image data collected by cameras, thereby affecting the accuracy of quality inspection results.

[0111] A variety of image clarity evaluation algorithms (such as those based on gradient, frequency domain, and information entropy) are used to calculate the clarity of target quality inspection image data. For example, gradient-based algorithms measure clarity by calculating the gradient information of edges and details in the image. Specifically, edge detection is performed on the image (using, for example, the Sobel operator or Canny operator), and then the gradient magnitude and number of edge pixels are counted. Larger gradient magnitudes and greater number of edge pixels indicate richer edges and details in the image, and therefore higher image clarity.

[0112] According to the preset weights, the real-time turbidity and image clarity are weightedly calculated to obtain the quality inspection credibility of the quality inspection results.

[0113] S314. When the quality inspection credibility is lower than the preset credibility threshold, multiple new acquisition positions are determined according to the image acquisition range of the underwater quality inspection robot and the preset image acquisition area of the target inspection object.

[0114] The distance between the newly added acquisition position and the target object is smaller than the distance between the target acquisition position and the target object. The image acquisition range of the underwater quality inspection robot includes the horizontal and vertical viewing angles of the robot's built-in camera, the maximum acquisition distance, and other information.

[0115] Specifically, when the quality inspection credibility is lower than a preset credibility threshold, the preset image acquisition area of the target detection object is segmented according to a preset rule to obtain a plurality of preset image acquisition sub-areas.

[0116] Determine the geometric center position of each preset image acquisition sub-region. For sub-regions with regular shapes, such as circles and rectangles, the center position can be directly calculated using the corresponding geometric formula; for sub-regions with irregular shapes, numerical integration methods are used for approximate calculation.

[0117] Taking the geometric center of the sub-area as the starting point, based on the image acquisition range of the underwater quality inspection robot, determine the minimum distance between the acquisition position of the corresponding preset image acquisition sub-area and the target detection object at which the robot's built-in camera can fully cover it. First, based on the coordinates of the boundary points of the sub-area and the camera's viewing angle range in the horizontal and vertical directions, a local coordinate system is established with the geometric center of the sub-area as the origin, and the intersection of the cone or prism formed according to the viewing angle range and the sub-area boundary at different distances from the origin is calculated. The system will gradually increase the distance value starting from the preset minimum distance, and each time a distance value is increased, it will determine whether the camera's coverage area can completely contain the preset image acquisition sub-area. When the first distance that satisfies the camera's ability to fully cover the corresponding preset image acquisition sub-area is found, this distance is the required minimum distance.

[0118] According to the center position of each preset image acquisition sub-region and the minimum distance from the center position, the newly added acquisition position corresponding to each preset image acquisition sub-region is calculated.

[0119] S315. Collect new quality inspection data and new quality inspection image data at the newly added collection location through the underwater quality inspection robot.

[0120] Step S315 is the same as the above steps S307 and Figure 2 In the embodiment shown, step S207 is similar, and reference may be made to the above steps S307 and Figure 2 The description of step S207 in the illustrated embodiment will not be repeated here.

[0121] S316: Update the quality inspection results based on the newly added quality inspection data and the newly added quality inspection image data.

[0122] Based on the newly added quality inspection data and the newly added quality inspection image data, the newly added quality inspection results corresponding to each newly added quality inspection position are determined. If there is one quality inspection result that is unqualified among all the newly added quality inspection results, the quality inspection result is updated to be unqualified; if all the newly added quality inspection results are qualified, the quality inspection result is updated to be qualified.

[0123] The step of determining the quality inspection result corresponding to the newly added quality inspection position in step S316 is the same as Figure 2 Step S208 in the illustrated embodiment is similar, and reference may be made to the description of step S208 , which will not be repeated here.

[0124] S317. When the real-time position of the underwater quality inspection robot is consistent with the end position in the preset moving path, calculate the quality inspection pass rate of the construction project corresponding to the preset moving path.

[0125] When the real-time position of the underwater quality inspection robot is consistent with the end position in the preset moving path, the quality inspection pass rate of the construction project corresponding to the preset moving path is calculated based on the quality inspection results of each collection position in the preset moving path.

