Ship lock metal structure safety detection and evaluation standardization system and method

Abstract

The invention provides a ship lock metal structure safety detection and evaluation standardization system and method, and relates to the technical field of ship lock engineering safety detection. A distributed intelligent sensing module is obtained, and multi-dimensional dynamic parameters of a ship lock metal structure are collected through the distributed intelligent sensing module; the computer sends a starting instruction to the distributed intelligent sensing module through a preset sensor control program, receives and stores dynamic parameters returned by each sensor in real time, and establishes a timestamp index. Compared with the prior art, the method has the following beneficial effects: by integrating multi-dimensional dynamic parameters such as vibration acceleration, temperature gradient, corrosion current density and the like, the state change of the ship lock metal structure under dynamic load and severe environment can be comprehensively captured, and the sampling frequency is automatically adjusted in combination with a trigger type sampling mechanism; therefore, the transient response under the sudden load is effectively captured, early damage missed judgment caused by only monitoring static parameters is avoided, and the actual safety condition of the structure is reflected more truly.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of ship lock engineering safety detection, in particular to a ship lock metal structure safety detection and evaluation standardization system and method. BACKGROUND

[0002] The ship lock metal structure is the core load-bearing component of the water transport hub, which has been subjected to dynamic water pressure, ship impact load and complex environmental corrosion for a long time. Its safety state is directly related to the smoothness and operation safety of the water transport channel. With the continuous growth of shipping volume and the extension of structure service time, the demand for accurate identification of early damage, dynamic response evaluation and full-process standardized detection of the structure is increasingly urgent, and a standardized detection and evaluation method that can integrate multi-dimensional parameters and adapt to dynamic conditions is needed to ensure the safe operation and maintenance of the ship lock metal structure.

[0003] In patent No. CN113624273A, a ship lock miter gate online monitoring system and method are disclosed, which mainly monitors parameters through stress sensors, inclination sensors and crack sensors distributed on the miter gate to realize basic state monitoring function. However, this technical solution only covers static stress and simple data fusion, does not include dynamic parameters such as vibration acceleration, temperature gradient, corrosion current density and cross-scale damage model, and cannot accurately capture dynamic loads such as ship impact and early damage in harsh environments such as low temperature and high humidity. At the same time, it lacks standardized detection process design, dynamic sampling trigger mechanism and quantitative damage evaluation logic, and it is difficult to solve the core technical problems such as non-uniform detection standard, poor adaptability to dynamic conditions and one-sided damage evaluation. SUMMARY

[0004] In view of the above-mentioned deficiencies of the prior art, the technical problem to be solved by the present application is to provide a ship lock metal structure safety detection and evaluation standardization system and method, which can integrate multi-dimensional dynamic parameters such as vibration, temperature and corrosion, construct a standardized detection and evaluation process, and realize accurate identification and safety grade determination of dynamic damage of ship lock metal structure.

[0005] To solve the above technical problems, the technical solution adopted by the present application is as follows: the present application provides a ship lock metal structure safety detection and evaluation standardization system and method, comprising the following steps: S1, acquiring a distributed intelligent sensing module, collecting multi-dimensional dynamic parameters of the ship lock metal structure through the distributed intelligent sensing module; the computer sends a start instruction to the distributed intelligent sensing module through a preset sensor control program, receives and stores the dynamic parameters returned by each sensor in real time, and establishes a timestamp index; S2. High-frequency noise suppression and feature extraction are performed on the parameters collected by S1 to obtain feature vectors representing the dynamic response of the structure. The computer calls the signal processing algorithm library to perform preprocessing on the dynamic parameters stored in S1, extracts feature quantities through the feature calculation subroutine, and concatenates them into feature vectors according to a preset format. S3. Obtain historical state data. Based on the feature vector and historical state data, obtain the predicted state parameters through a dynamic state prediction and fusion algorithm. The computer loads the historical state database, takes the feature vector as input, runs the state prediction model, iteratively calculates and outputs the predicted state parameters. S4. Based on the predicted state parameters, calculate the damage index and output the comprehensive safety level through the standardized damage assessment model; the computer calls the damage assessment algorithm, substitutes the predicted state parameters to calculate indicators such as fatigue damage degree and corrosion depth, and outputs the comprehensive safety level through the safety level determination logic.

[0006] In the preferred embodiment, step S1 consists of the following steps: S11. Vibration acceleration is monitored using a MEMS accelerometer array. Arranged at key nodes of the gate support arm, monitoring frequency Minimum monitoring frequency ; The computer initializes the MEMS accelerometer through the sensor driver, sets the sampling frequency parameters, and receives the vibration acceleration signal output by the sensor in real time. And store it in the cache; S12. A fiber optic temperature sensor network is used to monitor the temperature gradient. Distributed along the weld seam; S13. The computer receives and converts the current signal output by the corrosion current density electrode by controlling the sampling period of the electrode, thereby obtaining the corrosion current density. Sampling period Sampling interval ; S14. Establish a triggered sampling mechanism: The computer compares the vibration acceleration in the buffer area in real time. With acceleration threshold When vibration acceleration At that time, the sampling frequency registers of the MEMS accelerometer and dynamic water pressure sensor are dynamically adjusted via sensor control commands, starting from the base sampling frequency. Switch to high frequency sampling ; S15. The computer loads the environmental parameter calibration library, calls the corresponding signal attenuation coefficient based on real-time temperature and humidity data, and performs a correction algorithm on the original corrosion current signal to compensate for signal distortion caused by environmental factors. In the preferred embodiment, step S2 consists of the following steps: S21. The computer calls the wavelet analysis toolbox to analyze the vibration acceleration. Wavelet packet decomposition was performed, using the db4 wavelet and loading the db4 wavelet basis functions, on the data acquired by S1. implement Layer wavelet packet decomposition, using frequency band filtering subroutine for localization The corresponding decomposition coefficients are then used to run an energy calculation algorithm to obtain the vibration energy characteristics. ;in, Represented as low-frequency threshold, Represented as high-frequency threshold, This is expressed as the number of decomposition levels; S22. The computer sets the sliding window parameters for the dynamic water pressure signal. Perform a sliding window filtering operation with a window length of [value missing]. Within each window, the extreme value calculation function is called to obtain... and The difference between the two values ​​is used to obtain the dynamic load amplitude. The formula for calculating the dynamic load amplitude is: ; S23, The computer obtains information through the water level sensor. The window length calibration algorithm is invoked based on the rate of rise and fall of the water level. The numerical range dynamically adjusts the window length. Parameter values; S24. The computer, through a data integration program, integrates the vibration energy characteristics... Dynamic load amplitude Temperature gradient Corrosion current density Aligned by timestamp, concatenated into a feature vector. And store it in the feature database.

