Underwater structure defect detection knocking auscultation system and detection method

Abstract

The invention discloses an underwater structure defect detection knocking auscultation system and a detection method, and the system comprises an underwater operation unit which comprises a knocking device used for executing a set knocking action; the multi-channel acoustic signal acquisition module is used for acquiring underwater acoustic wave signals and / or underwater structure vibration signals; the first control and communication module is used for receiving an issued operation instruction, uploading a working state and acquiring information; the overwater control and analysis unit comprises a second control and communication module which is used for receiving the working state and the acquisition information of the underwater operation unit and issuing an operation instruction; the signal processing and intelligent analysis module is used for processing and analyzing the acquired information and realizing underwater structure defect detection; and the man-machine interaction module is used for setting knocking parameters and displaying an underwater structure defect detection result. According to the invention, standardization of knocking actions and digital acquisition and intelligent analysis of knocking signals can be realized, and objectivity, accuracy and efficiency of detection are improved.

Description

Technical Field

[0001] This invention relates to the field of underwater engineering structure inspection technology, and in particular to an underwater structural defect detection system and method using a percussion auscultation. Background Technology

[0002] During operation, underwater structures of hydraulic engineering projects, such as reservoir slopes, dam bodies, energy dissipation structures, and guide walls, are constantly immersed in and eroded underwater environments, inevitably leading to cracks and erosion. Failure to regularly inspect the safety of these underwater structures will threaten the safe operation of the hydropower station. The inspection of underwater components of hydraulic engineering projects has always been a weak link in hydropower plants. The operational status of these underwater components is a blind spot and a pain point in the safe production of hydropower plants. Because underwater structures are important and concealed, any damage could lead to serious safety accidents such as dam failure and flooding.

[0003] Regular inspection of underwater structures is crucial for ensuring their safe operation. The percussion test is a traditional and effective non-destructive testing method that analyzes the sound signals generated when the structure is struck to determine the presence of internal defects such as peeling, voids, and corrosion.

[0004] However, traditional underwater percussion testing relies primarily on divers using simple handheld tools (such as hammers), which has the following significant drawbacks: 1) High influence of human factors: Divers' striking force, frequency, and location are difficult to maintain consistently, leading to highly subjective, poor repeatability, and low reliability of the test results. 2) Difficult signal acquisition: The complex underwater noise environment makes it difficult for divers to accurately distinguish subtle differences in sound by hearing alone, easily resulting in missed detections or misjudgments. 3) Low operational efficiency: Manual percussion covers a small area, resulting in slow testing speed, and comprehensive testing of large structures is time-consuming and labor-intensive. 4) Difficulty in data recording and analysis: The lack of digital recording and subsequent analysis methods for percussion sound signals hinders historical data comparison and defect trend assessment.

[0005] Therefore, there is an urgent need for an underwater structural defect detection system and method that can standardize the tapping action, digitally acquire and intelligently analyze the tapping signal, and improve the objectivity, accuracy, efficiency and applicability of the detection. Summary of the Invention

[0006] To address the shortcomings of existing technologies, this invention provides an underwater structural defect detection system and method using a percussion auscultation technique, which standardizes the percussion action, digitizes and intelligently analyzes the percussion signals, and improves the objectivity, accuracy, efficiency, and applicability of the detection.

[0007] In the first aspect, an underwater structural defect detection percussion system is provided, including an underwater operation unit and a surface control and analysis unit that is communicatively connected to it;

[0008] The underwater operation unit includes:

[0009] A striking device used to perform a pre-set striking action;

[0010] A multi-channel acoustic signal acquisition module is used to acquire underwater acoustic wave signals and / or underwater structural vibration signals;

[0011] The first control and communication module is electrically connected to the striking device and the multi-channel acoustic signal acquisition module, and is used to receive the operation instructions issued by the surface control and analysis unit and upload the working status and acquisition information of the underwater operation unit.

[0012] The above-water control and analysis unit includes:

[0013] The second control and communication module is used to receive the working status and collected information of the underwater operation unit, and to issue operation commands to the underwater operation unit.

[0014] The signal processing and intelligent analysis module is electrically connected to the second control and communication module and is used to process and analyze the collected information to realize underwater structural defect detection.

[0015] The human-machine interaction module is electrically connected to the second control and communication module and the signal processing and intelligent analysis module. It is used to set the tapping parameters, display the working status and collected information of the underwater operation unit, and display the underwater structural defect detection results.

[0016] Furthermore, the striking device includes:

[0017] The shell, whose interior forms a sealed cavity;

[0018] The drive mechanism is disposed within the housing;

[0019] The striking actuator is connected to the drive mechanism and is used to perform reciprocating striking motion along a preset trajectory under the control of the drive mechanism.