[0126] Specifically, the real-time position of the underwater quality inspection robot is obtained. When the real-time position of the underwater quality inspection robot is detected to be consistent with the end position in the preset movement path, the number of sampling locations with qualified quality inspection results is divided by the total number of sampling locations in the preset movement path to obtain the quality inspection pass rate of the construction project corresponding to the preset movement path.

[0127] S318. When the quality inspection pass rate is less than a preset threshold, determine the reasons for the failure of the construction project.

[0128] When the quality inspection pass rate is less than a preset threshold, the reasons for the failure of the construction project are determined based on the abnormal quality inspection data and abnormal quality inspection image data corresponding to the unqualified collection positions.

[0129] Among them, unqualified collection locations are collection locations where the quality inspection results are unqualified, and the reasons for failure include construction problems and design problems.

[0130] Specifically, when the quality inspection pass rate is less than a preset threshold, abnormal quality inspection data and abnormal quality inspection image data corresponding to the unqualified acquisition position are acquired.

[0131] For abnormal quality inspection data, construction records are first retrieved from the construction project database. This database stores all relevant information from the beginning to the current stage of the construction project, including material procurement and usage. When obtaining material procurement information, detailed material data is obtained by searching the database for tables or files related to material procurement. Material usage is determined based on the construction logs, construction drawings, and detailed records of each construction step in the construction records. By analyzing the construction logs, it is determined in which parts of the target inspection object different batches of materials were used, as well as the chronological order of their use.

[0132] Next, compare material usage with design requirements, using the construction drawings. The construction drawings detail the material specifications and models for each part. Comparing the actual materials used with the design requirements determines if there are any problems during construction. If the materials used don't match the design requirements, the failure is determined to be a construction issue; if they do, the failure is determined to be a design issue.

[0133] For abnormal quality inspection image data, image segmentation algorithms, such as Mask R-CNN, are used to accurately segment defective areas on the target surface from the background. Feature extraction is then performed on the segmented defective areas, including shape features (such as perimeter, area, and aspect ratio), texture features (such as texture parameters extracted from the gray-level co-occurrence matrix), and color features (such as color distribution in the RGB color space). The extracted features are then compared and matched against a pre-stored feature library of various construction and design defects.

[0134] If the defect signature has a high degree of match with the signatures in the construction defect signature library, the failure is judged to be a construction problem. If the defect signature has a high degree of match with the signatures in the design defect signature library, the failure is judged to be a design problem.

[0135] In some embodiments, in order to more accurately determine whether the cause of failure is a construction problem or a design problem, abnormal quality inspection data, abnormal quality inspection image data and construction records can be sent to construction experts and designers, and feedback from construction experts and designers can be received to determine the cause of failure.

[0136] S319. Determine the rework area and rework project based on the abnormal quality inspection data, abnormal quality inspection image data, and construction project corresponding to the unqualified collection location.

[0137] Specifically, the abnormal quality inspection data includes unqualified acquisition locations of data collected by the acoustic sensor, resulting in a first location set. The abnormal quality inspection data includes unqualified acquisition locations of data collected by the electrochemical sensor, resulting in a second location set. The abnormal quality inspection data includes unqualified acquisition locations of data collected by the pressure sensor, resulting in a third location set. The abnormal quality inspection data includes unqualified acquisition locations of data collected by the image sensor, resulting in a fourth location set.

[0138] Obtain a rework project table corresponding to the construction project. Obtain the first rework project in the rework project table that corresponds to the abnormality in the data collected by the acoustic sensor, and use the quality inspection area corresponding to each position in the first position set as the rework area for the first rework project. Obtain the second rework project in the rework project table that corresponds to the abnormality in the data collected by the electrochemical sensor, and use the quality inspection area corresponding to each position in the first position set as the rework area for the second rework project. Obtain the third rework project in the rework project table that corresponds to the abnormality in the data collected by the pressure sensor, and use the quality inspection area corresponding to each position in the third position set as the rework area for the third rework project. Obtain the fourth rework project in the rework project table that corresponds to the abnormality in the quality inspection image data, and use the quality inspection area corresponding to each position in the fourth position set as the rework area for the fourth rework project.

[0139] By combining the above rework items and their corresponding rework areas, we can obtain the rework areas and rework items corresponding to the construction project.

[0140] S320: When a construction machine corresponding to the rework project fails, determine the extent to which the failure of the construction machine affects the construction quality of the rework project.