[0007] In the preferred embodiment, step S3 specifically involves the following steps: S31. Constructing the state vector The data structure, in which Represented as stress, Expressed as inclination angle, Expressed as corrosion depth, , , As vector elements, initialize the vector storage space; S32. Obtain the state transition matrix by importing structural parameters through finite element simulation. Simultaneously, a scheduled task is set to dynamically update the state transition matrix by calling the material degradation model. The matrix parameters are updated periodically. ; S33. The computer constructs nonlinear observation equations using a matrix operation library. The mathematical model in which Represented as an observation vector, Represented as an observation matrix, Represented as observation noise, the observation matrix is ​​set. The initial value will be the observation noise. Model it as a Gaussian distribution and store its parameters; S34. Wavelet packet vibration energy characteristics and dynamic load amplitude Vibrational energy characteristics will be used as input variables. and dynamic load amplitude Substituting the values ​​into the filtering equation, the prediction and update iterative process is executed. The extended Kalman filter algorithm is used for iterative updates, and the updated state estimate is output after each iteration. .

[0008] In the preferred embodiment, step S4 consists of the following steps: S41, Preset fatigue limit Material constants and cycle life Parameters, substitute into the preset ones , , Parameters, based on stress Perform a summation operation to obtain the fatigue damage degree. The calculation formula is: ; S42. The computer, through a modal analysis program, analyzes the vibration energy characteristics... After determining the vibration frequency type, the correction coefficient calculation algorithm is called to determine the vibration mode correction coefficient. The value of the vibration mode correction coefficient is given. With fatigue damage degree Multiply to adjust the weights; S43, Set time interval ,according to and time interval The corrosion depth is obtained by performing fractional calculations. The calculation formula is: ,in This represents the initial corrosion depth. Expressed as electrochemical equivalent, Expressed as material density, Expressed as the number of electrons transferred. It is expressed as Faraday's constant; S44, Based on temperature gradient Calculate the compensation coefficient, and multiply the compensation coefficient by the corrosion rate calculation result to complete the adjustment; S45. Constructing a comprehensive security level using the Analytic Hierarchy Process (AHP). According to fatigue damage degree and corrosion depth The system compares the data with a preset threshold and outputs the overall security level based on the judgment logic. ; In a preferred embodiment, the triggered sampling mechanism in step S14 further includes: Set temperature gradient threshold Real-time computer monitoring and The magnitude relationship when the temperature gradient Simultaneously, encrypted sampling of corrosion current density is initiated, and a command is sent to the corrosion current density electrode to change the value of the sampling interval register from the sampling interval. Modified to encrypted sampling interval .

[0009] In the preferred embodiment, the window length of the sliding window filtering in step S22 is... According to the rate of rise and fall of water level Perform classification, and call the window length adjustment function based on the classification results to adjust the window size accordingly. Updated to or Specifically: when At that time, the window length is from shortened to ; when When the window length is extended to ; in, This is represented as the high water level rate threshold. This is represented as the low water level rate threshold. This indicates shortening the window length. This indicates that the window length has been extended.

[0010] In the preferred embodiment, the state transition matrix in step S32 The update is based on a material degradation model. The computer calls a material parameter update program and periodically reads... and Specifically: elastic modulus With fatigue damage degree Linear decay, ; Corrosion potential With temperature gradient Index changes, ; Then, correct the state transition matrix based on the calculation results. The element value; in, Represented as the current elastic modulus, This is expressed as the initial elastic modulus. It is represented as the attenuation coefficient. This is represented as the current corrosion potential. This is represented as the initial corrosion potential. It is expressed as a temperature coefficient.

[0011] In the preferred embodiment, the vibration mode correction coefficient in step S42 The calculation is based on wavelet packet vibration energy characteristics. : when When, the correction factor is ; when When, the correction factor is ; when When, the correction factor is ; The computer determines this through an energy range determination program. For the given interval, call the function to calculate the correction coefficient for that interval, and substitute it into... , , , , Parameter calculation ; in, This is represented as the high energy threshold. This is represented as the low energy threshold. This is indicated as a high correction factor. This is indicated as a low correction factor.

[0012] The preferred solution also includes: S5. Based on the security level output by S4, a standardized inspection report is automatically generated. The report embeds dynamic parameter trend charts, damage assessment curves, and maintenance decision recommendations, and is pushed to the maintenance terminal in real time via a wireless transmission module. The computer calls the report generation template, extracts dynamic parameters, damage indicators, and other data from the database, draws trend charts and assessment curves through a chart generation program, matches maintenance recommendations with the security level, integrates them into a standardized report, and sends it to the preset maintenance terminal IP address or device ID via a wireless communication protocol. In a preferred embodiment, the present invention also provides a safety inspection and evaluation system for ship lock metal structures, wherein the method for performing any of the above-mentioned methods includes: The distributed intelligent sensing module is used to realize the multi-dimensional dynamic parameter acquisition mentioned above. The module has a built-in microprocessor that runs the sensor control program, performs parameter acquisition, signal conversion and data preprocessing, and transmits the data to the edge computing unit through the interface. The edge computing unit is used to implement the high-frequency noise suppression and feature extraction described above. The unit has a built-in processor and memory, runs algorithms such as wavelet packet decomposition and dynamic window filtering, processes the received raw data, and outputs feature vectors. The central processing module is used to realize the dynamic state prediction and fusion described above. The module integrates a high-performance processor and a simulation engine, runs a finite element analysis program and an extended Kalman filter algorithm, and calculates the predicted state parameters based on eigenvectors and historical data. The assessment output module is used to implement the standardized damage assessment and report generation described above. The module includes an assessment processor and a communication module, runs the damage assessment model and report generation program, outputs the safety level, and pushes the report through wireless transmission.

[0013] In the preferred embodiment, the distributed intelligent sensing module includes: MEMS accelerometer array, with a monitoring frequency of not less than The arrangement density is not less than At key nodes of the gate support arm; the sensor is connected to the module microprocessor via the SPI interface, and the microprocessor runs the sampling control program to collect and transmit vibration acceleration data at a set frequency; Fiber Bragg grating temperature sensor network with an accuracy of no less than The spacing along the main weld seam is not greater than Distributed arrangement; the sensor is connected to the grating demodulator, which transmits wavelength data to the microprocessor via RS485 interface, and the microprocessor runs a temperature conversion program to obtain the temperature gradient; Corrosion current density electrode, using platinum-titanium composite electrode material, with a sampling interval of no more than [missing information]. The electrode is connected to an electrochemical workstation, which transmits the current signal to the microprocessor via a USB interface. The microprocessor then runs a signal conversion program to obtain the corrosion current density. in, This is expressed as the sensor arrangement density. This is expressed as the sensor spacing.

[0014] In the preferred embodiment, the edge computing unit incorporates a wavelet packet decomposition algorithm and a dynamic window filtering program, with a processing delay of no more than [value missing]. Supports vibration signal frequency bands Energy features are extracted in real time; the unit processor loads the algorithm library to process the input raw signal in parallel, and a real-time scheduler ensures that the processing delay does not exceed [the specified threshold]. The extracted energy features are then stored in the feature cache area. in, This indicates a processing delay.

