Pipeline flaw detection robot control system and method

Abstract

The invention discloses a pipeline flaw detection robot control system and method, and relates to the technical field of robots, and the pipeline flaw detection robot control system comprises a data acquisition module, a data analysis module, a data processing module and a local database, the method comprises the following steps: acquiring environmental parameters and structural characteristic parameters of the dense stainless steel pipe network of the thermal power plant and running state parameters of a pipeline flaw detection robot, identifying obstacle types of an inherent structure in the dense stainless steel pipe network of the thermal power plant, detecting damage characteristics, evaluating a safety running risk level and generating a three-dimensional digital model; an obstacle avoidance path can be planned, an optimal detection mode can be matched, the running state of the pipeline flaw detection robot can be dynamically adjusted, the performance degradation trend of the dense stainless steel pipe network of the thermal power plant can be evaluated, the problems of low efficiency and poor safety of traditional detection are solved, and the detection precision and the maintenance reliability of the dense stainless steel pipe network of the thermal power plant are improved.

Description

Technical Field

[0001] This invention relates to the field of robotics, specifically to a control system and method for a pipeline flaw detection robot. Background Technology

[0002] In thermal power plant scenarios, dense stainless steel pipe networks are prone to mechanical damage and cracks over long-term use, which could lead to serious accidents such as system shutdowns if not detected in time. Traditional methods such as manual inspection and handheld device inspection are inefficient and unsafe, making it difficult to meet inspection requirements. Current breakthroughs in technologies such as mobile control and high-precision sensing have driven the development of pipe flaw detection robots suitable for nuclear scenarios. However, existing systems are difficult to match the requirements of miniaturization and dust concentration resistance in this scenario. Therefore, it is necessary to study a pipe flaw detection robot control system and method.

[0003] Existing technologies, such as the invention patent application with publication number CN117054525A, disclose a pipeline ultrasonic flaw detection system and its control method. The system includes: a mounting clamp on a pipeline inspection robot, and multiple preliminary ultrasonic flaw detection components and re-inspection ultrasonic flaw detection components on the mounting clamp. The preliminary component includes a first mounting frame, a first drive motor and a first drive wheel on the frame, and a preliminary ultrasonic flaw detection probe. The re-inspection component includes a second mounting frame, a second drive motor and a second drive wheel on the frame, and a re-inspection ultrasonic flaw detection probe. Both types of components can rotate circumferentially on the robot body, facilitating circumferential flaw detection of the pipeline. Another existing technology, such as the invention patent application with publication number CN113954089B, discloses an intelligent inspection device and method for a non-destructive testing robot. The device includes: a pipeline flaw detection system and a ground control system. The two transmit data wirelessly. The pipeline flaw detection system includes a pipeline crawler, an ultrasonic flaw detector, a servo motor, and a spray marking device. The servo motor drives the flaw detector to rotate for detection, and the defects are marked by the spray marking device. This allows for comprehensive intelligent detection and precise positioning, facilitating subsequent maintenance.

[0004] As can be seen from the above solutions, the current pipeline flaw detection robot control system lacks environmental adaptability and struggles to cope with extreme conditions such as high dust concentrations, high temperatures, and drastic pressure changes in high-risk scenarios at thermal power plants. This leads to decreased accuracy of sensors installed on the pipeline flaw detection robot and a decline in overall equipment reliability. In terms of detection capabilities, existing technologies lack an effective multi-source data collaborative analysis mechanism, failing to simultaneously quantify and fuse various damage characteristics such as crack depth and high-temperature oxidation. Furthermore, they fail to demonstrate the correlation between damage characteristics and safety risk levels in a three-dimensional digital model. Simultaneously, the pipeline flaw detection robot control system exhibits significant shortcomings in intelligence. Its path planning cannot fully consider the complex geometry of the pipeline network, and fixed detection modes result in low detection efficiency. It also lacks the ability to dynamically adjust its operating status based on extreme environmental parameters such as dust concentration and temperature to ensure continuous operation. Regarding the integration of the pipeline flaw detection robot control system, it fails to construct a multi-attribute three-dimensional digital model that integrates geometric structure, damage characteristics, safety levels, and environmental parameters to support comprehensive decision-making. The closed-loop real-time performance from detection to path planning and execution adjustment is poor, making it difficult to meet the stringent requirements of preventative maintenance in thermal power plants. Summary of the Invention

[0005] The purpose of this invention is to provide a pipeline flaw detection robot control system and method, which solves the problems existing in the background art.

[0006] To solve the above-mentioned technical problems, the present invention adopts the following technical solution: The first aspect of the present invention provides a pipeline flaw detection robot control system, including a data acquisition module: used to acquire internal environmental parameters, structural feature parameters and pipeline flaw detection robot operating status parameters of the dense stainless steel pipe network in a thermal power plant. The environmental parameters include temperature gradient, air pressure change and dust concentration. The structural feature parameters include pipe diameter, curvature and surface roughness. The pipeline flaw detection robot operating status parameters include real-time attitude angle and movement speed.

[0007] Data analysis module: used to identify the types of inherent structural obstacles inside the dense stainless steel pipe network of thermal power plants and locate their spatial positions, detect the damage characteristics of the dense stainless steel pipe network of thermal power plants, assess the safety operation risk level of the dense stainless steel pipe network of thermal power plants, and comprehensively generate a three-dimensional digital model of the dense stainless steel pipe network of thermal power plants.