[0141] When a construction machine corresponding to a rework project fails, the degree of influence of the failure on the construction quality of the rework project is determined based on the failure condition of the construction machine and the hydrological data of the rework area.

[0142] The impact levels range from mild to severe.

[0143] Specifically, real-time operating data for the construction machines corresponding to each item in the rework project is obtained, such as engine speed, operating voltage, operating current, hydraulic system pressure, machine operating speed, operating hours, and other parameters. This real-time operating data is compared with the preset normal operating data of the construction machines to determine whether there is any fault in the construction machines.

[0144] When a construction machine corresponding to each item in a rework project fails, the fault condition of the construction machine (i.e., the faulty construction machine) is determined based on the abnormal location corresponding to the abnormal data and the degree of deviation between the abnormal data and the normal data. The fault condition includes the location of the fault and the degree of fault, with the degree of fault ranging from mild, moderate, to severe. Based on the abnormal parameter-location correspondence table of the construction machine and the abnormal data, the fault location corresponding to each abnormal parameter in the abnormal data is determined. The degree of fault of the fault location is determined based on the degree of deviation between the abnormal parameters corresponding to the fault location and the normal parameters. The difference between the abnormal parameters and the normal parameters of the fault location is calculated. If the difference is within a preset first range, the fault degree of the fault location is mild; if the difference is within a preset second range, the fault degree of the fault location is moderate; if the difference is within a preset third range, the fault degree of the fault location is severe.

[0145] The preset weights of each fault location in the fault situation of the construction machine and the fault value corresponding to each fault degree are obtained, and the impact value of the construction machine fault on the construction quality is calculated by weighted average.

[0146] If the impact value is greater than the first preset threshold, it is determined that the impact of the fault on the construction quality of the rework project is serious.

[0147] If the impact value is less than or equal to a first preset threshold, sensors are used to obtain hydrological data for the rework area, including parameters such as water flow velocity, water pressure, water temperature, and water turbidity. If the hydrological data is within the first preset hydrological data range, it indicates that the current hydrological environment is stable, the water flow is gentle, and the impact on construction is within normal levels. The fault is determined to have a minor impact on the construction quality of the rework project. If the hydrological data is not within the first preset hydrological data range, it indicates that the current hydrological environment has a significant impact on construction. The fault is determined to have a severe impact on the construction quality of the rework project.

[0148] S321. When the impact is severe, determine one or more construction replacement plans based on the working information of idle construction machines, information of idle construction personnel, rework items, and hydrological data of the rework area.

[0149] Specifically, based on the historical operating parameters of the idle construction machines, the idle construction machines are identified as being normal, non-faulty idle construction machines. Based on the idle construction personnel information, the number of idle construction personnel adapted for each idle construction machine is determined. Based on a pre-set construction replacement plan table corresponding to each item in the rework project, one or more construction replacement plans are searched for in which the number of construction machines and their corresponding operators matches the number of normal, idle construction machines and their corresponding adapted idle construction personnel.

[0150] S322. Determine a first rework duration estimated to be required for rework according to the construction replacement plan, the rework items, and the rework area.

[0151] Specifically, the construction efficiency of the alternative construction plan corresponding to the rework item is obtained from the construction alternative plan table. Construction efficiency refers to the construction area that can be completed per unit time according to the construction plan. Based on the construction efficiency and the rework area, the estimated first rework duration required to perform the rework according to the construction alternative plan (i.e., rework without using the faulty construction machine) is calculated.

[0152] S323. Determine a second rework duration of the construction machine according to the fault condition of the construction machine, the rework item, the rework area, and the rework efficiency of the construction machine.

[0153] The second rework time is the sum of the maintenance time of the construction machine and the rework time required to use the construction machine (ie, the faulty construction machine) for rework.

[0154] Specifically, based on the fault condition of the construction machine, the first maintenance duration corresponding to each fault location and its corresponding fault severity in the fault condition is obtained from the maintenance duration table of the construction machine. The sum of all first maintenance durations is calculated to obtain the maintenance duration of the construction machine. The construction efficiency corresponding to the original construction plan is obtained. Based on the construction efficiency and the rework area, the rework duration of the original construction plan (i.e., rework using the faulty construction machine) is calculated.

[0155] The sum of the maintenance time of the construction machine and the rework time of the original construction plan is calculated as the second rework time of the construction machine.