[0015] In the preferred embodiment, the central processing module integrates a finite element simulation engine and an extended Kalman filter algorithm, with an update cycle of no more than [missing information]. To ensure that the prediction error is no greater than ; Module processor according to The finite element simulation engine is periodically called to update the state transition matrix, while the extended Kalman filter algorithm is run for state estimation. An error verification program ensures that the prediction error is within acceptable limits. Within the range; in, This is represented as the prediction error threshold.

[0016] This invention provides a standardized system and method for safety inspection and evaluation of ship lock metal structures. Through the coordination between the aforementioned structures, it offers the following advantages compared to existing methods: First, by integrating multi-dimensional dynamic parameters such as vibration acceleration, temperature gradient, and corrosion current density, it can comprehensively capture the state changes of the lock metal structure under dynamic loads and harsh environments. Combined with a trigger-based sampling mechanism, it can automatically adjust the sampling frequency, thereby effectively capturing the transient response under sudden loads and avoiding early damage omissions caused by monitoring only static parameters, thus more realistically reflecting the actual safety status of the structure. Secondly, by constructing a unified testing process, evaluation logic, and standard library, the problems of inconsistent testing standards and data collection methods among different units can be solved, making the testing results of different locks or the same lock at different times comparable, and providing a unified basis for the safety management of the entire life cycle of the structure. Third, by designing a trigger-based sampling mechanism and parameter adjustment logic adapted to working conditions, the monitoring parameters can be dynamically optimized according to the actual stress on the structure and environmental conditions, avoiding the insufficient accuracy of fixed monitoring modes under complex working conditions, thereby improving the accuracy of monitoring and evaluation in dynamic scenarios. Fourth, by introducing a quantitative damage assessment model and a three-level safety level determination logic, it can replace the traditional subjective assessment method that relies on human experience, reduce human judgment errors, and thus establish an objective damage assessment system. This solves the problem of assessment bias caused by the reliance on a single parameter in traditional methods and provides a reference for operation and maintenance decisions. Fifth, by automatically generating standardized reports that embed dynamic parameter trend charts, damage assessment curves, and maintenance recommendations, and pushing them to the operation and maintenance terminal in real time, the time from detection and assessment to operation and maintenance response can be shortened, realizing closed-loop management from detection, assessment, and decision-making, and improving the efficiency and pertinence of safe operation and maintenance of lock metal structures. Attached Figure Description

[0017] The present invention will be further described below with reference to the accompanying drawings and embodiments: Figure 1 This is a main view diagram of the process structure of this invention; Figure 2 This is a fatigue damage trend diagram of the present invention; Figure 3 This is a schematic diagram of the sensor deployment of the present invention; Figure 4 This is the safety level assessment matrix for this invention; Figure 5 This is a schematic diagram of the structure of the computer device of the present invention. Detailed Implementation

[0018] To better understand the purpose, system architecture, and functional implementation of this embodiment, the embodiments and features in the embodiments of this application can be combined with each other without conflict. The exemplary embodiments disclosed in this application will be described below with reference to the accompanying drawings, including specific technical details disclosed in this embodiment to aid understanding; however, these details should be considered exemplary rather than restrictive. Therefore, those skilled in the art should understand that various improvements and adjustments can be made to the embodiments described herein without departing from the scope and core ideas of the invention. Similarly, for clarity, detailed descriptions of well-known technologies, functions, and structures (such as the basic installation process of conventional sensors, common data transmission protocols, etc.) are omitted in the following description.

[0019] In the field of safety monitoring technology for ship lock metal structures, traditional methods mainly rely on a single type of sensor to acquire structural response data and determine the safety status through preset thresholds. These methods can achieve basic structural status assessments using a limited number of characteristic parameters, thus improving monitoring efficiency to some extent. In most application scenarios, using an assessment method based on fixed thresholds can significantly reduce the frequency of manual inspections and improve the availability of the monitoring system.

[0020] With increasingly stringent safety requirements for ship lock engineering, structural monitoring technology is gradually evolving from single-parameter assessment to multi-parameter fusion analysis to meet the safety assessment needs under complex working conditions. Multi-source information fusion methods can comprehensively process various monitoring parameters such as stress, deformation, and corrosion within a unified analytical framework, typically yielding a more comprehensive structural safety status than traditional single-parameter assessments. In the safety assessment of ship lock structures under complex environments, multi-source fusion methods usually require the integration of structural mechanics models for accurate status identification and safety warnings. However, traditional multi-source monitoring data does not fully encompass the correlation between structural dynamic response and material performance degradation, making it difficult for assessment models to accurately predict the long-term safety status of the structure.

[0021] This solution is based on distributed intelligent sensing, multi-scale signal processing and dynamic fusion evaluation technology. It constructs a standardized method for the entire process of parameter acquisition, feature extraction, state prediction, damage assessment and report output, which solves the problems of lag and one-sidedness in structural safety monitoring under dynamic working conditions and provides technical support for the safe operation and maintenance of large ship locks.

[0022] Example 1 like Figures 1-4 As shown, a standardized method for safety inspection and evaluation of ship lock metal structures includes the following steps: S1: Multi-dimensional dynamic parameter acquisition, which is further divided into the following sub-steps: like Figure 1 As shown, S11: Distributed sensor array deployment Based on the stress characteristics and vulnerable areas of the lock's metal structure, three types of sensors were strategically placed: MEMS accelerometer array deployment: Select key stress nodes such as gate arm hinges, gate shaft columns, and diagonal joints, and arrange sensors at a density of "5 sensors / square meter" to ensure monitoring frequency. The 20Hz frequency can cover high-frequency vibrations caused by ship collisions; the sensor is fixed by a welded support, the support material of which is the same as that of the gate body, to avoid interference of installation stress on the vibration signal.

[0023] Fiber Bragg grating temperature sensor network deployment: Distributed along the main weld seam of the gate and in areas prone to corrosion, enabling real-time capture of temperature gradients. Spatial distribution differences; the sensor optical cable is fixed by a stainless steel C-shaped steel trough, which is welded along the surface of the structure to prevent the optical cable from shifting due to water flow impact.

[0024] Corrosion current density electrode deployment: Platinum-titanium composite electrode material is used, embedded in a pre-set groove on the surface of the metal structure to ensure that the electrode is flush with the surface of the structure; the electrode sampling interval is set by default. It can monitor the current change during the electrochemical corrosion process in real time, providing a data basis for subsequent corrosion depth calculation.

[0025] S12: The triggered adaptive sampling mechanism is set to balance sampling accuracy and data redundancy, and a triggered sampling logic based on multi-parameter thresholds is established. The specific operation is as follows: Initial sampling frequency setting: dynamic water pressure Vibration acceleration Temperature gradient Corrosion current density The initial sampling frequency is 100Hz, which meets the requirements for capturing parameter changes under normal operating conditions.

[0026] First trigger condition (vibration acceleration trigger): Real-time comparison of vibration acceleration collected by MEMS sensor. With threshold, when At the moment of impact, such as when a ship collides, it will automatically... and The sampling frequency was increased to 500Hz to ensure distortion-free signal under transient loads; when After 10 seconds, the sampling frequency dropped back to 100Hz.