[0008] Preferably, the specific method for identifying the type of inherent structural obstacle inside the dense stainless steel pipe network of a thermal power plant and locating its spatial position is as follows: Point cloud data of the interior of the dense stainless steel pipe network of the thermal power plant is acquired by scanning with a laser radar installed on a pipe flaw detection robot to construct a three-dimensional contour. When the pipe flaw detection robot identifies the inherent structure inside the dense stainless steel pipe network of the thermal power plant, it matches the corresponding obstacle type stored in the local database according to the obstacle type corresponding to the inherent structure inside the dense stainless steel pipe network of the thermal power plant, and directly locates the spatial position of the detected inherent structural obstacle inside the dense stainless steel pipe network of the thermal power plant using the self-localization data of the pipe flaw detection robot.

[0009] Preferably, the specific method for detecting the damage characteristics of the dense stainless steel pipe network in a thermal power plant is as follows: extract the measured values ​​of pipe diameter and bending arc from the point cloud data inside the dense stainless steel pipe network of the thermal power plant, and compare them with the corresponding pipe diameter and bending arc in the original point cloud data of the dense stainless steel pipe network of the thermal power plant. If the difference between any measured pipe diameter and the original pipe diameter exceeds a preset diameter deformation threshold, or the difference between any measured bending arc and the original bending arc exceeds a preset arc deformation threshold, then it is determined that the dense stainless steel pipe network of the thermal power plant has mechanical damage characteristics.

[0010] By using ultrasonic sensors and high-definition vision sensors installed on the pipeline flaw detection robot, ultrasonic echo signals and images of the inner wall surface of the pipeline are acquired simultaneously. When the echo amplitude in the ultrasonic signal exceeds the preset crack amplitude threshold and crack features appear in the inner wall surface image of the pipeline, it is determined that the dense stainless steel pipeline network of the thermal power plant has crack damage features.

[0011] When the wall thickness reduction measured by ultrasonic echo signal exceeds the preset high-temperature oxidation thickness threshold and the surface roughness of the pipe exceeds the preset surface roughness tolerance value, it is determined that the dense stainless steel pipe network of the thermal power plant has high-temperature oxidation damage characteristics.

[0012] Preferably, the method for assessing the safety operation risk level of the dense stainless steel pipe network in a thermal power plant is as follows: based on the damage characteristics of the dense stainless steel pipe network in a thermal power plant, the safety operation risk level of the dense stainless steel pipe network in a thermal power plant is divided into three levels.

[0013] If mechanical damage characteristics, crack damage characteristics, and high-temperature oxidation damage characteristics are detected simultaneously in the dense stainless steel pipe network of a thermal power plant, the safety operation risk level of the dense stainless steel pipe network of the thermal power plant is determined to be Level 1.

[0014] If any two of the following characteristics are detected in the dense stainless steel pipe network of a thermal power plant: mechanical damage, crack damage, or high-temperature oxidation damage, the safety operation risk level of the dense stainless steel pipe network of the thermal power plant is determined to be Level II.

[0015] If any one of the mechanical damage characteristics, crack damage characteristics, or high-temperature oxidation damage characteristics is detected in the dense stainless steel pipe network of a thermal power plant, the safety operation risk level of the dense stainless steel pipe network of the thermal power plant is determined to be Level III.

[0016] Preferably, the method for generating a comprehensive three-dimensional digital model of the dense stainless steel pipe network of a thermal power plant is as follows: the types and spatial location information of internal structural obstacles in the dense stainless steel pipe network of the thermal power plant identified by the pipeline flaw detection robot, the spatial distribution and geometric deformation of the detected mechanical damage features, the extension path of crack damage features, the area distribution of high-temperature oxidation damage features, the wall thickness reduction and surface roughness are mapped to the constructed three-dimensional contour framework according to spatial coordinates, the safety operation risk level of the dense stainless steel pipe network of the thermal power plant is rendered by color, and environmental parameters are introduced into the three-dimensional contour, finally generating a three-dimensional digital model of the dense stainless steel pipe network of the thermal power plant that integrates geometric structure, damage features, safety operation level and environmental parameters.

[0017] Data processing module: Used to generate obstacle avoidance path for pipeline flaw detection robot based on 3D digital model of dense stainless steel pipe network in thermal power plant, match optimal detection mode of pipeline flaw detection robot, dynamically adjust the operating status of pipeline flaw detection robot according to environmental parameters, and evaluate the performance degradation trend of dense stainless steel pipe network in 3D thermal power plant.

[0018] Preferably, the method for generating the obstacle avoidance path for the pipeline flaw detection robot is as follows: Obstacle types and their spatial locations within the dense stainless steel pipe network of a three-dimensional thermal power plant are extracted using a digital model of the network. A path planning algorithm is then used, starting from the current location of the pipeline flaw detection robot and ending at the target detection point, to perform global path planning by avoiding the extracted obstacle types and spatial locations within the dense stainless steel pipe network of the thermal power plant. Simultaneously, if the dust concentration in a certain area within the dense stainless steel pipe network of the thermal power plant exceeds a preset dust concentration observation threshold set by the optical sensor, that area must be avoided during global path planning.

[0019] Preferably, the optimal detection mode for matching the pipeline flaw detection robot is determined as follows: based on the obstacle avoidance path of the pipeline flaw detection robot, if the safety operation risk level of the dense stainless steel pipeline network in the thermal power plant is Level 1, then the optimal detection mode for matching the pipeline flaw detection robot is the fine detection mode; if the safety operation risk level of the dense stainless steel pipeline network in the thermal power plant is Level 2, then the optimal detection mode for matching the pipeline flaw detection robot is the standard detection mode; and if the safety operation risk level of the dense stainless steel pipeline network in the thermal power plant is Level 3, then the optimal detection mode for matching the pipeline flaw detection robot is the rapid general survey mode.