[0020] Furthermore, the multi-channel acoustic signal acquisition module includes at least one hydrophone and / or one contact vibration sensor.

[0021] Furthermore, the underwater operation unit also includes:

[0022] The positioning and attitude sensing module, electrically connected to the first control and communication module, includes a depth sensor and a three-dimensional electronic compass / inertial measurement unit, used to acquire the position of the striking device underwater and the normal attitude of the striking surface in real time.

[0023] Furthermore, the signal processing and intelligent analysis module includes:

[0024] The preprocessing submodule is used to filter, reduce noise, and normalize the acquired underwater acoustic signals and / or underwater structural vibration signals.

[0025] The feature extraction submodule is used to extract time-domain and frequency-domain features from the preprocessed signal to form a feature vector.

[0026] The intelligent defect identification submodule is used to input feature vectors into a pre-trained underwater structure defect identification model based on machine learning, and output the defect type and corresponding probability of the underwater structure.

[0027] Furthermore, the underwater operation unit is integrated into the end of the robotic arm of the underwater robot and is carried and moved by the underwater robot.

[0028] Secondly, a method for detecting underwater structural defects is provided, which is implemented using the underwater structural defect detection percussion system as described above, and includes the following steps:

[0029] Testing planning: Set the tapping parameters and path in the surface control and analysis unit;

[0030] Tool deployment and positioning: Position the underwater operation unit to the point to be inspected;

[0031] Simultaneous acquisition of striking and signal: The striking device is controlled to strike, and the signal is simultaneously acquired through a multi-channel acoustic signal acquisition module;

[0032] Signal preprocessing and feature extraction: The signals acquired by the multi-channel acoustic signal acquisition module are preprocessed and features are extracted to obtain feature vectors;

[0033] Intelligent defect identification and localization: Input the feature vector into the trained underwater structure defect identification model based on machine learning model, output the defect type and corresponding probability of the underwater structure, and associate it with the location information;

[0034] Results visualization: The distribution of defects is displayed on the human-computer interaction module of the surface control and analysis unit.

[0035] Furthermore, the signals acquired by the multi-channel acoustic signal acquisition module include underwater acoustic wave signals and underwater structural vibration signals.

[0036] Furthermore, the underwater structure defect identification model is obtained through the following method:

[0037] Signals were collected from underwater structures struck under various known conditions, and features were extracted and labeled to obtain a sample dataset; the various known conditions include various defect types and defect-free states;

[0038] A machine learning model was trained based on a sample dataset to obtain an underwater structure defect identification model.

[0039] Furthermore, when visualizing the results, the distribution and severity of defects are displayed intuitively in the form of color coding or charts, and a structured inspection report is generated.

[0040] This invention proposes an underwater structural defect detection system and method using a tapping device to stably tap the wall of the underwater structure under test. A multi-channel acoustic signal acquisition module collects underwater sound wave signals and / or underwater structural vibration signals. The collected signals are then processed and analyzed to detect underwater structural defects. This system standardizes the tapping action, digitizes the tapping signals, and enables intelligent analysis, improving the objectivity, accuracy, efficiency, and applicability of the detection. Attached Figure Description

[0041] 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.

[0042] Figure 1 This is a schematic diagram of the architecture of an underwater structural defect detection percussion auscultation system provided in an embodiment of the present invention;

[0043] Figure 2 This is a schematic diagram of the underwater operation unit structure provided in an embodiment of the present invention;

[0044] Figure 3 This is a schematic diagram of an underwater robot structure equipped with an underwater operation unit provided in an embodiment of the present invention;

[0045] Figure 4 This is a flowchart of an underwater structural defect detection method provided by an embodiment of the present invention. Detailed Implementation

[0046] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be described in detail below. Obviously, the described embodiments are merely some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other implementation methods obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0047] In the description of this invention, it should be understood that the terms "upper," "lower," "front," "rear," "left," "right," "top," "bottom," "inner," "outer," "center," "longitudinal," "lateral," "vertical," and "horizontal," etc., indicating orientation or positional relationships, are based on the orientation or positional relationships shown in the accompanying drawings and are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. When an element is referred to as being "fixed to" another element, it can be directly on the other element or there may be an intermediate element. When an element is referred to as being "connected" to another element, it can be directly connected to the other element or there may be an intermediate element present.

[0048] It should be noted that in the description of this invention, the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance or order. Furthermore, in the description of this invention, unless otherwise stated, "a plurality of" means at least two.