[0027] Second triggering condition (temperature gradient trigger): Real-time calculation of temperature gradient The ratio of the temperature difference between two points in space to the distance, when In situations such as seasonal transitions or drastic temperature differences between day and night, the corrosion current density is activated simultaneously. Encrypted sampling, reducing the sampling interval from 1s to 0.2s, is used to capture the effect of sudden temperature changes on the corrosion rate; when After 5 minutes, the sampling interval was restored to 1 second.

[0028] S13: Adaptation treatment for low temperature and high humidity environments Specialized packaging and signal calibration processes are employed to ensure data acquisition accuracy in harsh environments characterized by low temperatures and high humidity. Moisture-proof encapsulation for sensors: The terminals of the MEMS accelerometer and the corroded current density electrode are sealed with silicone rubber and externally encased in a DN40 stainless steel protective tube filled with moisture-proof cotton to prevent short circuits or signal drift caused by condensation intrusion; the fiber optic cable connectors of the fiber optic grating sensor are sealed with heat-shrink tubing to prevent moisture from entering and affecting the grating reflection signal.

[0029] Corrosion current signal calibration: The signal attenuation coefficient under low temperature and high humidity conditions was obtained through laboratory pre-experiments. A calibration algorithm was built into the acquisition terminal to calibrate the original corrosion current signal. Make corrections, the correction formula is as follows ,in The environmental attenuation coefficient is dynamically adjusted based on real-time temperature and humidity to ensure improved accuracy of corrosion current signal acquisition.

[0030] After S1 is executed, the original signal sequence is output. This sequence serves as the input data for S2.

[0031] S2: High-frequency noise suppression and feature extraction. Based on the original signal output from S1, S2 separates effective features from noise using multi-scale signal processing techniques to generate feature vectors representing the dynamic response of the structure. This is further subdivided into the following sub-steps: S21: Wavelet packet decomposition of the vibration acceleration signal, specifically for the triaxial vibration acceleration acquired in S1. This includes high-frequency vibrations from ship impacts and low-frequency noise from water level fluctuations. Wavelet packet decomposition technology is used to extract the effective frequency band energy features, as follows: Signal preprocessing: processing the raw signal The DC component of the signal is removed to eliminate the influence of sensor zero drift on subsequent analysis; at the same time, the signal is normalized to scale the amplitude to the [1,1] interval to avoid analysis bias caused by differences in signal amplitude on different axes.

[0032] Wavelet packet decomposition execution: The db4 wavelet is selected as the base wavelet for the preprocessed packet. The signal is decomposed into 5 levels to obtain wavelet packet coefficients in 32 frequency bands. ( Based on the structural vibration characteristics, coefficients corresponding to the 5-15Hz frequency band were selected (this frequency band is the main vibration frequency band of the structure caused by ship impact, excluding water level fluctuation noise <5Hz and electromagnetic interference >15Hz).

[0033] Frequency band energy characteristic calculation: coefficients of the selected 5~15Hz frequency band The energy values ​​of each frequency band are calculated and summed to obtain the wavelet packet energy characteristics. The calculation formula is: ; in, This represents the number of wavelet packet coefficients corresponding to the 5~15Hz frequency band. The number of sampling points. For the first Each frequency band The wavelet packet coefficients at time 10:00. This is the energy value of the coefficient. This feature enables the identification of vibration energy in structural cracks up to 1 mm in size.

[0034] S22: Sliding window filtering of dynamic water pressure signal Dynamic water pressure collected by S1 A sliding filter technique with dynamically adjusted window length is used to calculate the dynamic load amplitude. The operation is as follows: Window length is dynamically determined based on the water level rise and fall rate collected by S1. Adjust the length of the sliding window in real time The specific rules are as follows: when (High water level fluctuation scenario): Window length The response time has been reduced from 100ms to 50ms to improve the response speed to rapidly changing loads; when (Conventional water level fluctuation scenario): Window length Hold for 100ms; when (Low water level fluctuation scenario): Window length The time was extended to 200ms to enhance noise suppression.

[0035] Sliding window filtering is performed with a defined window length. right The signal is subjected to sliding filtering, and the maximum value within each window is calculated. and minimum value The difference between the two is the dynamic load amplitude corresponding to that window. The calculation formula is: ; in, For the window The maximum value of dynamic water pressure at any given time (unit: kPa). For the window Minimum dynamic water pressure at any given time (unit: kPa). It can intuitively reflect the intensity of water pressure fluctuations, providing load input for subsequent state prediction.

[0036] S23: Feature Vector Integration Wavelet packet energy features extracted from S21 Dynamic load amplitude calculated by S22 The temperature gradient collected by S1 Corrosion current density Perform dimension alignment and concatenation to generate feature vectors representing the dynamic response of the structure. This feature vector serves as the core input to S3, and it is crucial to ensure the consistency of the timestamps for all parameters (achieved through the clock synchronization function of the edge computing unit, with synchronization errors minimized). 1ms).

[0037] S3: Dynamic State Prediction and Fusion. Based on the feature vectors output by S2 and historical state data, S3 achieves accurate prediction of structural stress, tilt angle, and corrosion depth through finite element-driven state space modeling and extended Kalman filtering (EKF). This is further subdivided into the following sub-steps: S31: Construction of Three-Dimensional State Vectors Based on the safety assessment requirements of the lock's metal structure, a three-dimensional state vector including "stress tilt angle corrosion depth" is constructed. As the core object for state prediction, its expression is:

[0038] in, for The stress values ​​of key structural components at all times. for The tilt angle of the structure at any given moment reflects the degree of structural deformation. for The erosion depth of the structure at any given time; simultaneously, historical monitoring data is retrieved to obtain the state matrix of the previous time step. , as the initial value for state prediction.

[0039] S32: Finite element model-driven state-space model establishment. Using ANSYS finite element simulation and material degradation modeling, the parameters of the state-space model are constructed, including the state transition matrix. Input matrix Observation matrix The operation is as follows: State transition matrix Acquisition: Based on the design drawings of the lock's metal structure, a full-size finite element model was established; the structural response under different loads was simulated, and the state vector was obtained by fitting the model. and The mapping relationship, i.e., the state transition matrix. (3×3 matrix), which reflects the temporal evolution of the structural state.

[0040] State transition matrix Dynamic updates: Taking into account the degradation of material properties over service time, updates are performed hourly based on real-time monitoring data. The update logic is based on two types of material parameter models: 1. Degenerative model of elastic modulus: elastic modulus With fatigue damage degree Linear decay, the formula is: ,in The initial elastic modulus of the material. for The elastic modulus at time t, with 0.2 as the attenuation coefficient; 2. Corrosion Potential Degradation Model: Corrosion Potential With temperature gradient Exponential change, formula is ,in The initial corrosion potential at room temperature is 0.05, and the temperature influence coefficient is calibrated through electrochemical experiments. Based on the two models mentioned above, the material parameters of the finite element model are corrected, and then the state transition matrix is ​​updated. This ensures that the model matches the actual service condition of the structure.

