Water conservancy project pipeline-oriented quality detection method and system

Abstract

The invention discloses a water conservancy project pipeline-oriented quality detection method and system, and belongs to the technical field of detection. The method comprises the following steps: constructing an environment interference model to obtain an environment interference coefficient; constructing a detection probe state model to obtain a state coefficient; constructing a data-pipeline stability model to output stability; constructing an optical working condition matching degree model based on the coefficients, the turbidity of water in the pipeline and the reflectivity of the inner wall; and finally, dynamically adjusting the core temperature of the target imaging unit through a temperature optimization model in combination with the matching degree, the stability and the current imaging unit temperature. According to the invention, through multi-source information fusion and hierarchical modeling, comprehensive evaluation and adaptive regulation and control of a pipeline detection environment are realized, and the detection quality and the system stability under complex working conditions are significantly improved.

Description

Technical Field

[0001] This invention belongs to the field of testing technology, and in particular relates to a quality testing method and system for water conservancy engineering pipelines. Background Technology

[0002] As key structures in water supply and drainage systems, the quality of pipelines in water conservancy projects directly affects project safety and operational efficiency. Therefore, developing efficient and accurate pipeline quality inspection methods and systems is of great significance for preventing pipeline leaks, deformation, corrosion, and other defects, and for improving the level of intelligent operation and maintenance.

[0003] Currently, pipeline quality inspection relies heavily on manual inspections, single-sensor detection, or automated systems based on fixed thresholds. Common technologies include endoscopic visual inspection, acoustic detection, and electromagnetic detection. While these methods can acquire localized information, they are susceptible to various factors such as environmental interference, equipment status, and data communication stability within the complex and ever-changing internal environment of pipelines. This results in insufficient reliability of the inspection results and a lack of systematic evaluation and adaptive adjustment capabilities for the overall inspection conditions.

[0004] Existing technologies often consider a single type of influencing factor in isolation, failing to establish a collaborative evaluation model that integrates multi-source information. This makes it difficult to achieve stable and high-precision quality inspection in real-world engineering environments with strong interference and high variability. In particular, in optical inspection, factors such as environmental interference, probe contamination, communication packet loss, and water turbidity collectively affect imaging quality. Traditional methods lack comprehensive modeling and real-time control mechanisms for these factors, resulting in low detection efficiency and poor adaptability. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides a quality inspection method and system for water conservancy engineering pipelines, solving the aforementioned problems.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a quality inspection method for pipelines in water conservancy projects, comprising: The environmental interference coefficient is obtained based on the ambient electromagnetic field strength, the vibration acceleration of the vehicle platform, and the background noise sound pressure level (in dB) inside the pipeline. Based on the thickness of dirt in the optical probe window, the fluctuation rate of the probe power supply voltage, and the real-time yaw rate of the vehicle, the state coefficient of the detection probe is obtained. The pipeline stability model is constructed based on the number of consecutive data packet loss, the signal-to-noise ratio of the wireless communication link, and the frequency of sudden changes in gas pressure inside the pipeline. The output data is the pipeline stability. Based on the environmental interference coefficient and the state coefficient of the detection probe, the turbidity of the water in the pipeline and the reflectivity of the inner wall of the pipeline are obtained to determine the optical working condition matching degree. A temperature optimization model is constructed based on optical condition matching degree, data-pipeline stability, and current imaging unit core temperature (chip temperature) to obtain the target imaging unit core temperature.

[0007] Based on the above technical solutions, the present invention also provides the following optional technical solutions: A further technical solution: The temperature optimization model is expressed as follows: in, This indicates the core temperature of the target imaging unit. This indicates the current core temperature of the imaging unit. Indicates data-pipeline stability. Indicates the degree of matching between the target optical conditions. This indicates the degree of optical condition matching.

[0008] Further technical solution: The method for obtaining the optical condition matching degree is as follows: To obtain the turbidity of the water inside the pipe and the reflectivity of the inner wall of the pipe; The absolute difference between the turbidity of the water in the pipeline and the reflectance of the inner wall of the pipeline and the corresponding ideal value is compared with the corresponding allowable deviation from the ideal value to obtain the turbidity deviation index and the reflectance deviation index. Based on the environmental interference coefficient and the turbidity deviation index and reflectance deviation index under the detection probe state coefficient, the optical condition matching degree is obtained through the optical condition matching degree model, which is expressed as follows: in, Indicates the degree of matching between optical operating conditions. Indicates the environmental interference coefficient. Indicates the detection state coefficient. Indicates the turbidity deviation index. Indicates the deviation of reflectance from the exponent, the The larger the value, the greater the optical imaging potential.

[0009] Further technical solution: The method for obtaining data-pipeline stability is as follows: The number of consecutive data packet losses, the signal-to-noise ratio of the wireless communication link, and the frequency of sudden changes in air pressure inside the pipeline were obtained. Import the number of consecutive data packet losses into the formula Obtain the packet loss frequency index, where, Indicates the number of consecutive packet losses. Indicates the number of consecutive packet losses; Import the signal-to-noise ratio of the wireless communication link into the formula Obtain the signal-to-noise ratio index. Indicates the signal-to-noise ratio of a wireless communication link. Indicates the reference signal-to-noise ratio; Import the frequency of sudden changes in gas pressure inside the pipeline into the formula. Obtain the frequency index of air pressure sudden changes. This indicates the frequency of sudden changes in air pressure inside the pipeline. Reference mutation frequency; Based on the packet loss frequency index, signal-to-noise ratio index, and air pressure change frequency index, data-pipeline stability is obtained through a data-pipeline stability model, which is expressed as follows: in, Indicates data-pipeline stability. Indicates the number of packet loss events. This represents the signal-to-noise ratio index. The index representing the frequency of sudden changes in air pressure, the Furthermore, the larger the value, the more stable the overall system operation.

[0010] Further technical solution: The method for obtaining the state coefficient of the detection probe is as follows: Acquire the thickness of dirt on the optical probe window, the fluctuation rate of the probe power supply voltage, and the real-time yaw rate of the vehicle; The dirt thickness of the optical probe window, the fluctuation rate of the probe power supply voltage, and the real-time yaw rate of the vehicle are subjected to maximum-minimum normalization to obtain the dirt thickness index, voltage fluctuation index, and yaw rate index. Based on the fouling thickness index, voltage fluctuation index, and yaw rate index, the probe state coefficients are obtained through a probe state model, which is expressed as follows: in, Indicates the detection state coefficient. Indicates the dirt thickness index. Indicates the voltage fluctuation index. Indicates the yaw rate index. Represents the weight coefficient and The Furthermore, the larger the value, the worse the condition of the detection probe.