[0049] like Figure 1 As shown, this embodiment provides an underwater structural defect detection percussion system, including an underwater operation unit and a surface control and analysis unit that are communicatively connected to it; the underwater operation unit and the surface control and analysis unit can be connected via umbilical cable or wireless communication.

[0050] Specifically, the underwater operation unit includes:

[0051] A striking device used to perform a pre-set striking action;

[0052] A multi-channel acoustic signal acquisition module is used to acquire underwater acoustic wave signals and / or underwater structural vibration signals;

[0053] The first control and communication module is electrically connected to the striking device and the multi-channel acoustic signal acquisition module. It is used to receive operation commands issued by the surface control and analysis unit (for controlling the striking device to generate striking with specific force and frequency) and to upload the working status and acquisition information of the underwater operation unit.

[0054] More specifically, the striking device includes:

[0055] The pressure-resistant and waterproof shell has a sealed cavity inside. As the external protective shell of the underwater operation unit, the pressure-resistant and waterproof shell can ensure dynamic sealing in deep water environment and prevent the internal electrical modules from short-circuiting when exposed to water.

[0056] The drive mechanism is disposed within the housing;

[0057] The striking actuator is connected to the drive mechanism and is used to perform reciprocating striking motion along a preset trajectory under the control of the drive mechanism.

[0058] The drive mechanism and the striking actuator can be electromagnetically driven or driven by a motor-driven cam / crank connecting rod.

[0059] like Figure 2 As shown, this is an electromagnetically driven striking device. The driving mechanism uses a tubular electromagnetic coil 4, and the striking actuator includes a connecting rod 6, a striking hammer 3 located at one end of the connecting rod 6, and a return spring 2 sleeved on the connecting rod 6. The other end of the connecting rod 6 is inserted into the housing 5 and is coaxial with the tubular electromagnetic coil 4. A seal is provided between the connecting rod 6 and the housing 5, and a limit block (not shown) is provided at the end of the connecting rod 6 near the tubular electromagnetic coil 4 to prevent the connecting rod 6 from detaching. The two ends of the return spring 2 abut against the striking hammer 3 and the housing 5, respectively. During operation, a certain current is applied to the tubular electromagnetic coil 4, causing it to generate a magnetic field of corresponding magnitude. This magnetic field attracts the connecting rod 6 to the center of the tubular electromagnetic coil 4, thereby causing the striking hammer 3 to retract. This retracts the striking hammer 3, compressing the return spring 2 between the housing 5 and the striking hammer 3, allowing the return spring 2 to store a certain amount of elastic potential energy. When the power to the tubular electromagnetic coil 4 is de-energized, the striking hammer 3, losing its magnetic field attraction, is ejected by the return spring 2, creating an impact and achieving the striking purpose. Rapid striking is achieved through continuous energization and discharging. The striking force is adjusted by changing the current input to the tubular electromagnetic coil 4, and the striking frequency is controlled by the frequency of current switching to adapt to different testing environments and requirements. The multi-channel acoustic signal acquisition module 1 is mounted on the housing 5.

[0060] In other embodiments, a motor-driven cam / crank-connecting rod type striking device can be used. In this embodiment, the driving mechanism includes a motor and a transmission mechanism. The transmission mechanism can be a cam / crank-connecting rod. The striking execution mechanism includes a connecting rod and a striking hammer disposed at one end of the connecting rod. When the transmission mechanism is a cam, a return spring is provided between the other end of the connecting rod and the housing. When the transmission mechanism is a crank-connecting rod, the other end of the connecting rod is connected to the crank-connecting rod through a rotating rod. The connection between the rotating rod and the connecting rod, as well as the crank-connecting rod, is rotatable. During operation, the motor rotates, thereby driving the cam / crank-connecting rod to rotate, which in turn converts the selective motion of the electrode into the linear reciprocating motion of the connecting rod and the striking hammer, achieving rapid striking. The striking frequency and force can be controlled by controlling the power and speed of the electrode.

[0061] The multi-channel acoustic signal acquisition module includes at least one high-sensitivity hydrophone or one contact vibration sensor. The high-sensitivity hydrophone is used to acquire underwater acoustic wave signals generated by the impact; the contact vibration sensor (such as an accelerometer or a pressure transducer sensor) is used to directly acquire underwater structural vibration signals transmitted through the impact head. In some preferred embodiments, the multi-channel acoustic signal acquisition module includes both a high-sensitivity hydrophone and a contact vibration sensor to simultaneously acquire underwater acoustic wave signals and underwater structural vibration signals.