[0156] S324. When the reason for non-compliance is a construction problem, the shorter of the shortest first rework time and the shortest second rework time is used as the predicted rework time for the rework item.

[0157] When the reason for non-compliance is a construction problem, compare the shortest first rework time and the second rework time, and use the shorter time as the predicted rework time for the rework item.

[0158] Among them, the shortest first rework duration is the shortest among all first rework durations.

[0159] S325. When the reason for non-conformity is a design problem, determine the redesign time of the rework area based on the preset design schedule, rework items and rework area.

[0160] When the reason for non-compliance is a design problem, the first design duration corresponding to the rework item and the rework area in the preset design schedule corresponding to the construction project is obtained, and the sum of all first design durations is calculated to obtain the redesign duration of the rework area.

[0161] S326. When the redesign time is greater than or equal to the maintenance time, the second rework time is used as the predicted rework time.

[0162] Compare the redesign duration with the repair duration. When the redesign duration is greater than or equal to the repair duration, use the second rework duration as the predicted rework duration.

[0163] S327. When the redesign time is less than the maintenance time, the shorter of the shortest first rework time and the shortest third rework time is used as the predicted rework time.

[0164] When the redesign time is less than the maintenance time, the difference between the second rework time and the redesign time is calculated to obtain the third rework time. The third rework time is compared with the shortest first rework time, and the shorter time is used as the predicted rework time.

[0165] S328. Adjust the construction time of the remaining construction items in the preset construction plan based on the predicted rework time.

[0166] Specifically, the remaining construction projects that are to be carried out after the construction project in the preset construction plan are obtained. The start and completion time points of each construction project in the remaining construction projects are obtained, and the predicted rework duration is added to the start and completion time points of each construction project to obtain the new start and completion time points of each construction project. The start and completion time points of the remaining construction projects are then replaced with the corresponding new start and completion time points.

[0167] In an embodiment of the present application, the underwater quality inspection robot's movement speed and direction are dynamically adjusted based on real-time hydrological data to ensure that the robot can accurately reach each collection location, avoid detection position deviations caused by interference from factors such as water flow, and improve the reliability of data collection. When a covering is detected on the surface of the detection object and the covering can be removed by the underwater quality inspection robot, the underwater quality inspection robot removes the covering on the surface of the detection object and then collects quality inspection data and quality inspection image data of the detection object. Based on the quality inspection data and the quality inspection image data, the detection object is quality inspected and a quality inspection result is generated, thereby improving the accuracy of the quality inspection results of the underwater quality inspection. When the quality inspection reliability is lower than a preset threshold, multiple new collection locations are accurately determined based on the image acquisition range of the underwater quality inspection robot and the preset image acquisition area of the target detection object. These new collection locations are closer to the target detection object, which can reduce the impact of environmental factors (such as turbidity) on image acquisition and data acquisition, making the collected new quality inspection data and new quality inspection image data clearer and more accurate, thereby improving the accuracy of the quality inspection results of the underwater quality inspection. When it is detected that the use of faulty construction machines for construction will have a serious impact on the construction quality of the rework project, a construction replacement plan is formulated based on idle construction machines and idle construction personnel. Even if the construction machine required by the original construction plan fails, the rework project can be carried out according to the construction replacement plan. While ensuring the construction quality, the impact of the construction machine failure on the construction progress of the rework project is reduced.

[0168] The above describes the construction quality supervision method in the embodiment of the present application. The following describes in detail the construction quality supervision system in the embodiment of the present application in combination with the above construction quality supervision method.

[0169] See also Figure 4 , which is a schematic diagram of an exemplary hardware structure of the construction quality supervision system in an embodiment of the present application.

[0170] In some embodiments, the construction quality supervision system 400 includes a computer device, which can be a terminal device. The computer device includes a processor 401, memory 402, a sensor module 403, a communication module 404, an input device 405, and an output device 406, all connected via a system bus. The processor 401 of the computer device provides computing and control capabilities. The memory 402 of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operating system and computer programs stored in the non-volatile storage medium. The database stores data. The sensor module 403 of the computer device collects hydrological data and quality inspection data. The communication module 404 of the computer device transmits hydrological data, quality inspection data, quality inspection image data, and the location of an underwater quality inspection robot to a server, and sends control commands to the underwater quality inspection robot. The input device 405 of the computer device receives collected hydrological data, quality inspection data, quality inspection image data, and other collected data. The output device 406 of the computer device displays quality inspection results. When the computer program is executed by the processor 401, the construction quality supervision method in the embodiment of the present application is implemented.