[0020] Preferably, the method for dynamically adjusting the operating status of the pipeline flaw detection robot according to environmental parameters is as follows: During the obstacle avoidance path of the generated pipeline flaw detection robot, the temperature gradient, air pressure change, and dust concentration of the dense stainless steel pipelines in the thermal power plant are acquired in real time. When the dust concentration exceeds the preset dust concentration observation threshold of the optical sensor, the movement speed is immediately reduced to a safe limit and the cleaning device is activated. When the temperature gradient of the dense stainless steel pipelines in the thermal power plant exceeds the preset warning temperature gradient value, causing local overheating of the pipeline flaw detection robot, the real-time attitude angle of the pipeline flaw detection robot is adjusted to dissipate heat from the local overheated area. When the air pressure change of the dense stainless steel pipelines in the thermal power plant exceeds the preset air pressure change amplitude threshold during the detection period, it affects the optical sensor of the pipeline flaw detection robot and causes measurement error. The real-time attitude angle of the pipeline flaw detection robot is adjusted to compensate for the measurement error caused by the air pressure change.

[0021] Preferably, the method for evaluating the performance degradation trend of the three-dimensional dense stainless steel pipe network of a thermal power plant is as follows: based on the damage feature data in the digital model of the three-dimensional dense stainless steel pipe network of the thermal power plant in the current inspection cycle, the data is compared with the three-dimensional digital model of the same dense stainless steel pipe network of the thermal power plant in the previous inspection cycle stored in the local database when it was not repaired. If the expansion rate of any damage feature between the current inspection cycle and the previous inspection cycle exceeds its preset warning degradation expansion rate threshold, the performance degradation trend of the three-dimensional dense stainless steel pipe network of the thermal power plant is determined to be rapid degradation; otherwise, the performance degradation trend of the three-dimensional dense stainless steel pipe network of the thermal power plant is slow degradation.

[0022] A second aspect of the present invention provides a control method for a pipeline flaw detection robot control system, characterized by comprising the following steps: 1. Data acquisition: acquiring internal environmental parameters, structural characteristic parameters, and pipeline flaw detection robot operating status parameters of a dense stainless steel pipe network in a thermal power plant. The environmental parameters include temperature gradient, air pressure change, and dust concentration. The structural characteristic parameters include pipe diameter, curvature, and surface roughness. The pipeline flaw detection robot operating status parameters include real-time attitude angle and motion speed. Step 2. Data Analysis: Identify the types of inherent structural obstacles within the dense stainless steel pipe network of the thermal power plant and locate their spatial positions; detect the damage characteristics of the dense stainless steel pipe network of the thermal power plant; assess the safety operation risk level of the dense stainless steel pipe network of the thermal power plant; and comprehensively generate a three-dimensional digital model of the dense stainless steel pipe network of the thermal power plant.

[0023] Step 3. Data Processing: Generate obstacle avoidance path for the pipeline flaw detection robot based on the 3D digital model of the dense stainless steel pipe network of the thermal power plant, match the optimal detection mode of the pipeline flaw detection robot, dynamically adjust the operating status of the pipeline flaw detection robot according to environmental parameters, and evaluate the performance degradation trend of the 3D dense stainless steel pipe network of the thermal power plant.

[0024] The beneficial effects of the present invention are as follows: (1) The first part of the present invention adopts a multi-dedicated sensor collaborative design, which can accurately collect multi-dimensional data in the extreme environment of high dust concentration and temperature and pressure fluctuation in thermal power plants, avoids the problem of accuracy decay of traditional sensors, and breaks through the limitations of traditional single parameter collection by collecting multi-dimensional data, providing complete and accurate data support for subsequent analysis.

[0025] (2) The second part of the present invention: Combined with the local database, it accurately identifies and locates obstacles in the dense stainless steel pipe network of thermal power plants, avoids misjudgment of complex structures, and can simultaneously detect multiple types of damage such as mechanical deformation, cracks, and high-temperature oxidation. It is more comprehensive than traditional single damage detection. The risk level is integrated into the three-dimensional model through color rendering, which intuitively presents the risk distribution and allows staff to quickly locate high-risk areas. The constructed three-dimensional digital model provides accurate geometric reference for subsequent robot path planning and detection decisions, which significantly improves the practical guidance value of the analysis results.

[0026] (3) The third part of the present invention: when planning the path, it avoids obstacles and high dust concentration areas, matches the detection mode as needed, adjusts the operating status in real time to ensure continuous operation, and can also assess the degradation trend of dense stainless steel pipe network in thermal power plant, provide support for preventive maintenance, reduce failure risk, and improve the safety of pipe flaw detection robot and the forward-looking nature of maintenance of dense stainless steel pipe network in thermal power plant. Attached Figure Description

[0027] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0028] Figure 1 This is a schematic diagram of the system modules of the present invention.

[0029] Figure 2 This is a schematic diagram of the method flow of the present invention. Detailed Implementation

[0030] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0031] Reference Figure 1 As shown, the first aspect of the present invention provides a pipeline flaw detection robot control system, including: a data acquisition module, a data analysis module, a data processing module, and a local database.

[0032] It should be noted that the data acquisition module is connected to the data analysis module, the data analysis module is connected to the data processing module, and the local database is connected to the data acquisition module, the data analysis module, and the data processing module.

[0033] The data acquisition module is used to acquire internal environmental parameters, structural feature parameters, and pipeline flaw detection robot operating status parameters of the dense stainless steel pipe network in thermal power plants. The environmental parameters include temperature gradient, air pressure change, and dust concentration. The structural feature parameters include pipe diameter, curvature, and surface roughness. The pipeline flaw detection robot operating status parameters include real-time attitude angle and movement speed.