[0041] Input matrix With observation matrix Determine: Input matrix (3×2 matrix) is used to associate the load input in the eigenvectors. ) and state vector The observation matrix was obtained through finite element simulation fitting. (4×3 matrix) is used to associate state vectors The observed vector, i.e. the feature vector output by S2, is obtained by linear regression fitting.

[0042] S33: Extended Kalman Filter (EKF) Fusion Iteration: The EKF algorithm is used to implement the iterative process of "state prediction observation update" to correct the prediction error of the state vector. The specific steps are as follows: Step S331: State Prediction Based on the state transition matrix State at the previous moment Predict the prior state at the current moment. The formula is: ; in, The load input vector output by S2. The noise is the process noise, which follows a mean of 0 and a covariance of . Gaussian distribution, It is a 3×3 diagonal matrix, with diagonal elements Calibration was performed using experimental data.

[0043] Step S332: Covariance prediction, calculate prior states covariance matrix The formula is: ; in, The state of the previous moment The covariance matrix, for The transpose of .

[0044] Step S333: Kalman gain calculation, based on the observation matrix. Prior covariance Covariance of observation noise Calculate Kalman gain The formula is: ; in, To observe the noise covariance (a 4×4 diagonal matrix, where the diagonal elements are set according to the sensor accuracy, such as...) correspond (observation error) for The transpose of the matrix, This represents finding the inverse of a matrix.

[0045] Step S334: State update, based on the observation vector output from S2. With Kalman gain Correcting the prior state , obtain the posterior state That is, the final predicted state parameters, the formula is: ; in, The observation residual reflects the deviation between the predicted value and the actual observed value.

[0046] Step S335: Covariance Update Update post-test status covariance matrix To prepare for the next iteration, the formula is: ; in, It is a 3×3 identity matrix.

[0047] After S3 is executed, the predicted state parameters are output. ,in To predict stress, To predict dip angle, To predict corrosion depth.

[0048] like Figure 4 As shown, S4: Standardized Damage Assessment. Based on the predicted state parameters output by S3, S4 uses a standardized fatigue damage and corrosion depth calculation model, combined with three-level safety level logic, to achieve a quantitative assessment of the structural safety status. Specifically, it is broken down into the following sub-steps: like Figure 2 As shown, S41: Fatigue damage calculation, based on Miner's linear cumulative damage theory, according to the predicted stress output from S3. Based on the fatigue characteristics of metallic materials, the fatigue damage degree is calculated. The operation is as follows: Step S411: Determination of fatigue limit and cycle life Access the materials database to obtain the fatigue limit of the lock's metal structure materials (such as Q345 steel). and cycle life under different stress levels. .

[0049] Step S412: Calculation of vibration mode correction coefficients Considering the influence of vibration frequency on fatigue damage, wavelet packet energy extracted based on S2 is used. Calculate vibration mode correction coefficients The correction factor varies with The increase is due to the growth of [something], and the specific rules are as follows: when (Dominated by high-frequency vibrations, such as ship impacts): ; when (Dominated by low-frequency vibrations, such as water level fluctuations): ; when (Mid-to-high frequency vibration transition zone): Linear interpolation calculation, 0.3 is the difference between the maximum and minimum values ​​of the correction coefficient, 0.3 is... The interval length.

[0050] Step S413: Calculate fatigue damage degree based on Miner's linear cumulative damage theory, considering vibration mode correction coefficient. ,calculate Cumulative fatigue damage over time The formula is: ; in, This is the material fatigue constant (a typical value for Q345 steel). The stress ratio reflects the relative magnitude of the actual stress and the fatigue limit. This indicates that the damage from all stress cycles within the monitoring period is accumulated. This is the vibration mode correction coefficient. The value range of is [0,1]. The closer the value is to 1, the closer the structure is to fatigue failure.

[0051] S42: Corrosion depth calculation, based on Faraday's law of electrolysis, using the initial predicted corrosion depth value output from S3. Corrosion current density collected by S1 By combining temperature gradient compensation, the actual corrosion depth is calculated. The operation is as follows: Step S421: Calculation of temperature gradient compensation coefficient Considering the effect of temperature on the corrosion rate, the temperature gradient collected by S1 is used. Calculate the temperature compensation coefficient The rule is "for every 10°C increase, the corrosion rate correction factor increases by 15%", and the formula is:

[0052] in, This is the reference length for the temperature gradient. This refers to the temperature difference over a 1m length, and 0.15 is the corrosion rate increment coefficient for every 10℃ increase in temperature, calibrated through corrosion experiments on Q345 steel at different temperatures.

[0053] Step S422: Corrosion depth calculation, based on Faraday's electrolysis law, combined with temperature compensation coefficient. ,calculate Actual corrosion depth at any given time The formula is:

[0054] in, The initial corrosion depth of the structure was obtained through baseline measurements prior to inspection. The electrochemical equivalent of the metallic material is represented by a typical value for Q345 steel. for The corrosion current density at any given time needs to be converted to A / m² for calculation. The sampling interval is... For material density, This represents the number of electrons transferred by the metal ion. For Faraday's constant, This is the temperature gradient compensation coefficient.

[0055] S43: Comprehensive safety level determination, based on the three-level logic of the analytic hierarchy process (AHP), uses the AHP to determine the "fatigue damage degree". Corrosion depth Predicting the dip angle The weight of "" is combined with the critical threshold to define the comprehensive security level. (Level 1 is dangerous, Level 2 is a warning, and Level 3 is safe). The specific judgment logic is as follows: Level 1 (Hazard): Meets any of the following conditions: (Fatigue damage nearing failure); , This represents the critical corrosion depth. , This is the critical tilt angle.

[0056] Level 2 (Warning): Meets all of the following conditions: (Moderate cumulative fatigue damage); and (The corrosion depth is close to the critical value); and (Moderate tilt deformation).

[0057] Level 3 (Safety): Meets all of the following conditions: (Minor fatigue damage); (Slight corrosion depth); (Slight tilt deformation).

[0058] After S4 is executed, the fatigue damage level is output. Corrosion depth With overall security level .

[0059] S5: Standardized test report generation and real-time push. Based on the security assessment results output by S4, S5 automatically generates standardized test reports and pushes them to the operation and maintenance terminal, realizing a closed loop of "assessment decision-making". It is specifically divided into the following sub-steps: S51: Standardized Report Content Integration In accordance with the requirements of the "Technical Specification for Prototype Observation of Hydraulic Structures in Water Transport Engineering", a report framework was constructed, embedding multi-dimensional evaluation data. Specific content includes: Basic information module: Lock name, detection time, sensor deployment location diagram, detection status; Dynamic parameter trend graph: embedded from S1 acquisition , , , Time series trend chart (data from the last 24 hours), with abnormal fluctuation points marked; Damage assessment curve: embedded S4 calculation Cumulative curve (data from the last 30 days) Growth curve (data from the last 90 days), with the critical threshold line marked; Security Level and Maintenance Recommendations: Determine the overall security level of S4 output. And associated with targeted maintenance suggestions, such as It was suggested that "navigation should be suspended immediately, and weld inspection and structural reinforcement should be carried out." It was recommended that "the repainting of the corroded area and stress retesting be completed within 30 days"; It is recommended to "maintain the regular inspection frequency and update the assessment once per quarter".