[0062] In some preferred embodiments, the underwater operation unit further includes:

[0063] The positioning and attitude sensing module, electrically connected to the first control and communication module, includes a depth sensor and a three-dimensional electronic compass / inertial measurement unit (IMU) for real-time acquisition of the underwater position of the striking device and the normal attitude of the striking surface. This allows for adjustment of the striking device's attitude based on its underwater position and the normal attitude of the striking surface, ensuring the striking hammer is substantially perpendicular to the underwater structure surface. The positioning and attitude sensing module and the first control and communication module can be housed within the striking device's casing.

[0064] Specifically, the surface control and analysis unit includes:

[0065] The second control and communication module is used to receive the working status and collected information of the underwater operation unit, and to issue operation commands to the underwater operation unit.

[0066] The signal processing and intelligent analysis module is electrically connected to the second control and communication module and is used to process and analyze the collected information to realize underwater structural defect detection.

[0067] The human-machine interaction module is electrically connected to the second control and communication module and the signal processing and intelligent analysis module. It is used to set the striking parameters (force, frequency, interval), display the working status and collected information of the underwater operation unit, and display the underwater structural defect detection results.

[0068] The signal processing and intelligent analysis module includes:

[0069] The preprocessing submodule is used to filter, reduce noise, and normalize the acquired underwater acoustic signals and / or underwater structural vibration signals.

[0070] The feature extraction submodule is used to extract time-domain features (such as peak value, decay time, and root mean square value) and frequency-domain features (such as spectrum, main frequency, and bandwidth energy) from the preprocessed signal to form a feature vector.

[0071] The intelligent defect identification submodule is used to input feature vectors into a pre-trained underwater structure defect identification model based on machine learning models (such as support vector machines (SVM) and convolutional neural networks (CNN), and output the defect type of the underwater structure (including defects such as no defects, voids, peeling, corrosion, etc.) and the corresponding probability.

[0072] like Figure 3 As shown, in practical implementation, for ease of movement, the underwater operation unit 01 can be integrated into the end effector of the robotic arm of the underwater robot 02 (ROV / AUV), and carried by the underwater robot 02 to achieve large-scale automated inspection. The structure of the underwater robot can adopt existing underwater robots, and its structure is not the focus of this invention, so it will not be described in detail here.

[0073] Based on the aforementioned underwater structural defect detection percussion system, this invention also provides a method for detecting underwater structural defects, such as... Figure 4 As shown, it includes the following steps:

[0074] S1. Detection Planning: Set the tapping parameters and path in the waterborne control and analysis unit.

[0075] Specifically, the detection path, tapping grid points or areas, and tapping parameters (force, frequency, interval) for each point are set in the water control and analysis unit.

[0076] S2. Tool Deployment and Positioning: Position the underwater operation unit to the point to be inspected.

[0077] Specifically, the underwater operation unit is transported to a predetermined starting position on the surface of the structure to be inspected, and the positioning and attitude sensing module ensures that the hammer is basically perpendicular to the surface of the structure.

[0078] S3. Simultaneous Acquisition of Impact and Signal: Control the impact device to impact, and simultaneously acquire signals through the multi-channel acoustic signal acquisition module.

[0079] Specifically, the control and drive module drives the hammer to strike the surface of the underwater structure with a set force and frequency; simultaneously, it triggers a multi-channel acoustic signal acquisition module to acquire underwater acoustic signals and underwater structural vibration signals at the moment of impact and for a period of time thereafter, and records the position and attitude information of the impact point. The acquired signals include underwater acoustic signals or underwater structural vibration signals, preferably including both underwater acoustic signals and underwater structural vibration signals.

[0080] S4. Signal Preprocessing and Feature Extraction: The signals acquired by the multi-channel acoustic signal acquisition module are preprocessed (filtered, denoised, normalized) and features (including time-domain features and frequency-domain features) are extracted to obtain feature vectors.

[0081] S5. Intelligent Defect Identification and Localization: The feature vector is input into a pre-trained underwater structure defect identification model based on a machine learning model. The model outputs the defect type and corresponding probability of the underwater structure and associates it with the location information. The association with location information specifically includes: combining the precise location information of the impact point to form a detection point cloud map or two-dimensional mapping map with defect probability annotations.

[0082] S6. Result Visualization: The human-computer interaction module of the surface control and analysis unit displays the location distribution of defects, determines their scale and characteristics, and then judges their severity according to relevant specifications. Preferably, the distribution and severity of defects are displayed intuitively in color-coded or chart form, and a structured inspection report is generated.