[0034] It should be noted that the dense stainless steel pipe network of a thermal power plant refers to a complex system in a thermal power plant in which a large number of single pipes are closely arranged and connected in space through fittings such as elbows, tees, valves, and flanges.

[0035] It should be noted that the temperature is measured by a temperature sensor, the air pressure change is measured by a high-precision air pressure sensor, the dust concentration is obtained by an optical sensor, the pipe diameter and curvature are obtained by LiDAR scanning, the surface roughness is obtained by high-definition images of the inner wall surface captured by a high-definition vision sensor, the real-time attitude angle of the pipe inspection robot is obtained by its integrated inertial measurement unit, and the movement speed is measured in real time by an encoder installed on the drive motor.

[0036] The data analysis module is used to identify the types of inherent structural obstacles within the dense stainless steel pipe network of a thermal power plant and locate their spatial positions, detect the damage characteristics of the dense stainless steel pipe network of a thermal power plant, assess the safety operation risk level of the dense stainless steel pipe network of a thermal power plant, and comprehensively generate a three-dimensional digital model of the dense stainless steel pipe network of a thermal power plant.

[0037] In a specific embodiment of the present invention, the method for identifying the type of inherent structural obstacle inside the dense stainless steel pipe network of a thermal power plant and locating its spatial position is as follows: point cloud data of the interior of the dense stainless steel pipe network of the thermal power plant is obtained by scanning with a laser radar installed on a pipe flaw detection robot to construct a three-dimensional contour. When the pipe flaw detection robot identifies the inherent structure inside the dense stainless steel pipe network of the thermal power plant, it matches the corresponding obstacle type stored in the local database according to the obstacle type corresponding to the inherent structure inside the dense stainless steel pipe network of the thermal power plant, and directly locates the spatial position of the detected inherent structural obstacle inside the dense stainless steel pipe network of the thermal power plant through the self-localization data of the pipe flaw detection robot.

[0038] It should be noted that acquiring point cloud data of the dense stainless steel pipe network inside the thermal power plant to construct a three-dimensional profile is to provide a unified geometric reference framework for the accurate spatial positioning of obstacles and subsequent obstacle avoidance paths.

[0039] Examples of obstruction types include flanges, pipe supports and hangers, and elbows that change the direction of pipes.

[0040] It should be noted that the self-localization data of the pipeline flaw detection robot refers to the core information set that the pipeline flaw detection robot perceives in real time through its internal sensors to accurately describe its own position, attitude and motion state in space.

[0041] In a specific embodiment of the present invention, the method for detecting the damage characteristics of the dense stainless steel pipe network of a thermal power plant is as follows: extract the measured values ​​of pipe diameter and bending arc from the point cloud data inside the dense stainless steel pipe network of the thermal power plant, and compare them with the corresponding pipe diameter and bending arc in the original point cloud data of the dense stainless steel pipe network of the thermal power plant. If the difference between any measured pipe diameter and the original pipe diameter exceeds a preset diameter deformation threshold, or the difference between any measured bending arc and the original bending arc exceeds a preset arc deformation threshold, then it is determined that the dense stainless steel pipe network of the thermal power plant has mechanical damage characteristics.

[0042] By using ultrasonic sensors and high-definition vision sensors installed on the pipeline flaw detection robot, ultrasonic echo signals and images of the inner wall surface of the pipeline are acquired simultaneously. When the echo amplitude in the ultrasonic signal exceeds the preset crack amplitude threshold and crack features appear in the inner wall surface image of the pipeline, it is determined that the dense stainless steel pipeline network of the thermal power plant has crack damage features.

[0043] When the wall thickness reduction measured by ultrasonic echo signal exceeds the preset high-temperature oxidation thickness threshold and the surface roughness of the pipe exceeds the preset surface roughness tolerance value, it is determined that the dense stainless steel pipe network of the thermal power plant has high-temperature oxidation damage characteristics.

[0044] It should be noted that the original point cloud data of the dense stainless steel pipe network of the thermal power plant refers to the point cloud data of the original dense stainless steel pipe network of the thermal power plant in the design drawings.

[0045] For example, the surface image of the pipe shows crack features, such as continuous linear fracture texture or branching lines on the inner wall surface of the pipe.

[0046] In one specific embodiment, the wall thickness reduction obtained by measuring the ultrasonic echo signal is specifically measured as follows: when the ultrasonic wave propagates in the dense stainless steel pipe network of a thermal power plant, it generates reflected echoes. By accurately measuring the time interval between the transmitted pulse and the returned echo, multiplying it by the known propagation speed of the ultrasonic wave in the dense stainless steel pipe network of the thermal power plant, and dividing by the number of reflected echoes, the actual wall thickness at that location of the pipe can be calculated. By comparing the measured wall thickness with the original design wall thickness of the pipe, the difference is the wall thickness reduction.

[0047] In a specific embodiment of the present invention, the method for assessing the safety operation risk level of the dense stainless steel pipe network of a thermal power plant is as follows: based on the damage characteristics of the dense stainless steel pipe network of the thermal power plant, the safety operation risk level of the dense stainless steel pipe network of the thermal power plant is divided into three levels.

[0048] If mechanical damage characteristics, crack damage characteristics, and high-temperature oxidation damage characteristics are detected simultaneously in the dense stainless steel pipe network of a thermal power plant, the safety operation risk level of the dense stainless steel pipe network of the thermal power plant is determined to be Level 1.