[0011] Further technical solution: The method for obtaining the environmental interference coefficient is as follows: Acquire ambient electromagnetic field strength, vehicle platform vibration acceleration, and background noise sound pressure level inside the pipeline; The environmental electromagnetic field strength, vehicle platform vibration acceleration, and background noise sound pressure level in the pipeline are subjected to maximum-minimum normalization to obtain the magnetic field strength index, vibration index, and noise sound pressure level index. Based on the magnetic field strength index, vibration index, and noise sound pressure level index, the environmental interference coefficient is obtained through an environmental interference model, which is expressed as follows: in, Indicates the environmental interference coefficient. Indicates the magnetic field strength index. Indicates the vibration index. The noise sound pressure level index, the The larger the value, the stronger the environmental interference.

[0012] A quality inspection system for water conservancy project pipelines, employing the aforementioned quality inspection method for water conservancy project pipelines.

[0013] This invention provides a quality inspection method and system for water conservancy engineering pipelines, which has the following advantages compared with the prior art: 1. This invention establishes a multi-level collaborative model of environmental interference, probe status, communication-pipeline stability, and optical matching degree to achieve a systematic and quantitative evaluation of pipeline inspection conditions, overcoming the limitations of traditional single-index detection. 2. This invention introduces an optical working condition matching degree and temperature optimization model, which can dynamically adjust the core temperature of the imaging unit according to the real-time environment and equipment status, effectively improving the imaging quality under adverse conditions such as dirt, vibration, and turbidity changes, and enhancing the stability and clarity of detection. 3. By using a data-pipeline stability model to quantitatively evaluate the communication link and pipeline air pressure status, the system can maintain continuous operation when there is packet loss, signal attenuation or sudden changes in air pressure, reducing the risk of detection interruption caused by external interference. Attached Figure Description

[0014] Figure 1 This is the intended flow of the present invention. Detailed Implementation

[0015] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0016] The specific implementation of the present invention will be described in detail below with reference to specific embodiments.

[0017] Please see Figure 1 The present invention provides a quality inspection method for water conservancy engineering pipelines, comprising: The environmental interference coefficient is obtained based on the ambient electromagnetic field strength, the vibration acceleration of the vehicle platform, and the background noise sound pressure level (in dB) inside the pipeline. Based on the thickness of dirt in the optical probe window, the fluctuation rate of the probe power supply voltage, and the real-time yaw rate of the vehicle, the state coefficient of the detection probe is obtained. Based on the number of consecutive data packet losses, the signal-to-noise ratio of the wireless communication link, and the frequency of sudden changes in air pressure inside the pipeline, the output data is pipeline stability. Based on the environmental interference coefficient and the state coefficient of the detection probe, the turbidity of the water in the pipeline and the reflectivity of the inner wall of the pipeline are obtained to determine the optical working condition matching degree. A temperature optimization model is constructed based on optical condition matching degree, data-pipeline stability, and current imaging unit core temperature (chip temperature) to obtain the target imaging unit core temperature.

[0018] The following example will provide a more detailed explanation of the above technical solution: Suppose that at location A, a critical hydraulic pipeline needs quality inspection. User A deploys an inspection vehicle equipped with an optical probe into the pipeline. During the inspection, this method assesses the complex internal conditions of the pipeline in real time and adaptively adjusts the operating temperature of the imaging unit.

[0019] Specifically, when the testing vehicle moves inside the pipeline, the ambient electromagnetic field strength, the vibration acceleration of the vehicle platform, and the background noise sound pressure level inside the pipeline are collected in real time. For example, in a certain section of the pipeline, the electromagnetic field strength may be high due to the presence of nearby high-voltage cables; simultaneously, the vehicle may experience significant vibration acceleration when passing through pipeline joints; and the rapid water flow inside the pipeline may also result in a high background noise sound pressure level. After these raw data are collected, a high environmental interference coefficient is calculated through simple weighted summation, indicating that the current environment significantly interferes with the testing.

[0020] Meanwhile, the condition of the detection probe itself is continuously monitored. For example, the optical probe window may gradually accumulate dirt due to sediment deposition inside the pipe, leading to a decrease in light transmittance; the probe power supply may be affected by fluctuations in the carrier's battery, resulting in slight voltage fluctuations; and the carrier may generate a certain yaw rate when turning inside the pipe. After these parameters are collected, a moderate detection probe condition coefficient is obtained through simple average calculation, indicating that the probe performance is affected to some extent.

[0021] Regarding data transmission, the detection system monitors the number of consecutive packet losses, the signal-to-noise ratio (SNR) of the wireless communication link, and the frequency of pressure fluctuations within the pipeline. For example, deep within the pipeline, the wireless signal may attenuate, leading to occasional packet loss; the SNR of the communication link may decrease with increasing distance; and changes in water pressure within the pipeline may cause slight pressure fluctuations. This data is input into a data-pipeline stability model, which, through a simple linear combination, outputs a moderately low data-pipeline stability, indicating a certain degree of volatility in data transmission and the pipeline environment.

[0022] Subsequently, the method calculates the optical condition matching degree based on the acquired environmental interference coefficient and the detection probe state coefficient, combined with the turbidity of the water inside the pipe and the reflectivity of the pipe inner wall. For example, in a certain section of the pipe, the water quality may be relatively turbid, and algae may be attached to the inner wall of the pipe, resulting in reduced reflectivity. In this case, a higher environmental interference coefficient and a moderate probe state coefficient will further reduce the optical condition matching degree, indicating that the potential for optical imaging is low under the current environmental and equipment conditions.

[0023] Finally, based on the calculated optical condition matching degree, data-pipeline stability, and the current core temperature of the imaging unit, a temperature optimization model is constructed to obtain the target imaging unit core temperature. For example, if the optical condition matching degree and data-pipeline stability are both low, while the current chip temperature is within the normal range, the temperature optimization model may suggest setting the target imaging unit core temperature slightly below the normal operating temperature to reduce power consumption, decrease thermal noise, and reserve adjustment space for potentially more severe operating conditions. Conversely, if the optical condition matching degree and data-pipeline stability are high, the model may suggest setting the target temperature slightly above the normal operating temperature to improve the imaging unit's response speed and image quality. In this way, the core temperature of the imaging unit is dynamically adjusted to adapt to the constantly changing internal environment of the pipeline and detection conditions, thereby ensuring relatively reliable detection data under various conditions.

[0024] Based on the above examples, the technical concept of this embodiment demonstrates a significant technical contribution. Traditional pipeline inspection methods often consider environmental factors or equipment status in isolation, lacking the ability to comprehensively evaluate and adaptively adjust multi-source information. For example, in the above examples, judging water turbidity solely based on a single turbidity sensor, or judging equipment status solely based on probe fouling thickness, may not fully reflect the true potential of optical imaging. Existing technologies typically use fixed thresholds or human experience for judgment. When encountering complex and variable pipeline environments, the reliability of their detection results is severely affected, and they cannot be optimized in real time according to actual operating conditions.