[0060] S52: Wireless Transmission and Terminal Push Using LoRa technology through the wireless transmission module of the edge computing unit, which has strong anti-interference capabilities, standardized reports are pushed to designated operation and maintenance terminals in real time in PDF format, and stored in the cloud database at the same time. After the push is completed, a "report delivered" feedback signal is generated to ensure that operation and maintenance personnel can obtain the evaluation results in a timely manner.

[0061] Example 2 This system serves as the hardware platform for the aforementioned methods, employing a four-layer architecture: perception layer, edge layer, core layer, and application layer. The functions and methodological steps of each layer correspond to each other, ensuring fully automated execution of the entire process. The perception layer is a distributed intelligent perception module: corresponding to method S1, including a MEMS accelerometer array, a fiber optic temperature sensor network, and a corrosion current density electrode, to achieve accurate acquisition of multi-dimensional dynamic parameters; The edge layer consists of edge computing units: corresponding to method S2, it incorporates a wavelet packet decomposition algorithm, a dynamic window filtering program, and a clock synchronization module to handle latency. It can complete high-frequency noise suppression and feature extraction in real time within 50ms; The core layer is the central processing module: corresponding to method S3, it integrates the ANSYS finite element simulation engine and the extended Kalman filter algorithm, updates the state-space model parameters every 10 minutes, and predicts the error. 5%, achieving dynamic state prediction and fusion; The application layer is the assessment output module: corresponding to methods S4 and S5, with built-in standardized damage assessment model, report generation template and wireless transmission module, which can automatically complete security level determination, report generation and operation and maintenance push.

[0062] The distributed intelligent sensing module includes a MEMS accelerometer, a fiber optic temperature sensor, and a corrosion current density electrode.

[0063] Edge computing units include processors and storage units.

[0064] Central Processing Module: Processor: Intel Xeon E3 1230v5, clock speed 3.4GHz; Simulation engine: ANSYS Mechanical APDL, which supports multiphysics coupling simulation; Algorithm latency: EKF iteration latency 10ms, state-space model update delay 1 min.

[0065] The evaluation output module transmits data wirelessly, and reports are generated in PDF / Excel formats. The terminal supports Windows / Linux system monitoring screens and Android / iOS mobile apps.

[0066] Example 3: The scene was set as a 1:10 scale model of the Three Gorges Dam ship lock miter gate to simulate static loads, periodic loads, and a corrosive environment. Sensors are deployed according to S11: MEMS sensors are placed at the hinge of the model arm (5 per square meter), fiber optic grating sensors are placed along the weld seam (0.5m spacing), and corrosion electrodes are embedded in the underwater area of ​​the model. Collect data under three operating conditions according to S21-S22 (static load 100kPa, periodic load 50~150kPa@2Hz, corrosion current 10kPa). A / cm²), cross-validation determined the optimal number of wavelet packet decomposition layers to be 5, and the base length of dynamic window filtering was 100ms; Following steps S32-S33, the EKF process noise covariance is calibrated by fitting finite element simulation and experimental data. Observation noise covariance ; The fatigue limit of Q345 steel was determined using 100 sets of failure test data according to S43. Critical corrosion depth Critical Inclination Angle ; Output the pre-trained algorithm parameters to provide a foundation for field applications.

[0067] Example 4: Applied to water level rise and fall rates of 0.8 m / min, where water flow turbulence noise is significant, water pressure fluctuations and structural vibrations need to be closely monitored; S12: Vibration acceleration trigger threshold Temperature gradient trigger threshold ; S22: Because The sliding window length has been reduced from 100ms to 50ms; S33: EKF process noise covariance (Increase the noise margin for stress prediction); S2 Extraction (High-frequency vibrations from ship impact) (Water pressure fluctuation amplitude); S3 Prediction (Actual measured stress value: 185 MPa, error: 2.7%) ; S4 calculation , ( ),determination (Warning); Maintenance recommendation: "Complete the stress retest of the gate arm within 30 days and check for microcracks in the welds." Example 5: Applied to low-temperature and high-humidity corrosion scenarios, with ambient temperatures of 8℃~0℃ and humidity of 95%, condensation easily forms on the structural surface, significantly increasing the corrosion rate. S13: The corrosion electrode is sealed with silicone rubber and encapsulated with a stainless steel protective tube, and filled with moisture-proof cotton. S42: Temperature gradient ,calculate ; S41: Low vibration frequency ( ), ; S1 collection A / cm² (signal drift reaches 50% without encapsulation, and drift after encapsulation) 5%) S4 calculation (The calculated value without compensation is 0.9 mm / month, which is 96% consistent with the experimental value of 1.25 mm / month with the strip). S4 Judgment , ( ), ,determination (Warning); Maintenance recommendation: "Reapply anti-corrosion coating to the underwater area of ​​the gate, using low-temperature resistant epoxy coating"; Example 6 It is applied to sudden load scenarios of ship collisions. A 5,000-ton ship accidentally hits the gate while docking, with an impact energy of 600kJ, requiring a rapid response to transient damage. S12: Moment of impact The trigger sampling frequency was increased to 500Hz, and the corrosion current sampling interval was shortened to 0.2s; S32: Temporarily change the state transition matrix The weight of the mid-tilt angle was increased from 0.3 to 0.8 to prioritize capturing the structural rotation response; S41: , ; Execution result: S2 was extracted 80ms after the impact. , ; S3 Prediction (Actual tilt angle measured value: 1.45) (error 3.4%) ; S4 calculation (Sudden impact caused a sharp increase in fatigue damage), judgment (Warning); Push delay: It only takes 15 seconds for the report to be generated and pushed to the operation and maintenance terminal, and the operation and maintenance personnel can arrive at the site within 10 minutes; Example 7 Further explanation in conjunction with Example 1, such as Figure 5 The structure shown is... Figure 5 A schematic diagram of the structure of a computer device provided in an embodiment of this application. The computer device includes: Processor, memory, communication bus, and computer programs stored in memory that can run on the processor.

[0068] The processor can call the computer program in memory to implement the standardized system and method for safety detection and evaluation of lock metal structures provided in the above embodiments. The method includes: S1, acquiring a distributed intelligent sensing module to collect multi-dimensional dynamic parameters of the lock metal structure; the computer sends a start command to the distributed intelligent sensing module through a preset sensor control program, receives and stores the dynamic parameters returned by each sensor in real time, and establishes a timestamp index; S2, performing high-frequency noise suppression and feature extraction on the parameters collected in S1 to obtain a feature vector characterizing the dynamic response of the structure; the computer calls a signal processing algorithm library to process the parameters stored in S1. The dynamic parameters undergo preprocessing, extracting feature quantities through a feature calculation subroutine and concatenating them into a feature vector according to a preset format; S3, acquiring historical state data, and obtaining predicted state parameters through a dynamic state prediction and fusion algorithm based on the feature vector and historical state data; the computer loads the historical state database, takes the feature vector as input, runs the state prediction model, iteratively calculates and outputs the predicted state parameters; S4, based on the predicted state parameters, calculates damage indicators through a standardized damage assessment model and outputs the comprehensive safety level; the computer calls the damage assessment algorithm, substitutes the predicted state parameters to calculate indicators such as fatigue damage degree and corrosion depth, and outputs the comprehensive safety level through the safety level determination logic.