[0049] If any two of the following characteristics are detected in the dense stainless steel pipe network of a thermal power plant: mechanical damage, crack damage, or high-temperature oxidation damage, the safety operation risk level of the dense stainless steel pipe network of the thermal power plant is determined to be Level II.

[0050] If any one of the mechanical damage characteristics, crack damage characteristics, or high-temperature oxidation damage characteristics is detected in the dense stainless steel pipe network of a thermal power plant, the safety operation risk level of the dense stainless steel pipe network of the thermal power plant is determined to be Level III.

[0051] It should be noted that the Level 1 safety operation risk level of dense stainless steel pipe networks in thermal power plants is higher than the Level 2 safety operation risk level, and the Level 2 safety operation risk level of dense stainless steel pipe networks in thermal power plants is higher than the Level 3 safety operation risk level.

[0052] In a specific embodiment of the present invention, the method for comprehensively generating a three-dimensional digital model of a dense stainless steel pipe network in a thermal power plant is as follows: the types and spatial location information of internal structural obstacles in the dense stainless steel pipe network of the thermal power plant identified by the pipeline flaw detection robot, the spatial distribution and geometric deformation of the detected mechanical damage features, the extension path of crack damage features, the area distribution of high-temperature oxidation damage features, the wall thickness reduction and surface roughness are mapped to the constructed three-dimensional contour framework according to spatial coordinates. The safety operation risk level of the dense stainless steel pipe network of the thermal power plant is rendered by color, and environmental parameters are introduced into the three-dimensional contour. Finally, a three-dimensional digital model of the dense stainless steel pipe network of the thermal power plant integrating geometric structure, damage features, safety operation level and environmental parameters is generated.

[0053] It should be noted that the geometric deformation of mechanical damage characteristics refers to the difference between the measured values ​​and the original values ​​of the pipe diameter and curvature.

[0054] It should be noted that the spatial distribution of mechanical damage features and high-temperature oxidation damage features is obtained directly from the self-localization data of the pipeline flaw detection robot, while the extension path of crack damage features is obtained from the image of the inner wall surface of the pipeline.

[0055] It should be noted that the spatial coordinate mapping adopts a real-time registration algorithm based on feature point matching, and ensures the consistency of multi-source data in the spatiotemporal dimension through a timestamp synchronization mechanism. This algorithm is mature and will not be elaborated here.

[0056] The geometric structure refers to the constructed three-dimensional outline framework that can accurately reflect the true physical form inside the dense stainless steel pipe network of a thermal power plant.

[0057] For example, the safety operation risk level of the dense stainless steel pipe network in a thermal power plant can be rendered by color, such as rendering the first-level safety operation risk level in red, the second-level safety operation risk level in yellow, and the third-level safety operation risk level in green.

[0058] The data processing module is used to generate obstacle avoidance paths for the pipeline flaw detection robot based on the 3D digital model of the dense stainless steel pipe network of the thermal power plant, match the optimal detection mode of the pipeline flaw detection robot, dynamically adjust the operating status of the pipeline flaw detection robot according to environmental parameters, and evaluate the performance degradation trend of the 3D dense stainless steel pipe network of the thermal power plant.

[0059] In a specific embodiment of the present invention, the method for generating the obstacle avoidance path of the pipeline flaw detection robot is as follows: the types of obstacles and their spatial locations inside the pipeline network are extracted using a three-dimensional digital model of the dense stainless steel pipeline network of a thermal power plant. A path planning algorithm is used to avoid the extracted types of obstacles and their spatial locations inside the dense stainless steel pipeline network of the thermal power plant by taking the current location of the pipeline flaw detection robot as the starting point and the detection target point as the ending point. At the same time, if the dust concentration in a certain area inside the dense stainless steel pipeline network of the thermal power plant exceeds the preset dust concentration observation threshold of the optical sensor, the area must be avoided during the global path planning.

[0060] It should be noted that path planning algorithms are a type of core artificial intelligence algorithm used to autonomously calculate safe and efficient travel routes from the starting point to the destination in environments with obstacles, thereby ensuring that pipeline flaw detection robots can autonomously and safely complete inspection tasks. This algorithm is mature and will not be elaborated on here.

[0061] It should be noted that high dust concentrations are avoided when planning the route because high dust environments pose a threat to the mechanical structure and operational stability of the pipeline inspection robot, reducing the reliability of the inspection task, the accuracy of the data, and the safety of the robot equipment.

[0062] In a specific embodiment of the present invention, the method for matching the optimal detection mode of the pipeline flaw detection robot is as follows: based on the obstacle avoidance path of the pipeline flaw detection robot, if the safety operation risk level of the dense stainless steel pipeline network of the thermal power plant is level one, then the optimal detection mode of the pipeline flaw detection robot is the fine detection mode; if the safety operation risk level of the dense stainless steel pipeline network of the thermal power plant is level two, then the optimal detection mode of the pipeline flaw detection robot is the standard detection mode; if the safety operation risk level of the dense stainless steel pipeline network of the thermal power plant is level three, then the optimal detection mode of the pipeline flaw detection robot is the rapid general survey mode.

[0063] It should be noted that the moving speed of the pipeline flaw detection robot in fine inspection mode is less than that in standard inspection mode, and the moving speed of the pipeline flaw detection robot in standard inspection mode is less than that in rapid survey mode.