[0025] This embodiment achieves a comprehensive and quantitative assessment of the internal pipeline inspection conditions by introducing multiple comprehensive evaluation indicators, including environmental interference coefficient, detection probe state coefficient, data-pipeline stability, and optical condition matching degree. Obtaining these coefficients and stability values ​​allows the system to systematically understand the challenges currently faced in inspection from multiple dimensions, such as environment, equipment, and data transmission. More importantly, this embodiment further correlates these evaluation results with the core temperature of the imaging unit, achieving adaptive control of the imaging unit's operating temperature by constructing a temperature optimization model. This intelligent control mechanism based on multi-source information fusion enables the imaging unit to dynamically adjust its operating state in complex and ever-changing pipeline environments to maximize imaging quality and inspection efficiency.

[0026] For example, in the above example, when environmental interference is strong, probe condition is poor, data transmission is unstable, and optical condition matching is low, the method of this embodiment can comprehensively determine that high-intensity imaging is not suitable at present, and adjust the core temperature of the imaging unit accordingly to avoid unnecessary energy consumption and potential overheating risks, while ensuring that relatively stable data is obtained under the existing conditions. This adaptive temperature control capability is not available in the prior art. In this way, this embodiment effectively solves the problems of insufficient reliability of detection results, lack of systematic evaluation and adaptive adjustment capabilities, low detection efficiency, and poor adaptability in the prior art, and significantly improves the intelligence level and reliability of pipeline quality inspection in water conservancy projects.

[0027] Preferably, the environmental interference coefficient is obtained as follows: Acquire ambient electromagnetic field strength, vehicle platform vibration acceleration, and background noise sound pressure level inside the pipeline; The environmental electromagnetic field strength, vehicle platform vibration acceleration, and background noise sound pressure level in the pipeline are subjected to maximum-minimum normalization to obtain the magnetic field strength index, vibration index, and noise sound pressure level index. Based on the magnetic field strength index, vibration index, and noise sound pressure level index, the environmental interference coefficient is obtained through an environmental interference model, which is expressed as follows: in, Indicates the environmental interference coefficient. Indicates the magnetic field strength index. Indicates the vibration index. The noise sound pressure level index, the The larger the value, the stronger the environmental interference.

[0028] The ambient electromagnetic field strength refers to the electromagnetic radiation intensity in the environment where the detection vehicle operates inside the pipeline. It can be measured using an electromagnetic field sensor integrated on the vehicle, which can sense and quantify the surrounding electromagnetic wave energy density in real time. Alternatively, it can be measured periodically at pre-set electromagnetic field monitoring points outside the pipeline, and the data transmitted to the vehicle for reference. The vehicle platform vibration acceleration refers to the intensity of mechanical vibration experienced by the platform during the vehicle's movement within the pipeline. This is typically monitored in real time using a triaxial accelerometer mounted on the platform to obtain the instantaneous acceleration value. Alternatively, piezoelectric sensors or MEMS (microelectromechanical systems) accelerometers can be used to sense and quantify the vehicle's vibration level. The background noise sound pressure level inside the pipeline refers to the intensity of ambient noise inside the pipeline, excluding the operating sound of the detection equipment itself. It can be measured using a high-sensitivity microphone or sound pressure sensor. These sensors can capture sound waves generated by fluid flow, structural resonance, or external interference within the pipeline and convert them into quantifiable sound pressure level (in dB) data. Another approach is to use ultrasonic sensors to scan the inside of the pipeline during non-detection periods to establish a background noise baseline. Max-min normalization is a data preprocessing technique designed to transform raw data with different dimensions or ranges to a unified scale, such as [0, 1] or [-1, 1]. Its purpose is to eliminate the influence of differences in units and numerical ranges of different physical quantities on subsequent calculations, ensuring the comparability of various indicators in the model. This can be achieved by subtracting the minimum value from the raw data and then dividing by the difference between the maximum and minimum values; or by performing a linear mapping based on preset empirical maximum and minimum values. The magnetic field strength index, vibration index, and noise sound pressure level index are dimensionless indices obtained after max-min normalization, representing the influence of environmental electromagnetic field strength, platform vibration acceleration, and background noise sound pressure level inside the pipeline on detection, respectively. Obtaining these indices allows for the unified quantification and comparison of different types of environmental interference factors, providing standardized input for subsequent environmental interference models. The environmental interference model is a mathematical function used to integrate the magnetic field strength index, vibration index, and noise sound pressure level index to quantify the overall interference level of the current environment on the detection process. This model maps the cumulative effect of each interference index to an environmental interference coefficient ranging from 0 (no interference) to close to 1 (strong interference) through exponential decay. Environmental Interference Coefficient This is a dimensionless value ranging from 0 (no interference) to close to 1 (strong interference), used to comprehensively assess the degree of interference in the current detection environment. A larger value indicates stronger environmental interference and a greater potential impact on optical imaging. Its value range is... This ensures that the coefficient can effectively reflect the continuous change from no interference to extremely strong interference.

[0029] This application's solution systematically acquires and quantifies environmental interference factors during pipeline inspection in water conservancy projects, thereby providing accurate input for subsequent optical condition matching evaluation. Specifically, firstly, three key environmental parameters are collected in real time: ambient electromagnetic field strength, vibration acceleration of the testing platform, and background noise sound pressure level within the pipeline. These raw data reflect the complexity and dynamism of the environment in which the testing platform operates. To eliminate the influence of different physical dimensions and numerical ranges on the evaluation results, these raw data undergo max-min normalization, converting them into unified magnetic field strength index, vibration index, and noise sound pressure level index. These indices characterize the degree of interference from various environmental factors in a standardized form. Subsequently, these normalized indices are input into a pre-set environmental interference model. This model uses an exponential function to comprehensively calculate each independent interference index, generating a single environmental interference coefficient. The coefficient ranges from 0 to 1, with higher values ​​indicating stronger environmental interference. In this way, the proposed method can comprehensively and quantitatively assess the interference level of the current detection environment. This environmental interference coefficient... It was subsequently used to calculate optical condition matching degree. This allows the assessment of optical condition matching to fully consider the impact of environmental factors. This comprehensive assessment method, which takes environmental interference into account, makes the subsequent optimization of the target imaging unit core temperature based on optical condition matching more accurate and reliable, avoiding misjudgments or inefficient operations caused by inaccurate environmental interference assessments.