[0069] Furthermore, computer equipment also includes: The Communications Interface (CI) is used for communication between the memory and the processor.

[0070] The memory may include high-speed RAM, and may also include non-volatile memory, such as at least one disk drive.

[0071] If the memory, processor, and communication interface are implemented independently, they can be interconnected via a bus to communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 5 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0072] Furthermore, when the logical instructions in the aforementioned memory can be implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0073] A processor may include one or more processing units, such as an application processor (AP), an application-specific integrated circuit (ASIC), a modem processor, a central processing unit (CPU), an image signal processor (ISP), a controller, memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural network processing unit (NPU). Different processing units may be independent devices or integrated into one or more processors. The controller may serve as a central nervous system and command center. The controller generates operation control signals based on instruction opcodes and timing signals to control instruction fetching and execution. The processor may also include memory for storing instructions and data. In some embodiments, the memory in the processor is a cache memory. This memory can store instructions or data that the processor has recently used or that is used repeatedly. If the processor needs to reuse the instruction or data, it can directly retrieve it from the memory. This avoids repeated access, reduces processor waiting time, and thus improves system efficiency.

[0074] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0075] Display devices are used to display images, videos, etc. Display devices may include display panels, which may employ liquid crystal displays (LCDs), organic light-emitting diodes (OLEDs), active-matrix organic light-emitting diodes (AMOLEDs), flexible light-emitting diodes (FLEDs), MiniLEDs, MicroLEDs, Micro-OLEDs, quantum dot light-emitting diodes (QLEDs), etc.

[0076] Alternatively, in a specific implementation, if the memory, processor, and communication interface are integrated on a single chip, then the memory, processor, and communication interface can communicate with each other through an internal interface.

[0077] On the other hand, this application also provides a computer-non-transitory readable storage medium storing a computer program. When executed by a processor, this program implements the above-mentioned standardized system and method for safety inspection and evaluation of lock metal structures. The method includes: S1, acquiring a distributed intelligent sensing module to collect multi-dimensional dynamic parameters of the lock metal structure; the computer sends a start command to the distributed intelligent sensing module through a preset sensor control program, receives and stores the dynamic parameters returned by each sensor in real time, and establishes a timestamp index; S2, performing high-frequency noise suppression and feature extraction on the parameters collected in S1 to obtain a feature vector characterizing the dynamic response of the structure; the computer calls signal processing... The algorithm library preprocesses the dynamic parameters stored in S1, extracts features through a feature calculation subroutine, and concatenates them into a feature vector according to a preset format. S3 acquires historical state data and obtains predicted state parameters based on the feature vector and historical state data using a dynamic state prediction and fusion algorithm. The computer loads the historical state database, takes the feature vector as input, runs the state prediction model, iteratively calculates, and outputs the predicted state parameters. S4 calculates damage indicators and outputs the comprehensive safety level based on the predicted state parameters using a standardized damage assessment model. The computer calls the damage assessment algorithm, substitutes the predicted state parameters to calculate indicators such as fatigue damage degree and corrosion depth, and outputs the comprehensive safety level through safety level determination logic.

[0078] In another aspect, this application also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. The computer program can execute computer instructions. When the computer program is executed by a processor, the computer can execute the standardized system and method for safety inspection and evaluation of lock metal structures provided by the above methods. This method includes: S1, acquiring a distributed intelligent sensing module to collect multi-dimensional dynamic parameters of the lock metal structure; the computer sends a start command to the distributed intelligent sensing module through a preset sensor control program, receives and stores the dynamic parameters returned by each sensor in real time, and establishes a timestamp index; S2, performing high-frequency noise suppression and feature extraction on the parameters collected in S1. The computer obtains feature vectors representing the dynamic response of the structure; it calls the signal processing algorithm library to preprocess the dynamic parameters stored in S1, extracts feature quantities through the feature calculation subroutine, and concatenates them into feature vectors according to a preset format; S3, it acquires historical state data, and obtains predicted state parameters through a dynamic state prediction and fusion algorithm based on the feature vectors and historical state data; the computer loads the historical state database, takes the feature vectors as input, runs the state prediction model, iteratively calculates and outputs the predicted state parameters; S4, it calculates damage indicators and outputs the comprehensive safety level based on the predicted state parameters through a standardized damage assessment model; the computer calls the damage assessment algorithm, substitutes the predicted state parameters to calculate indicators such as fatigue damage degree and corrosion depth, and outputs the comprehensive safety level through the safety level determination logic.

[0079] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus or device (such as a computer-based system, a processor-included system or other system that can fetch and execute instructions from, an instruction execution system, apparatus or device).

[0080] For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit a program for use in or in conjunction with an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing. Furthermore, a computer-readable medium can even be paper or other suitable media on which the program can be printed, since the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0081] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0082] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0083] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0084] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other.

[0085] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0086] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A method for standardized safety inspection and evaluation of ship lock metal structures, characterized by, The method comprises the following steps: S1, acquiring a distributed intelligent sensing module, collecting multi-dimensional dynamic parameters of the ship lock metal structure through the distributed intelligent sensing module; the computer sends a start instruction to the distributed intelligent sensing module through a preset sensor control program, and stores the dynamic parameters returned by each sensor in real time, and establishes a time stamp index; S2, high-frequency noise suppression and feature extraction are performed on the parameters collected in S1 to obtain a feature vector representing the dynamic response of the structure; the computer calls a signal processing algorithm library, performs preprocessing on the dynamic parameters stored in S1, extracts feature quantities through a feature calculation subroutine, and splices them into a feature vector in a preset format; S3, obtaining historical state data, and obtaining predicted state parameters through a dynamic state prediction and fusion algorithm according to the feature vector and the historical state data; the computer loads a historical state database, takes the feature vector as input, runs a state prediction model, iteratively calculates and outputs predicted state parameters; S4, according to the predicted state parameters, calculating damage indicators and outputting a comprehensive safety level through a standardized damage assessment model; the computer calls a damage assessment algorithm, substitutes the predicted state parameters to calculate fatigue damage degree, corrosion depth and other indicators, and outputs a comprehensive safety level through safety level determination logic.