[0064] It should be noted that the fine inspection mode uses a high-frequency ultrasonic sensor and a high-definition vision sensor installed on the pipeline flaw detection robot to simultaneously scan the obstacle avoidance path with millimeter-level resolution. The standard inspection mode uses a medium-frequency ultrasonic sensor and an infrared thermal imaging sensor installed on the pipeline flaw detection robot to collaboratively scan the obstacle avoidance path. The rapid survey mode uses a lidar and a basic vision sensor installed on the pipeline flaw detection robot to quickly scan the macroscopic shape of the obstacle avoidance path.

[0065] For example, the fine inspection mode strictly limits the movement speed of the pipeline flaw detection robot to 0.1 m / s to ensure ultra-high data density and accuracy, the standard inspection mode balances inspection efficiency and detail capture capability with the pipeline flaw detection robot at a speed of 0.3 m / s, and the rapid survey mode increases the speed of the pipeline flaw detection robot to 0.5 m / s to achieve efficient coverage.

[0066] In a specific embodiment of the present invention, the method for dynamically adjusting the operating state of the pipeline flaw detection robot according to environmental parameters is as follows: During the obstacle avoidance path travel of the generated pipeline flaw detection robot, the temperature gradient, air pressure change, and dust concentration of the dense stainless steel pipelines in the thermal power plant are acquired in real time. When the real-time dust concentration exceeds the preset dust concentration observation threshold of the optical sensor, the movement speed is immediately reduced to a safe limit and the cleaning device is activated. When the temperature gradient of the dense stainless steel pipelines in the thermal power plant exceeds the preset warning temperature gradient value, causing local overheating of the pipeline flaw detection robot, the real-time attitude angle of the pipeline flaw detection robot is adjusted to dissipate heat from the local overheated area. When the air pressure change of the dense stainless steel pipelines in the thermal power plant exceeds the preset air pressure change amplitude threshold during the detection period, it affects the optical sensor of the pipeline flaw detection robot and causes measurement error. The real-time attitude angle of the pipeline flaw detection robot is adjusted to compensate for the measurement error caused by the air pressure change.

[0067] It should be noted that path planning is to avoid the pipeline flaw detection robot from entering known areas with high dust concentrations, while operational status adjustment is to immediately adjust the operational status to ensure the safety of the pipeline flaw detection robot when it suddenly encounters high dust concentrations.

[0068] It should be noted that the cleaning device is activated to ensure that the sensors of the pipeline flaw detection robot can be used normally and to continue to inspect the dense stainless steel pipeline network of the thermal power plant.

[0069] In one specific embodiment, the real-time attitude angle of the pipeline flaw detection robot is adjusted to compensate for the measurement error caused by air pressure changes. The specific method is as follows: the air pressure change inside the pipeline is monitored in real time by a high-precision air pressure sensor. When the air pressure change of the dense stainless steel pipeline in the thermal power plant exceeds the preset air pressure change amplitude threshold during the detection period, the required real-time attitude angle adjustment amount is calculated based on the air pressure-refractive index physical model. Then, the drive mechanism of the pipeline flaw detection robot is controlled to make precise fine adjustments. By changing the observation angle of the optical sensor, the detection beam is directed at the inner wall surface of the pipeline at a closer vertical angle, thereby reducing the optical path bending effect caused by air pressure changes.

[0070] It should be noted that the pressure-refractive index physical model is a mature pre-built calculation model based on classical physics principles, in which known and stable physical laws are pre-programmed and embedded. This model correlates the refractive index change of the gas medium with the pressure parameter through a strict functional relationship. The application of this model is already quite mature, and will not be elaborated on here.

[0071] For example, the real-time attitude angle of the pipeline flaw detection robot is adjusted to compensate for measurement errors caused by air pressure changes. For instance, when the air pressure change of the dense stainless steel pipelines in a thermal power plant exceeds the preset air pressure change amplitude threshold during the detection period, causing the laser rangefinder beam path to deviate by 0.1 degrees, the required real-time attitude angle adjustment is calculated to be 0.1 degrees based on the air pressure-refractive index physical model. The system then uses the inertial measurement unit to precisely adjust the yaw angle of the pipeline flaw detection robot by 0.1 degrees so that the beam is re-perpendicularly incident on the target area. At this time, the inertial measurement unit provides real-time feedback of attitude data to ensure adjustment accuracy, ultimately achieving active compensation for measurement errors.

[0072] In a specific embodiment of the present invention, the method for evaluating the performance degradation trend of a three-dimensional dense stainless steel pipe network in a thermal power plant is as follows: based on the damage feature data in the digital model of the three-dimensional dense stainless steel pipe network in the current inspection cycle, the data is compared with the three-dimensional digital model of the same dense stainless steel pipe network in the previous inspection cycle stored in the local database. If the expansion rate of any damage feature between the current inspection cycle and the previous inspection cycle exceeds its preset warning degradation expansion rate threshold, then the performance degradation trend of the three-dimensional dense stainless steel pipe network in the thermal power plant is determined to be rapid degradation; otherwise, the performance degradation trend of the three-dimensional dense stainless steel pipe network in the thermal power plant is slow degradation.

[0073] The expansion rate refers to the ratio of the change in the area of ​​the damaged feature to the time interval between two detection cycles.

[0074] It should be noted that the core objective of performance degradation trend assessment in the pipeline flaw detection robot control system is to monitor the natural expansion of damage features in order to assess the long-term effects of material aging and environmental oxidation.

[0075] Reference Figure 2 As shown, the second aspect of the present invention provides a control method for a pipeline flaw detection robot control system, including step 1. Data acquisition: acquiring internal environmental parameters, structural characteristic parameters, and pipeline flaw detection robot operating status parameters of a dense stainless steel pipeline network in a thermal power plant. The environmental parameters include temperature gradient, air pressure change, and dust concentration. The structural characteristic parameters include pipe diameter, curvature, and surface roughness. The pipeline flaw detection robot operating status parameters include real-time attitude angle and movement speed.