[0030] The following is a concrete example. During the inspection of pipelines in hydraulic engineering projects, an electromagnetic field sensor can be configured to measure the environmental electromagnetic field strength in real time; for example, a Hall effect sensor or a fluxgate sensor can be used. Simultaneously, a triaxial MEMS accelerometer is installed on the inspection platform to continuously monitor the platform's vibration acceleration. Furthermore, a miniature electret microphone or piezoelectric sound pressure sensor can be deployed inside the pipeline to obtain the background noise sound pressure level. Once these sensors acquire the raw data, for example, the electromagnetic field strength range is 0-100 μT, the vibration acceleration range is 0-5g, and the background noise sound pressure level range is 30-90 dB, their respective maximum and minimum values ​​can be set for normalization. For example, the electromagnetic field strength can be normalized to the [0,1] interval, where 0 μT corresponds to 0 and 100 μT corresponds to 1. Similarly, the vibration acceleration and noise sound pressure level are also normalized accordingly, resulting in the magnetic field strength index, vibration index, and noise sound pressure level index. For example, if the current magnetic field strength index... The vibration index is 0.5. The noise sound pressure level index is 0.3. If the value is 0.4, then substituting these indices into the environmental disturbance model, then... =0.699. This is the calculated value. The value will directly reflect the overall interference level of the current environment and serve as an important parameter for subsequent optical condition matching degree calculations.

[0031] Through the above technical solution, this application can accurately quantify the degree of environmental interference during the inspection of water conservancy engineering pipelines. By comprehensively considering the environmental electromagnetic field strength, the vibration acceleration of the vehicle platform, and the background noise sound pressure level inside the pipeline, and converting them into a unified environmental interference coefficient, the one-sidedness of assessing a single environmental factor is effectively avoided. This accurate environmental interference assessment allows the influence of external interference to be fully accounted for when calculating the optical condition matching degree, thereby improving the accuracy of the optical condition matching degree assessment. Ultimately, this helps to more accurately optimize the core temperature of the target imaging unit, ensuring that the imaging system can maintain its optimal working condition in complex and variable environments, significantly improving the reliability and imaging quality of water conservancy engineering pipeline quality inspection.

[0032] Preferably, the method for obtaining the state coefficient of the detection probe is as follows: Acquire the thickness of dirt on the optical probe window, the fluctuation rate of the probe power supply voltage, and the real-time yaw rate of the vehicle; The dirt thickness of the optical probe window, the fluctuation rate of the probe power supply voltage, and the real-time yaw rate of the vehicle are subjected to maximum-minimum normalization to obtain the dirt thickness index, voltage fluctuation index, and yaw rate index. Based on the fouling thickness index, voltage fluctuation index, and yaw rate index, the probe state coefficients are obtained through a probe state model, which is expressed as follows: in, Indicates the detection state coefficient. Indicates the dirt thickness index. Indicates the voltage fluctuation index. Indicates the yaw rate index. Represents the weight coefficient and The Furthermore, the larger the value, the worse the condition of the detection probe.

[0033] Specifically, the thickness of the contaminant on the optical probe window refers to the physical thickness of foreign objects or deposits adhering to the surface of the optical probe window during the detection process. This thickness directly affects light transmittance and scattering, thus reducing image quality. It can be obtained through real-time measurement using a miniature optical sensor integrated near the probe window, for example, by detecting changes in light beam attenuation or reflection within the contaminant layer, or indirectly through a mechanical scraping device in conjunction with the sensor. The probe power supply voltage fluctuation rate refers to the instability of the voltage supplying the detection probe within a certain time range. Severe voltage fluctuations can cause malfunctions in the probe's internal electronic components, affecting the stability and accuracy of data acquisition. This fluctuation rate can be obtained by real-time monitoring using a high-precision voltage sensor on the probe power supply line and calculating its root mean square value or peak-to-peak value ratio to the nominal voltage within a specific time window. The real-time yaw rate of the carrier refers to the speed at which the carrier carrying the detection probe rotates around its vertical axis as it moves within the pipe. A large yaw rate can lead to image blurring, distortion, or unstable field of view, thus affecting the normal operation of the imaging unit. This angular velocity can be measured in real time using a gyroscope sensor in the inertial measurement unit (IMU) integrated inside the vehicle.

[0034] Max-min normalization is a data preprocessing technique designed to transform raw data with different dimensions and numerical ranges into a unified, predefined numerical interval, such as [0, 1]. This method eliminates differences in dimensions and orders of magnitude between different physical quantities, making them comparable in subsequent calculations and preventing a single parameter from dominating the final result due to its large numerical range. The fouling thickness index, voltage fluctuation index, and yaw rate index are the results after max-min normalization. They quantify the relative influence of fouling thickness, voltage fluctuation rate, and yaw rate on the probe status, respectively. Generally, a larger value indicates a greater negative impact of the corresponding factor on the probe status.

[0035] The probe state model is a mathematical expression used to comprehensively evaluate the contribution of multiple influencing factors to the overall state of the probe. This model generates a single probe state coefficient by weighted summation of the fouling thickness index, voltage fluctuation index, and yaw rate index. The weighting coefficients are as follows: Used to adjust the relative importance of each index in the model. For example, if dirt has the most critical impact on image quality, the dirt thickness index can be given a higher weight. These weighting coefficients can be determined based on actual application scenarios, empirical data, or through machine learning methods, and the sum of all weighting coefficients is 1 to ensure the rationality of the coefficients. (Detection probe state coefficient) It is a dimensionless value between 0 and 1. The larger the value, the worse the overall condition of the detection probe, and the more serious the performance degradation or failure risk may be.

[0036] This application's solution systematically acquires key parameters affecting the probe's condition, including the thickness of the fouling at the optical probe window, the fluctuation rate of the probe's power supply voltage, and the real-time yaw rate of the vehicle. These raw data undergo max-min normalization to convert them into uniform-dimensional fouling thickness, voltage fluctuation, and yaw rate indices, thus eliminating dimensional differences between different physical quantities and enabling their effective comprehensive evaluation. Subsequently, these normalized indices are input into the probe's condition model, and the probe's condition coefficients are calculated through weighted summation. This model assigns different weights based on the actual importance of each influencing factor, thereby more accurately reflecting the probe's overall operating status. In this way, this application provides a quantitative and comprehensive probe condition assessment. This assessment result serves as a key input for calculating the optical condition matching degree, allowing the optical condition matching degree to more accurately reflect the actual imaging potential, thereby improving the overall reliability and adaptability of the method for quality inspection of pipelines in water conservancy projects.