[0171] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0172] In some embodiments of the present application, a computer-readable storage medium is provided, including instructions. When the instructions are executed on the construction quality supervision system 400, the construction quality supervision system 400 can execute the construction quality supervision method in the embodiments of the present application.

[0173] In some embodiments of the present application, a computer program product is also provided. When the computer program product runs on the construction quality supervision system 400, the construction quality supervision system 400 executes the construction quality supervision method in the embodiments of the present application.

[0174] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0175] As used in the above embodiments, the term “when” may be interpreted to mean “if” or “after” or “in response to determining that” or “in response to detecting that”, depending on the context. Similarly, the phrases “upon determining that” or “if (stated condition or event) is detected” may be interpreted to mean “if determining that” or “in response to determining that” or “upon detecting (stated condition or event)” or “in response to detecting (stated condition or event)”, depending on the context.

[0176] In the above embodiments, all or part of the embodiments can be implemented using software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of this application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer, or a data storage device such as a server or data center that integrates one or more available media. The available medium can be magnetic media (e.g., floppy disk, hard disk, tape), optical media (e.g., DVD), or semiconductor media (e.g., solid-state drive).

[0177] Those skilled in the art will appreciate that all or part of the process steps in the above-described method embodiments can be implemented by a computer program instructing the relevant hardware. The program can be stored in a computer-readable storage medium, and when executed, the program can include the process steps in the above-described method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A construction quality supervision method, characterized in that: include: Acquire real-time hydrological data within a preset area of the underwater quality inspection robot, wherein the real-time hydrological data includes water flow velocity, water flow direction, and turbidity; Determining a moving speed and a moving direction of the underwater quality inspection robot according to the real-time hydrological data, a preset moving path of the underwater quality inspection robot, and a real-time position of the underwater quality inspection robot, wherein the preset moving path includes one or more collection locations; Controlling the underwater quality inspection robot to move at the moving speed and in the moving direction; When the real-time position of the underwater quality inspection robot is consistent with the target acquisition position in the preset movement path, the underwater quality inspection robot collects surface image data of the target inspection object corresponding to the target acquisition position, where the target acquisition position is one of all acquisition positions in the preset movement path; When a covering is detected on the surface of the target object in the surface image data, and the covering can be removed by the underwater quality inspection robot, determining a removal scheme for the covering according to the type and coverage of the covering, the removal scheme including removal by a water spray device and removal by a robotic arm; Controlling the underwater quality inspection robot to execute the removal plan; When it is detected that the underwater quality inspection robot has completed executing the removal plan, the underwater quality inspection robot collects target quality inspection data and target quality inspection image data corresponding to the target collection position, and no covering exists on the surface of the target detection object in the target quality inspection image data; A quality inspection result of the target acquisition position is determined according to the target quality inspection data and the target quality inspection image data.

2. The method according to claim 1, characterized in that When a covering is detected on the surface of the target detection object in the surface image data, and the covering can be removed by the underwater quality inspection robot, determining a plan for removing the covering according to the type and coverage of the covering specifically includes: When it is detected that a covering exists on the surface of the target detection object in the surface image data and the covering can be removed by the underwater quality inspection robot, identifying the shape and coverage of the covering according to the surface image data; determining one or more cover collection locations based on the shape and the coverage range; Controlling the underwater quality inspection robot to move to the cover collection position to collect image data around the cover; identifying the distance between the covering and the surface of the detection object based on the image data surrounding the covering; A plan for removing the covering is determined based on the spacing and the covering type.

3. The method according to claim 1, characterized in that After the step of determining the quality inspection result of the target acquisition position based on the target quality inspection data and the target quality inspection image data, the method further includes: Calculating the quality inspection credibility of the quality inspection result according to the turbidity of the target acquisition position and the image clarity of the target quality inspection image data; When the quality inspection credibility is lower than a preset credibility threshold, a plurality of new acquisition positions are determined according to the image acquisition range of the underwater quality inspection robot and the preset image acquisition area of the target detection object, and the distance between the new acquisition positions and the target detection object is less than the distance between the target acquisition positions and the target detection object; Collecting the newly added quality inspection data and newly added quality inspection image data of the newly added collection position by the underwater quality inspection robot; The quality inspection result is updated according to the newly added quality inspection data and the newly added quality inspection image data.