[0076] Step 2. Data Analysis: Identify the types of inherent structural obstacles within the dense stainless steel pipe network of the thermal power plant and locate their spatial positions; detect the damage characteristics of the dense stainless steel pipe network of the thermal power plant; assess the safety operation risk level of the dense stainless steel pipe network of the thermal power plant; and comprehensively generate a three-dimensional digital model of the dense stainless steel pipe network of the thermal power plant.

[0077] Step 3. Data Processing: Generate obstacle avoidance path for the pipeline flaw detection robot based on the 3D digital model of the dense stainless steel pipe network of the thermal power plant, match the optimal detection mode of the pipeline flaw detection robot, dynamically adjust the operating status of the pipeline flaw detection robot according to environmental parameters, and evaluate the performance degradation trend of the 3D dense stainless steel pipe network of the thermal power plant.

[0078] The above content is merely an example and illustration of the concept of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described, or use similar methods to replace them, as long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, and all such modifications and additions should fall within the protection scope of the present invention.

Claims

1. A control system for a pipeline flaw detection robot, characterized in that, include: Data acquisition module: used to acquire internal environmental parameters, structural feature parameters and pipeline flaw detection robot operating status parameters of dense stainless steel pipe network in thermal power plant. The environmental parameters include temperature gradient, air pressure change and dust concentration. The structural feature parameters include pipe diameter, curvature and surface roughness. The pipeline flaw detection robot operating status parameters include real-time attitude angle and movement speed. Data analysis module: used to identify the types of inherent structural obstacles inside the dense stainless steel pipe network of thermal power plants and locate their spatial positions, detect the damage characteristics of the dense stainless steel pipe network of thermal power plants, assess the safety operation risk level of the dense stainless steel pipe network of thermal power plants, and comprehensively generate a three-dimensional digital model of the dense stainless steel pipe network of thermal power plants. Data processing module: Used to generate obstacle avoidance path for pipeline flaw detection robot based on 3D digital model of dense stainless steel pipe network in thermal power plant, match optimal detection mode of pipeline flaw detection robot, dynamically adjust the operating status of pipeline flaw detection robot according to environmental parameters, and evaluate the performance degradation trend of dense stainless steel pipe network in 3D thermal power plant.

2. The pipeline flaw detection robot control system according to claim 1, characterized in that, The specific method for identifying the types of inherent structural obstacles within the dense stainless steel pipe network of a thermal power plant and locating their spatial positions is as follows: Point cloud data of the interior of the dense stainless steel pipe network in a thermal power plant is acquired by scanning with a lidar mounted on a pipe flaw detection robot to construct a three-dimensional profile. When the pipe flaw detection robot identifies the inherent structure inside the dense stainless steel pipe network of the thermal power plant, it matches the obstacle type stored in the local database with the obstacle type corresponding to the inherent structure inside the dense stainless steel pipe network of the thermal power plant, and directly locates the spatial position of the detected inherent structure obstacle inside the dense stainless steel pipe network of the thermal power plant through the self-localization data of the pipe flaw detection robot.

3. The pipeline flaw detection robot control system according to claim 2, characterized in that, The specific method for detecting the damage characteristics of the dense stainless steel pipe network in a thermal power plant is as follows: The measured values ​​of pipe diameter and curvature are extracted from the point cloud data of the dense stainless steel pipe network in the thermal power plant. These values ​​are then compared with the corresponding pipe diameter and curvature in the original point cloud data of the dense stainless steel pipe network in the thermal power plant. If the difference between any measured pipe diameter and the original pipe diameter exceeds the preset diameter deformation threshold, or the difference between any measured curvature and the original curvature exceeds the preset curvature deformation threshold, then it is determined that the dense stainless steel pipe network in the thermal power plant has mechanical damage characteristics. By using ultrasonic sensors and high-definition vision sensors installed on the pipeline flaw detection robot, ultrasonic echo signals and images of the inner wall surface of the pipeline are acquired simultaneously. When the echo amplitude in the ultrasonic signal exceeds the preset crack amplitude threshold and crack features appear in the inner wall surface image of the pipeline, it is determined that the dense stainless steel pipe network of the thermal power plant has crack damage features. When the wall thickness reduction measured by ultrasonic echo signal exceeds the preset high-temperature oxidation thickness threshold and the surface roughness of the pipe exceeds the preset surface roughness tolerance value, it is determined that the dense stainless steel pipe network of the thermal power plant has high-temperature oxidation damage characteristics.

4. The pipeline flaw detection robot control system according to claim 3, characterized in that, The specific method for assessing the safety operation risk level of dense stainless steel pipe networks in thermal power plants is as follows: Based on the damage characteristics of dense stainless steel pipe networks in thermal power plants, the safe operation risk level of dense stainless steel pipe networks in thermal power plants is divided into three levels. If mechanical damage characteristics, crack damage characteristics, and high-temperature oxidation damage characteristics are detected simultaneously in the dense stainless steel pipe network of a thermal power plant, the safety operation risk level of the dense stainless steel pipe network of the thermal power plant is determined to be Level 1. If any two of the following characteristics are detected in the dense stainless steel pipe network of a thermal power plant: mechanical damage, crack damage, or high-temperature oxidation damage, the safety operation risk level of the dense stainless steel pipe network of the thermal power plant is determined to be Level II. If any one of the mechanical damage characteristics, crack damage characteristics, or high-temperature oxidation damage characteristics is detected in the dense stainless steel pipe network of a thermal power plant, the safety operation risk level of the dense stainless steel pipe network of the thermal power plant is determined to be Level III.