[0037] The following is a concrete example to illustrate this. In actual testing, the probe state coefficients can be obtained in the following ways: The dirt thickness of the optical probe window can be measured in real time by a miniature laser rangefinder sensor installed at the edge of the probe window. This sensor calculates the dirt layer thickness by emitting a laser and receiving the reflected signal. The probe power supply voltage fluctuation rate can be obtained through a high-precision voltage sampling circuit integrated into the probe power management module. This circuit samples the voltage value at a frequency of 100 times per second and calculates the ratio of the standard deviation of the voltage to the average voltage as the fluctuation rate every minute. The real-time yaw rate of the vehicle is provided by a MEMS gyroscope sensor inside the vehicle. This sensor outputs three-axis angular velocity data at a frequency of 200Hz, where the yaw axis angular velocity data is used for calculation. After acquiring this raw data, an embedded processor (e.g., a microcontroller based on an ARM Cortex-M4 core) executes a max-min normalization algorithm. For example, if the dirt thickness range is set to 0mm to 0.5mm, a dirt thickness of 0.2mm will be normalized to a dirt thickness exponent of 0.4. Similarly, voltage fluctuation rate and yaw rate are also normalized to their corresponding exponents. Finally, the processor inputs these normalized exponents into a preset detection probe state model; for example, the weighting coefficients can be set as follows: =0.6 (dirt has the greatest impact), =0.25 (voltage fluctuation is the next most significant factor). =0.15 (the yaw rate has a relatively small impact), thus the final detection probe state coefficient is calculated.

[0038] Through the above technical solution, this application enables a comprehensive and quantitative assessment of the operating status of the detection probe. This assessment considers multiple key factors, such as the cleanliness of the optical probe window, the stability of the power supply voltage, and the motion posture of the carrier, all of which directly affect imaging quality and the reliability of data acquisition. By converting these factors into a unified index and performing a weighted summation, a detection probe status coefficient that accurately reflects the probe's health condition can be obtained. The introduction of this coefficient makes the subsequent calculation of optical condition matching more accurate, thereby avoiding data distortion or misjudgment caused by poor probe condition, significantly improving the accuracy and reliability of pipeline quality inspection in water conservancy projects, and ensuring high-quality inspection results even in complex and variable environments.

[0039] Preferably, the data-pipeline stability is obtained as follows: The number of consecutive data packet losses, the signal-to-noise ratio of the wireless communication link, and the frequency of sudden changes in air pressure inside the pipeline were obtained. Import the number of consecutive data packet losses into the formula Obtain the packet loss frequency index, where, Indicates the number of consecutive packet losses. Indicates the number of consecutive packet losses; Import the signal-to-noise ratio of the wireless communication link into the formula Obtain the signal-to-noise ratio index. Indicates the signal-to-noise ratio of a wireless communication link. Indicates the reference signal-to-noise ratio; Import the frequency of sudden changes in gas pressure inside the pipeline into the formula. Obtain the frequency index of air pressure sudden changes. This indicates the frequency of sudden changes in air pressure inside the pipeline. Reference mutation frequency; Based on the packet loss frequency index, signal-to-noise ratio index, and air pressure change frequency index, data-pipeline stability is obtained through a data-pipeline stability model, which is expressed as follows: in, Indicates data-pipeline stability. Indicates the number of packet loss events. This represents the signal-to-noise ratio index. The index representing the frequency of sudden changes in air pressure, the Furthermore, the larger the value, the more stable the overall system operation.

[0040] The aforementioned data on the number of consecutive data packet losses, the signal-to-noise ratio (SNR) of the wireless communication link, and the frequency of pressure fluctuations within the pipeline are fundamental data for evaluating the operational stability of a pipeline quality inspection system in water conservancy projects. The number of consecutive data packet losses reflects the reliability of the data transmission link; a high loss rate typically indicates communication interruption or severe interference. The SNR of the wireless communication link directly quantifies the quality of the wireless signal; a low SNR indicates that the signal is susceptible to noise, and data transmission may be unstable. The frequency of pressure fluctuations within the pipeline characterizes the physical stability of the pipeline's internal environment, such as water flow impact and cavitation. These fluctuations can cause platform shaking or abnormal sensor readings. These parameters can be obtained by integrating corresponding sensors and communication modules onto the inspection vehicle. For example, the communication module can statistically analyze packet transmission and reception in real time to obtain the number of packet losses and report the link's SNR; a high-precision pressure sensor can continuously monitor changes in pipeline pressure and calculate the frequency of fluctuations through a signal processing unit.

[0041] Import the number of consecutive data packet losses into the formula The steps to obtain the packet loss index aim to calculate the number of consecutive data packet losses. This is transformed into a standardized, dimensionless index of packet loss frequency. By using the form of an exponential function, different orders of magnitude can be... Mapped to the range [0, 1), where This is a reference number of consecutive packet losses used to adjust the sensitivity of the exponential curve. When When smaller, A value close to 0 indicates that packet loss has a small impact; when... When it increases, A value close to 1 indicates a significant impact from packet loss. This transformation method allows packet loss to be included in subsequent comprehensive assessments on a uniform scale.

[0042] Import the signal-to-noise ratio of the wireless communication link into the formula The steps to obtain the signal-to-noise ratio exponent are to convert the original wireless communication link signal-to-noise ratio into the exponent. Converted into a standardized signal-to-noise ratio index Similar to the packet loss frequency index, It is also mapped to the range (0, 1], where It is a reference signal-to-noise ratio. When At higher levels, A value close to 0 indicates good communication quality; when... At lower levels, A value approaching 1 indicates poor communication quality. This exponential form effectively reflects the nonlinear impact of the signal-to-noise ratio on communication stability and facilitates comprehensive calculations with other indices.

[0043] Import the frequency of sudden changes in gas pressure inside the pipeline into the formula. The steps to obtain the frequency index of pressure surges involve converting the original frequency of pressure surges within the pipeline into a single index. Converted into a standardized barometric pressure change frequency index By using the form of an exponential function, Mapped to the range [0, 1), where It is a reference mutation frequency. When When smaller, A value close to 0 indicates a stable pipeline environment; when When it increases, A value approaching 1 indicates an unstable pipeline environment. This conversion method quantifies the degree of disturbance in the physical environment and allows for unified evaluation with other data transmission-related indices.

[0044] The steps for obtaining data-pipeline stability using a data-pipeline stability model, based on packet loss frequency index, signal-to-noise ratio index, and air pressure change frequency index, are core to comprehensively evaluating system stability. This involves using the previously calculated packet loss frequency index... Signal-to-noise ratio index and the frequency index of sudden air pressure changes Import data - Pipeline stability model Ultimately, a comprehensive set of data is obtained – pipeline stability. The model employs the inverse form of the geometric mean, ensuring that any unstable factor (i.e., a large corresponding exponent value) will significantly reduce the overall stability. . The value range is [0, 1], with a larger value indicating a more stable overall system operation. This comprehensive evaluation method can fully reflect the stability of data transmission and the pipeline environment, providing an accurate basis for subsequent temperature optimization.