2. The method for safety inspection and evaluation of lock metal structure according to claim 1, characterized in that, The specific steps of step S1 are: S11, monitoring vibration acceleration by using MEMS acceleration sensor array , arranged at the key node of the gate support arm, monitoring frequency Minimum monitoring frequency ; The computer initializes the MEMS acceleration sensor through a sensor driver, sets a sampling frequency parameter, and receives a vibration acceleration signal output by the sensor in real time And stores to the cache area; S12, monitoring temperature gradient by using fiber grating temperature sensor network , distributed along the weld. S13, the computer receives and converts the current signal output by the electrode by controlling the sampling period of the corrosion current density electrode to obtain the corrosion current density sampling period sampling interval ; S14, Establish a trigger sampling mechanism: computer real-time comparison of the buffer area in the vibration acceleration with the acceleration threshold , when the vibration acceleration , through the sensor control instruction dynamic adjustment of MEMS acceleration sensor and dynamic water pressure sensor sampling frequency register, from the basic sampling frequency Switch to high frequency sampling frequency ; S15, the computer loads an environmental parameter calibration library, calls the corresponding signal attenuation coefficient according to the real-time temperature and humidity data, and executes a correction algorithm on the original corrosion current signal to compensate for signal distortion caused by environmental factors.

3. The method for safety inspection and evaluation of lock metal structure according to claim 2, characterized in that, The specific steps of step S2 are: S21, the computer calls wavelet analysis toolbox, and the vibration acceleration is subjected to wavelet packet decomposition, db4 wavelet is selected, db4 wavelet base function is loaded, and the S1 collected is executed Wavelet packet decomposition is carried out, and the corresponding decomposition coefficients are positioned through a frequency band screening subroutine Vibration energy characteristics are obtained by running an energy calculation algorithm again ; wherein, is represented as a low-frequency threshold value, is represented as a high-frequency threshold value, is represented as a decomposition layer number; S22, the computer sets the sliding window parameters, and the dynamic water pressure signal The sliding window filtering operation is performed, and the window length is In each window, the extreme value calculation function is called to obtain and And the difference between the two is calculated to obtain the dynamic load amplitude The formula for calculating the dynamic load amplitude is: ； S23, the computer obtains , calls the window length calibration algorithm, dynamically adjusts the parameter value of the window length according to the numerical range of the water level rising and falling rate . ; S24, the computer aligns, by a data integration program, the vibration energy features , dynamic load amplitude , temperature gradient , corrosion current density align by timestamp, splice into feature vector and store to feature database.

4. The method for safe inspection and evaluation of lock metal structures according to claim 1, characterized in that, The specific steps of step S3 are: S31, constructing a state vector of the data structure, wherein is represented as stress, is represented as inclination, is represented as corrosion depth, and , , initializing a vector storage space as a vector element; S32, obtain the state transition matrix by importing the structure parameter through finite element simulation At the same time, set the timing task, call the material degradation model to dynamically update the state transition matrix The matrix parameter is updated every ; S33, the computer constructs a nonlinear observation equation through a matrix operation library , wherein is represented as an observation vector, is represented as an observation matrix, is represented as observation noise, and the observation matrix is set to an initial value, and the observation noise is modeled as a Gaussian distribution and its parameters are stored; S34, the wavelet packet vibration energy feature and dynamic load amplitude As an input variable, the vibration energy feature and dynamic load amplitude is substituted into the filtering equation, and a prediction and update iteration process is performed, and the extended Kalman filtering algorithm is iteratively updated, and the updated state estimation value is output once per iteration .

5. The method for safe inspection and evaluation of lock metal structures according to claim 1, characterized in that, The specific steps of step S4 are: S41, preset fatigue limit , material constant , and cycle life parameters, into the preset , , parameters, according to the stress performing a summation operation to obtain the fatigue damage degree , the calculation formula is: ; S42. The computer, through a modal analysis program, analyzes the vibration energy characteristics... After determining the vibration frequency type, the correction coefficient calculation algorithm is called to determine the vibration mode correction coefficient. The value of the vibration mode correction coefficient is given. With fatigue damage degree Multiply to adjust the weights; S43, set time interval , according to and time interval perform fractional operation calculation to obtain corrosion depth , the calculation formula is: , wherein is expressed as initial corrosion depth, is expressed as electrochemical equivalent, is expressed as material density, is expressed as electron transfer number, is expressed as Faraday constant; S44、 according to the temperature gradient A compensation factor is calculated and multiplied by the corrosion rate calculation to complete the adjustment. S45, constructing comprehensive safety level by analytic hierarchy process , comparing fatigue damage degree and corrosion depth with preset threshold value, and outputting comprehensive safety level according to determination logic .

6. The method for safe inspection and evaluation of lock metal structures according to claim 2, characterized in that, The trigger sampling mechanism in step S14 further comprises: Setting temperature gradient threshold , computer real-time monitoring With The size relationship, when the temperature gradient , synchronous start corrosion current density encryption sampling, send instructions to the corrosion current density electrode, modify the value of the sampling interval register from the sampling interval To encryption sampling interval .

7. The method for safe inspection and evaluation of lock metal structures according to claim 3, characterized in that, Window length of the sliding window filtering in step S22 According to the water level rising rate Classify, and call a window length adjustment function according to a classification result, and respectively classify Update to Or Specifically: When the window length is shortened from to ; When the window length is extended to ; wherein, represents a high water rate threshold, represents a low water rate threshold, represents a shortened window length, represents a lengthened window length.

8. The method for safety inspection and evaluation of lock metal structure according to claim 4, characterized in that, In step S32, the state transition matrix is updated based on the material degradation model, and the computer calls a material parameter updating program to periodically read and , in particular: modulus of elasticity with fatigue damage degree linear attenuation, ; corrosion potential with temperature gradient exponential change, ; The element values of the state transition matrix are corrected again according to the calculation results ; wherein, denotes the current elastic modulus, denotes the initial elastic modulus, denotes the decay coefficient, denotes the current corrosion potential, denotes the initial corrosion potential, denotes the temperature coefficient.

9. The method for safe inspection and evaluation of lock metal structures according to claim 5, characterized in that, Vibration mode correction coefficient in step S42 The calculation is based on wavelet packet vibration energy characteristics. : When the correction factor is ; When the correction factor is ; When the correction factor is ; The computer determines the energy interval by an energy interval determination program The corresponding interval is called, and the correction coefficient calculation function is substituted , , , , and other parameters ; wherein, represents a high energy threshold, represents a low energy threshold, represents a high correction factor, represents a low correction factor.

10. A system for safety inspection and evaluation of a ship lock metal structure, characterized in that, A method for executing any one of claims 1-9, comprising: A distributed intelligent sensing module for realizing the multi-dimensional dynamic parameter collection of claim 2; a microprocessor built-in the module runs a sensor control program to perform parameter collection, signal conversion and data preprocessing, and transmits data to an edge computing unit through an interface; An edge computing unit for realizing the high-frequency noise suppression and feature extraction of claim 3; a processor and a memory built-in the unit run wavelet packet decomposition, dynamic window filtering and other algorithm programs to process the received original data and output feature vectors; A central processing module for realizing the dynamic state prediction and fusion of claim 4; the module integrates a high-performance processor and a simulation engine to run a finite element analysis program and an extended Kalman filter algorithm to calculate predicted state parameters based on feature vectors and historical data; An evaluation output module for realizing the standardized damage assessment and report generation of claim 5; the module includes an evaluation processor and a communication module to run a damage assessment model and a report generation program to output a safety level and push a report through wireless transmission.

Images