4. The method according to claim 1, wherein After the step of determining the quality inspection result of the target acquisition position based on the target quality inspection data and the target quality inspection image data, the method further includes: When the real-time position of the underwater quality inspection robot is consistent with the end position in the preset movement path, the quality inspection pass rate of the construction project corresponding to the preset movement path is calculated according to the quality inspection results of each collection position in the preset movement path; When the quality inspection pass rate is less than a preset threshold, the reasons for the failure of the construction project are determined based on the abnormal quality inspection data and abnormal quality inspection image data corresponding to the unqualified collection position. The unqualified collection position is the collection position where the quality inspection result is unqualified, and the reasons for the failure include construction problems and design problems.

5. The method according to claim 4, characterized in that When the quality inspection pass rate is less than a preset threshold, after the step of determining the cause of failure of the construction project based on the abnormal quality inspection data and abnormal quality inspection image data corresponding to the unqualified acquisition position, the method further includes: Determine a rework area and rework item based on the abnormal quality inspection data and abnormal quality inspection image data corresponding to the unqualified collection location and the construction item; When a construction machine corresponding to the rework item fails, determining a predicted rework time for the rework item based on the failure condition and failure reason of the construction machine; According to the predicted rework time, the construction time of the remaining construction items in the preset construction plan is adjusted.

6. The method according to claim 5, characterized in that When a construction machine corresponding to the rework item fails, determining a predicted rework time for the rework item according to the failure condition and failure reason of the construction machine specifically includes: When a construction machine corresponding to the rework project fails, determining the degree of impact of the failure on the construction quality of the rework project based on the failure condition of the construction machine and hydrological data of the rework area, wherein the degree of impact includes minor and severe. When the impact is severe, determining one or more construction replacement plans based on the working information of idle construction machines, the information of idle construction personnel, the rework project, and the hydrological data of the rework area; Determining, based on the construction replacement plan, the rework item, and the rework area, a first rework duration estimated to be required for rework according to the construction replacement plan; determining a second rework duration of the construction machine according to the fault condition of the construction machine, the rework item, the rework area, and the rework efficiency of the construction machine, where the second rework duration is the sum of the maintenance duration of the construction machine and the rework duration required to use the construction machine for the rework; The predicted rework duration of the rework item is determined according to the non-conformity reason, the shortest first rework duration, the maintenance duration, and the second rework duration, wherein the shortest first rework duration is the shortest among all first rework durations.

7. The method according to claim 6, characterized in that The step of determining the predicted rework duration of the rework item according to the failure reason, the shortest first rework duration, the maintenance duration, and the second rework duration specifically includes: When the reason for the failure is a construction problem, the shorter of the shortest first rework duration and the second rework duration is used as the predicted rework duration of the rework item; When the reason for the non-conformity is a design problem, determining the redesign time of the rework area according to the preset design schedule, the rework items and the rework area; When the redesign time is greater than or equal to the maintenance time, taking the second rework time as the predicted rework time; When the redesign time is less than the maintenance time, the shorter of the shortest first rework time and the third rework time is used as the predicted rework time, and the third rework time is the difference between the second rework time and the redesign time.

8. A construction quality supervision system, characterized in that: The system comprises an underwater quality inspection robot, a sensor and a server, wherein the underwater quality inspection robot and the sensor are respectively connected to the server for communication, and the sensor is connected to the underwater quality inspection robot, wherein the server comprises: one or more processors and a memory; The memory is coupled to the one or more processors, and is configured to store computer program codes, where the computer program codes include computer instructions. The one or more processors call the computer instructions to enable the construction quality supervision system to execute the method according to any one of claims 1 to 7.

9. A computer-readable storage medium storing computer instructions, characterized in that: When the computer instructions are executed on a construction quality supervision system, the construction quality supervision system is caused to execute the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that When the computer program product is run on a construction quality supervision system, the construction quality supervision system is enabled to execute the method according to any one of claims 1 to 7.

Images