[0045] This application's solution evaluates the data transmission and pipeline environmental stability of a hydraulic engineering pipeline quality inspection system in a multi-dimensional and quantitative manner, thereby providing a precise basis for the temperature optimization of the imaging unit. First, the system acquires three key raw data points in real time: the number of consecutive data packet losses, the signal-to-noise ratio (SNR) of the wireless communication link, and the frequency of pressure fluctuations within the pipeline. These data reflect the system's operating status from three aspects: communication reliability, signal quality, and physical environmental disturbances, respectively. To unify and quantify these heterogeneous raw data points for comprehensive evaluation, the system imports the number of consecutive data packet losses, the SNR of the wireless communication link, and the frequency of pressure fluctuations within the pipeline into preset exponential formulas to generate a packet loss index, a SNR index, and a pressure fluctuation frequency index. These indices are standardized to a specific range, allowing them to participate in subsequent calculations with uniform weights or levels of influence. Based on this, the system inputs these three standardized indices into a data-pipeline stability model, which uses specific mathematical operations (such as the reciprocal of the geometric mean) to fuse them into a single, comprehensive data-pipeline stability. This comprehensive model design ensures that a deterioration in any single metric will significantly impact the overall stability, thus avoiding errors caused by one-sided assessments. For example, even with a good signal-to-noise ratio, if the number of consecutive data packet losses is high, or if there are frequent pressure fluctuations within the pipeline, the overall stability will be accurately assessed as low. The final data obtained is the pipeline stability. As a key parameter, it is input into the temperature optimization model, where it, along with the optical condition matching degree and the current core temperature of the imaging unit, jointly determines the core temperature of the target imaging unit. Through this refined stability evaluation mechanism, the current operating state of the system can be more accurately reflected, enabling the temperature optimization model to dynamically adjust the core temperature of the imaging unit based on actual operational stability. This effectively extends equipment life and improves detection efficiency while ensuring imaging quality.

[0046] The following is a concrete example. Suppose that during a pipeline quality inspection task in a water conservancy project, the inspection vehicle is inside the pipeline collecting and transmitting data. To obtain data on pipeline stability, the system first monitors and acquires the following data in real time: the number of consecutive data packet losses. For example, within a certain time period, the system detects the consecutive loss of 5 data packets; the signal-to-noise ratio of the wireless communication link. For example, the signal-to-noise ratio of the current wireless communication link is 15dB; the frequency of sudden changes in air pressure inside the pipeline. For example, the gas pressure inside the pipeline changed abruptly twice within a unit of time. Next, the system imports this raw data into the corresponding exponential formula for processing. Assume the preset reference value is: the number of consecutive packet losses. The reference signal-to-noise ratio is 10. It is 20dB, based on the mutation frequency. The number of packet loss events is 5. First, calculate the packet loss exponent. =0.3935. Next, calculate the signal-to-noise ratio index. =0.4724. Next, calculate the barometric pressure change frequency index. =0.3297. Finally, these three indices are imported into the data-pipeline stability model to obtain the data-pipeline stability. = 0.6058. Through the above calculations, the system obtains the current data – pipeline stability. It is approximately 0.6058. This value will be input into the temperature optimization model, along with other parameters, to accurately calculate the core temperature of the target imaging unit.

[0047] Through the above technical solution, this application provides a comprehensive and refined data-pipeline stability assessment method. This method comprehensively considers multiple key factors, including data transmission reliability (measured by the number of consecutive data packet losses), communication link quality (measured by the signal-to-noise ratio of the wireless communication link), and physical disturbances in the pipeline's internal environment (measured by the frequency of sudden changes in air pressure within the pipeline). By transforming these heterogeneous raw data into standardized indices and using a data-pipeline stability model for comprehensive calculation, the method avoids the one-sidedness of single-index assessments, thus more accurately reflecting the overall operational stability of the system. This precise stability assessment allows subsequent temperature optimization models to obtain more reliable input parameters, thereby achieving more accurate control over the core temperature of the imaging unit. This not only helps maintain high-quality image acquisition in the complex and ever-changing environment of hydraulic engineering pipelines but also effectively avoids equipment overheating or performance degradation caused by environmental or communication instability, thereby improving detection efficiency and extending equipment lifespan.

[0048] Preferably, the optical condition matching degree is obtained as follows: To obtain the turbidity of the water inside the pipe and the reflectivity of the inner wall of the pipe; The absolute difference between the turbidity of the water in the pipeline and the reflectance of the inner wall of the pipeline and the corresponding ideal value is compared with the corresponding allowable deviation from the ideal value to obtain the turbidity deviation index and the reflectance deviation index. Based on the environmental interference coefficient and the turbidity deviation index and reflectance deviation index under the detection probe state coefficient, the optical condition matching degree is obtained through the optical condition matching degree model, which is expressed as follows: in, Indicates the degree of matching between optical operating conditions. Indicates the environmental interference coefficient. Indicates the detection state coefficient. Indicates the turbidity deviation index. Indicates the deviation of reflectance from the exponent, the The larger the value, the greater the optical imaging potential.

[0049] Obtaining the turbidity of the water inside the pipe and the reflectivity of the pipe's inner wall is fundamental to assessing the optical environment inside the pipe. Water turbidity refers to the degree to which suspended matter in the water obstructs the propagation of light. It is typically obtained by measuring the scattering or attenuation of light in water, for example, using a turbidity sensor based on the principle of infrared scattering for real-time measurement, or by evaluating it using the transmitted light intensity attenuation method. The reflectivity of the pipe's inner wall reflects its ability to reflect light, which directly affects the efficiency of light utilization and the uniformity of image brightness during imaging. It can be measured using a miniature spectrometer or a photodiode array in conjunction with a light source to obtain the reflection characteristics at different wavelengths.

[0050] The turbidity deviation index and reflectance deviation index are obtained by comparing the absolute differences between the turbidity of the water inside the pipe and the reflectance of the pipe's inner wall and their corresponding ideal values ​​with the corresponding allowable deviations from the ideal values. This aims to quantify the degree of deviation between the current optical conditions inside the pipe and the ideal imaging conditions. This ratio processing unifies the deviations of different physical quantities onto a dimensionless index, facilitating subsequent comprehensive calculations of the model. For example, an ideal water turbidity value and an allowable turbidity deviation range can be preset under specific imaging requirements. When the actual measured value differs from the ideal value, the turbidity deviation index is obtained by calculating the ratio of its absolute difference to the allowable deviation range. The reflectance deviation index is obtained in a similar way, by comparing the difference between the actual inner wall reflectance and the ideal reflectance, and combining this with the allowable deviation range for quantification.