5. A pipeline flaw detection robot control system according to claim 4, characterized in that, The specific method for generating a comprehensive three-dimensional digital model of the dense stainless steel pipe network of a thermal power plant is as follows: The pipeline flaw detection robot identifies the types and spatial locations of obstacles in the internal structure of the dense stainless steel pipe network of a thermal power plant, as well as the spatial distribution and geometric deformation of the detected mechanical damage features, the extension path of crack damage features, the area distribution of high-temperature oxidation damage features, the wall thickness reduction, and the surface roughness. These are mapped onto a constructed three-dimensional contour framework using spatial coordinates. The safety operation risk level of the dense stainless steel pipe network of the thermal power plant is rendered by color, and environmental parameters are introduced into the three-dimensional contour. Finally, a three-dimensional digital model of the dense stainless steel pipe network of the thermal power plant is generated, integrating geometric structure, damage features, safety operation level, and environmental parameters.

6. The pipeline flaw detection robot control system according to claim 5, characterized in that, The specific method for generating the obstacle avoidance path for the pipeline flaw detection robot is as follows: By extracting the types and spatial locations of obstacles within the dense stainless steel pipe network of a 3D thermal power plant using a digital model, a path planning algorithm is used to avoid these obstacles by starting from the current location of the pipe inspection robot and ending at the target point. Furthermore, if the dust concentration in a certain area of ​​the dense stainless steel pipe network exceeds the preset dust concentration observation threshold of the optical sensor, that area must be avoided during global path planning.

7. A pipeline flaw detection robot control system according to claim 6, characterized in that, The specific method for matching the optimal detection mode of the pipeline flaw detection robot is as follows: Based on the obstacle avoidance path of the pipeline flaw detection robot, if the safety operation risk level of the dense stainless steel pipeline network in the thermal power plant is Level 1, the optimal detection mode for the pipeline flaw detection robot is the fine detection mode; if the safety operation risk level of the dense stainless steel pipeline network in the thermal power plant is Level 2, the optimal detection mode for the pipeline flaw detection robot is the standard detection mode; and if the safety operation risk level of the dense stainless steel pipeline network in the thermal power plant is Level 3, the optimal detection mode for the pipeline flaw detection robot is the rapid general survey mode.

8. The pipeline flaw detection robot control system according to claim 7, characterized in that, The specific method for dynamically adjusting the operating status of the pipeline flaw detection robot based on environmental parameters is as follows: During the obstacle avoidance path of the generated pipeline flaw detection robot, the temperature gradient, air pressure change, and dust concentration of the dense stainless steel pipelines in the thermal power plant are acquired in real time. When the real-time dust concentration exceeds the preset dust concentration observation threshold of the optical sensor, the movement speed is immediately reduced to a safe limit and the cleaning device is activated. When the temperature gradient of the dense stainless steel pipelines in the thermal power plant exceeds the preset warning temperature gradient value, causing local overheating of the pipeline flaw detection robot, the real-time attitude angle of the pipeline flaw detection robot is adjusted to dissipate heat from the local overheated area. When the air pressure change of the dense stainless steel pipelines in the thermal power plant exceeds the preset air pressure change amplitude threshold during the detection period, it affects the optical sensor of the pipeline flaw detection robot and causes measurement error. The real-time attitude angle of the pipeline flaw detection robot is adjusted to compensate for the measurement error caused by the air pressure change.

9. A pipeline flaw detection robot control system according to claim 5, characterized in that, The specific method for assessing the performance degradation trend of dense stainless steel pipe networks in three-dimensional thermal power plants is as follows: Damage feature data in the 3D digital model of the dense stainless steel pipe network of a thermal power plant in the current inspection cycle is compared with the 3D digital model of the same dense stainless steel pipe network of a thermal power plant in the previous inspection cycle when it was not repaired, which is stored in the local database. If the expansion rate of any damage feature between the current inspection cycle and the previous inspection cycle exceeds its preset warning degradation expansion rate threshold, the performance degradation trend of the 3D dense stainless steel pipe network of the thermal power plant is determined to be rapid degradation, otherwise the performance degradation trend of the 3D dense stainless steel pipe network of the thermal power plant is slow degradation.

10. A control method for implementing the pipeline flaw detection robot control system according to any one of claims 1-9, characterized in that, include: Step 1. Data Acquisition: Obtain internal environmental parameters, structural feature parameters, and pipeline flaw detection robot operating status parameters of the dense stainless steel pipe network in the thermal power plant. The environmental parameters include temperature gradient, air pressure change, and dust concentration. The structural feature parameters include pipe diameter, curvature, and surface roughness. The pipeline flaw detection robot operating status parameters include real-time attitude angle and movement speed. Step 2. Data Analysis: Identify the types of inherent structural obstacles within the dense stainless steel pipe network of the thermal power plant and locate their spatial positions; detect the damage characteristics of the dense stainless steel pipe network of the thermal power plant; assess the safety operation risk level of the dense stainless steel pipe network of the thermal power plant; and comprehensively generate a three-dimensional digital model of the dense stainless steel pipe network of the thermal power plant. Step 3. Data Processing: Generate obstacle avoidance path for the pipeline flaw detection robot based on the 3D digital model of the dense stainless steel pipe network of the thermal power plant, match the optimal detection mode of the pipeline flaw detection robot, dynamically adjust the operating status of the pipeline flaw detection robot according to environmental parameters, and evaluate the performance degradation trend of the 3D dense stainless steel pipe network of the thermal power plant.

Images