[0083] The underwater structure defect identification model is obtained through the following method:

[0084] We acquired a large number of signals from underwater structures struck under various known conditions, and performed feature extraction and annotation to obtain a sample dataset; the various known conditions include various defect types and defect-free states.

[0085] A machine learning model was trained based on a sample dataset to obtain an underwater structure defect identification model.

[0086] It is understood that the same or similar parts in the above embodiments can be referred to each other, and the contents not described in detail in some embodiments can be referred to the same or similar contents in other embodiments.

[0087] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. An underwater structure defect detection knock auscultation system, characterized by, The underwater operation unit and a water control and analysis unit in communication connection with the underwater operation unit; The underwater operation unit comprises: a knocking device for performing a set knocking action; a multi-channel acoustic signal acquisition module for acquiring underwater acoustic wave signals and / or underwater structure vibration signals; a first control and communication module electrically connected with the knocking device and the multi-channel acoustic signal acquisition module, for receiving operation instructions issued by the water control and analysis unit and uploading working status and acquisition information of the underwater operation unit; The water control and analysis unit comprises: a second control and communication module for receiving working status and acquisition information of the underwater operation unit and issuing operation instructions to the underwater operation unit; a signal processing and intelligent analysis module electrically connected with the second control and communication module, for processing and analyzing the acquisition information to realize underwater structure defect detection; a man-machine interaction module electrically connected with the second control and communication module and the signal processing and intelligent analysis module, for setting knocking parameters, displaying working status and acquisition information of the underwater operation unit, and displaying underwater structure defect detection results.

2. The underwater structure defect detection knock auscultation system according to claim 1, characterized by, The knocking device comprises: a shell, the inside of which constitutes a sealed cavity; a driving mechanism arranged in the shell; a knocking execution mechanism connected with the driving mechanism, for reciprocating knocking movement along a preset trajectory under control of the driving mechanism.

3. The underwater structure defect detection knock auscultation system according to claim 1, characterized by, The multi-channel acoustic signal acquisition module comprises at least one hydrophone and / or one contact vibration sensor.

4. The underwater structure defect detection knock listening system according to any one of claims 1 to 3, characterized in that, The underwater operation unit further comprises: a positioning and attitude sensing module electrically connected with the first control and communication module, comprising a depth sensor and a three-dimensional electronic compass / inertial measurement unit, for real-time acquisition of the position of the knocking device and the normal attitude of the knocking surface under water.

5. The underwater structure defect detection knock listening system according to claim 1, wherein, The signal processing and intelligent analysis module comprises: a preprocessing submodule for filtering, noise reduction and normalization processing of the acquired underwater acoustic wave signals and / or underwater structure vibration signals; a feature extraction submodule for extracting time domain features and frequency domain features from the preprocessed signals to form a feature vector; a defect intelligent recognition submodule for inputting the feature vector into a trained underwater structure defect recognition model based on a machine learning model to output the defect type and corresponding probability of the underwater structure.

6. The underwater structure defect detection knock listening system of claim 1, wherein, The underwater operation unit is integrated at the end of a mechanical arm of an underwater robot and is carried and moved by the underwater robot.

7. A method of detecting defects in an underwater structure, characterized by, The underwater structure defect detection knocking auscultation system according to any one of claims 1 to 6 is implemented, comprising the following steps: Detection planning: setting knocking parameters and path in the water control and analysis unit; Tool deployment and positioning: positioning the underwater operation unit to the detection point; Knocking and signal synchronous acquisition: controlling the knocking device to knock and synchronously acquiring signals through the multi-channel acoustic signal acquisition module; Signal preprocessing and feature extraction: preprocessing and extracting features of the signals acquired by the multi-channel acoustic signal acquisition module to obtain a feature vector; Defect intelligent recognition and positioning: inputting the feature vector into a trained underwater structure defect recognition model based on a machine learning model to output the defect type and corresponding probability of the underwater structure, and associating with the position information; Result visualization: display the distribution of defects on the human-computer interaction module of the control and analysis unit on the water.

8. The method of claim 7, wherein, The signals collected by the multi-channel acoustic signal acquisition module include underwater acoustic wave signals and underwater structure vibration signals.

9. The method of claim 7, wherein, The underwater structure defect identification model is obtained by the following method: Signals collected by knocking on underwater structures in various known states are obtained, and feature extraction and labeling are performed to obtain a sample data set; various known states include various defect types and no defect states; Based on the sample data set, the machine learning model is trained to obtain the underwater structure defect identification model.

10. The method of claim 7, wherein, When visualizing the results, the distribution of defects is displayed in color-coded or chart form, and a structured detection report is generated.

Images