[0051] Based on the environmental interference coefficient and the turbidity deviation index and reflectance deviation index under the detection probe state coefficient, the optical condition matching degree is obtained through the optical condition matching degree model. This step comprehensively considers multiple factors affecting optical imaging quality. Environmental interference coefficient and detection probe state coefficient These reflect the negative impacts of external environmental factors (such as electromagnetic interference and vibration) and the condition of the detection equipment itself (such as probe contamination and power supply fluctuations) on imaging. Turbidity Deviation Index and reflectivity deviation index This directly quantifies the quality of the internal optical environment of the pipeline. Optical operating condition matching degree model. As a mathematical expression, this model organically combines these independent exponents and coefficients to output a comprehensive matching degree value between 0 and 1. The model is designed so that the stronger the environmental interference, the worse the probe condition, and the greater the deviation of the internal optical conditions of the pipeline from the ideal value, the higher the matching degree. The smaller the value, the larger the value, thus intuitively reflecting the current potential of optical imaging.

[0052] This application's solution involves accurately measuring the turbidity of the water inside the pipeline and the reflectivity of its inner wall, then quantitatively comparing these measurements with ideal values ​​to generate turbidity deviation indices and reflectivity deviation indices. Based on this, and combining the acquired environmental interference coefficient and the detection probe's state coefficient, these multi-dimensional data are input into a specially designed optical condition matching model for calculation. This model cleverly integrates the optical conditions of the environment, equipment, and pipeline interior into a unified matching index. This comprehensive evaluation method allows the optical condition matching degree to fully and accurately reflect the possibility of high-quality optical imaging under the current environment. When this optical condition matching degree is input into the aforementioned temperature optimization model, the temperature optimization model can output a more reasonable and optimized core temperature for the target imaging unit based on a more accurate condition assessment, thereby ensuring that the imaging unit acquires images under optimal operating conditions, effectively overcoming the limitations of judging optical conditions solely based on experience or a single factor.

[0053] The following example illustrates this: During the inspection of hydraulic engineering pipelines, a turbidity sensor mounted on a vehicle first measures the turbidity of the water inside the pipeline in real time, for example, if the current turbidity is measured to be 15 NTU. Simultaneously, a miniature spectrometer measures the average reflectance of the pipeline's inner wall, which is 0.6. Assuming an ideal water turbidity of 5 NTU with an allowable deviation of 10 NTU, and an ideal inner wall reflectance of 0.8 with an allowable deviation of 0.2, then the turbidity deviation index... This can be calculated as |15-5| / 10=1, the reflectance deviation index. This can be calculated as |0.6-0.8| / 0.2=1. Further, assuming the environmental electromagnetic field strength, vehicle platform vibration acceleration, and background noise sound pressure level inside the pipeline are obtained from other sensors, the environmental interference coefficient can be calculated. The value is 0.3. The state coefficient of the detection probe is calculated by the dirt thickness of the optical probe window, the fluctuation rate of the probe power supply voltage, and the real-time yaw rate of the vehicle. The value is 0.2. Substituting these parameters into the optical condition matching degree model, then... =0.326. This calculated optical condition matching degree The value will be used as input to the temperature optimization model to guide the adjustment of the core temperature of the imaging unit.

[0054] Through the above technical solution, this application provides a more refined and comprehensive method for evaluating optical condition matching. This method comprehensively considers the water quality conditions inside the pipeline (turbidity), the pipeline structural characteristics (inner wall reflectivity), as well as the influence of external environmental interference and the condition of the detection equipment itself, making the calculation results of optical condition matching more accurate and reliable. This precise matching evaluation provides a solid data foundation for subsequent optimization of the imaging unit's core temperature, thereby effectively improving the quality and stability of image acquisition during the quality inspection of hydraulic engineering pipelines, reducing detection errors and omissions caused by poor optical conditions, and ultimately improving the overall efficiency and reliability of the inspection.

[0055] Preferably, the temperature optimization model is expressed as: in, This indicates the core temperature of the target imaging unit. This indicates the current core temperature of the imaging unit. Indicates data-pipeline stability. Indicates the degree of matching between the target optical conditions. This indicates the degree of optical condition matching.

[0056] This temperature optimization model aims to dynamically calculate and set the optimal operating temperature of the imaging unit based on various environmental and system state parameters monitored in real time. It is the temperature that the system expects the imaging unit to reach in order to optimize imaging performance and extend device life; It is the current actual temperature of the imaging unit, which serves as the reference for temperature adjustment; It reflects the overall stability of data transmission and pipeline environment. The higher the value, the more stable the system operation, and vice versa. It is the preset ideal optical condition matching degree, which represents the best imaging conditions; This represents the actual measured optical condition matching degree, reflecting the actual degree of matching under current optical imaging conditions. This model can be implemented using various mathematical forms; for example, in addition to the expression based on the hyperbolic tangent function given in this application, it can also be constructed based on fuzzy logic reasoning, neural network prediction, or multivariate regression analysis.

[0057] This application's solution introduces a nonlinear model based on the hyperbolic tangent function to organically combine data-pipeline stability, target optical condition matching degree, and current optical condition matching degree, thereby dynamically adjusting the current imaging unit core temperature to obtain the target imaging unit core temperature. Specifically, the model... This item reflects the impact of system stability on the temperature adjustment range: when the system stability At higher levels, A smaller value indicates good environmental and data transmission conditions, resulting in a relatively smaller temperature adjustment range; conversely, when... At lower levels, A larger value allows for greater temperature adjustments to cope with unstable operating conditions. Meanwhile, The term quantifies the gap between the current optical operating conditions and the ideal operating conditions: when the current optical operating conditions match... Below the target optical condition matching degree When this value is positive, it indicates that imaging conditions need to be improved through temperature adjustment; when... Close to or higher When this term is zero or negative, it indicates that the optical conditions are good or even too good, and the temperature may need to be maintained or lowered. The introduction of the hyperbolic tangent function tanh makes the temperature adjustment response nonlinear and bounded, avoiding excessively large or small adjustment amounts under extreme conditions, thus ensuring the smoothness and robustness of temperature control. In this way, the model can intelligently adjust the core temperature of the imaging unit according to complex environmental changes and system operating states, aiming to achieve optimal imaging results under various operating conditions.

[0058] The following is a concrete example to illustrate this. Suppose that during the inspection of a hydraulic engineering pipeline, the current core temperature of the imaging unit... The temperature was 35°C. Data on pipeline stability was obtained using the method described above. A value of 0.7 (indicating relatively stable system operation) indicates the current optical condition matching degree. The value is 0.6 (indicating generally poor optical conditions), while the preset target optical condition matching degree is... The value is 0.9. Substituting these values ​​into the temperature optimization model, then... =35.1°C, indicating that the system recommends slightly increasing the core temperature of the imaging unit to improve the current optical imaging conditions. Conversely, if It has reached 0.95, which is higher than ,but A negative value may lead to Slightly lower The system can adjust the temperature appropriately to save energy or prevent overheating. In this way, the system can intelligently adjust the core temperature of the imaging unit according to real-time operating conditions to adapt to the constantly changing detection environment.

[0059] Through the above technical solution, this application provides a precise, dynamic, and adaptive method for optimizing the core temperature of an imaging unit. This method effectively addresses the technical problem of intelligently determining the optimal operating temperature of the imaging unit in complex and variable hydraulic engineering pipeline inspection environments, considering factors such as environmental interference, probe status, data transmission stability, and optical conditions. By introducing the influence of data-pipeline stability on the temperature adjustment range, and the difference between optical condition matching and target matching, as adjustment criteria, the imaging unit consistently operates within a temperature range conducive to acquiring high-quality images. This significantly improves the clarity and reliability of the inspected images and also helps extend the service life of the imaging unit.

[0060] A quality inspection system for water conservancy project pipelines, employing the aforementioned quality inspection method for water conservancy project pipelines.

[0061] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus.

[0062] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A quality inspection method for pipelines in water conservancy projects, characterized in that, include: The environmental interference coefficient is obtained based on the ambient electromagnetic field strength, the vibration acceleration of the vehicle platform, and the background noise sound pressure level inside the pipeline. Based on the thickness of dirt in the optical probe window, the fluctuation rate of the probe power supply voltage, and the real-time yaw rate of the vehicle, the state coefficient of the detection probe is obtained. The pipeline stability model is constructed based on the number of consecutive data packet losses, the signal-to-noise ratio of the wireless communication link, and the frequency of sudden changes in air pressure inside the pipeline. The output data is the pipeline stability. Based on the environmental interference coefficient and the state coefficient of the detection probe, the turbidity of the water in the pipeline and the reflectivity of the inner wall of the pipeline are obtained to determine the optical condition matching degree. A temperature optimization model is constructed based on optical condition matching degree, data-pipeline stability, and the current core temperature of the imaging unit to obtain the core temperature of the target imaging unit.

2. The quality inspection method for water conservancy project pipelines according to claim 1, characterized in that, The temperature optimization model is expressed as follows: in, This indicates the core temperature of the target imaging unit. This indicates the current core temperature of the imaging unit. Indicates data-pipeline stability. Indicates the degree of matching between the target optical conditions. This indicates the degree of optical condition matching.

3. The quality inspection method for water conservancy project pipelines according to claim 2, characterized in that, The method for obtaining the optical condition matching degree is as follows: To obtain the turbidity of the water inside the pipe and the reflectivity of the inner wall of the pipe; The absolute difference between the turbidity of the water in the pipeline and the reflectance of the inner wall of the pipeline and the corresponding ideal value is compared with the corresponding allowable deviation from the ideal value to obtain the turbidity deviation index and the reflectance deviation index. Based on the environmental interference coefficient and the turbidity deviation index and reflectance deviation index under the detection probe state coefficient, the optical condition matching degree is obtained through the optical condition matching degree model, which is expressed as follows: in, Indicates the degree of matching between optical operating conditions. Indicates the environmental interference coefficient. Indicates the detection state coefficient. Indicates the turbidity deviation index. Indicates the deviation of reflectance from the exponent, the Furthermore, the larger the value, the greater the optical imaging potential.

4. The quality inspection method for water conservancy project pipelines according to claim 2, characterized in that, The data-pipeline stability is obtained as follows: The number of consecutive data packet losses, the signal-to-noise ratio of the wireless communication link, and the frequency of sudden changes in air pressure inside the pipeline were obtained. Import the number of consecutive data packet losses into the formula Obtain the packet loss frequency index, where, Indicates the number of consecutive packet losses. Indicates the number of consecutive packet losses; Import the signal-to-noise ratio of the wireless communication link into the formula Obtain the signal-to-noise ratio index. Indicates the signal-to-noise ratio of a wireless communication link. Indicates the reference signal-to-noise ratio; Import the frequency of sudden changes in gas pressure inside the pipeline into the formula. Obtain the frequency index of air pressure sudden changes. This indicates the frequency of sudden changes in air pressure inside the pipeline. Reference mutation frequency; Based on the packet loss frequency index, signal-to-noise ratio index, and air pressure change frequency index, data-pipeline stability is obtained through a data-pipeline stability model.

5. The quality inspection method for water conservancy engineering pipelines according to claim 3, characterized in that, The method for obtaining the state coefficient of the detection probe is as follows: Acquire the thickness of dirt on the optical probe window, the fluctuation rate of the probe power supply voltage, and the real-time yaw rate of the vehicle; The dirt thickness of the optical probe window, the fluctuation rate of the probe power supply voltage, and the real-time yaw rate of the vehicle are subjected to maximum-minimum normalization to obtain the dirt thickness index, voltage fluctuation index, and yaw rate index. Based on the dirt thickness index, voltage fluctuation index, and yaw rate index, the probe state coefficient is obtained through the probe state model.

6. The quality inspection method for water conservancy project pipelines according to claim 3, characterized in that, The environmental interference coefficient is obtained as follows: Acquire ambient electromagnetic field strength, vehicle platform vibration acceleration, and background noise sound pressure level inside the pipeline; The environmental electromagnetic field strength, vehicle platform vibration acceleration, and background noise sound pressure level in the pipeline are subjected to maximum-minimum normalization to obtain the magnetic field strength index, vibration index, and noise sound pressure level index. Based on the magnetic field strength index, vibration index, and noise sound pressure level index, the environmental interference coefficient is obtained through an environmental interference model, which is expressed as follows: in, Indicates the environmental interference coefficient. Indicates the magnetic field strength index. Indicates the vibration index. The noise sound pressure level index, the The larger the value, the stronger the environmental interference.

7. The quality inspection method for water conservancy engineering pipelines according to claim 4, characterized in that, The data-pipeline stability model is represented as follows: in, Indicates data-pipeline stability. Indicates the number of packet loss events. This represents the signal-to-noise ratio index. The index representing the frequency of sudden changes in air pressure, the Furthermore, the larger the value, the more stable the overall system operation.

8. The quality inspection method for water conservancy project pipelines according to claim 5, characterized in that, The state model of the detection probe is represented as follows: in, Indicates the detection state coefficient. Indicates the dirt thickness index. Indicates the voltage fluctuation index. Indicates the yaw rate index. Represents the weight coefficient and The Furthermore, the larger the value, the worse the condition of the detection probe.

9. The quality inspection method for water conservancy project pipelines according to claim 6, characterized in that, The environmental disturbance model is represented as follows: in, Indicates the environmental interference coefficient. Indicates the magnetic field strength index. Indicates the vibration index. The noise sound pressure level index, the The larger the value, the stronger the environmental interference.

10. A quality inspection system for pipelines in water conservancy projects, characterized in that, The quality inspection method for water conservancy engineering pipelines as described in any one of claims 1-9 is adopted.

Images