Ship lock slope displacement monitoring and early warning method and system based on the influence of ship operation

Abstract

The present invention relates to the field of ship lock slope monitoring technology, and in particular to a ship lock slope displacement monitoring and early warning method and system based on the influence of ship hull operation. The method comprises the following steps: real-time acquisition of ship lock slope multi-source data of ship lock slope area nodes to obtain real-time ship lock slope multi-source displacement factor data; ship lock slope displacement prediction processing based on real-time ship lock slope multi-source displacement factor data to generate ship lock slope displacement prediction data; time-series spatial evolution trend analysis and time-series spatial evolution trend analysis of ship lock slope displacement based on ship lock slope displacement prediction data to generate time-space evolution ship lock slope deformation data; ship lock slope displacement monitoring and early warning status evaluation processing based on time-space evolution ship lock slope deformation data to generate ship lock slope displacement monitoring and early warning status evaluation data. The present invention realizes accurate monitoring of ship lock slope displacement by analyzing multiple factors related to ship lock slope.

Description

Technical Field

[0001] The present invention relates to the technical field of ship lock slope monitoring, and in particular to a ship lock slope displacement monitoring and early warning method and system based on the influence of ship hull operation. Background Art

[0002] After the ship lock is built and opened to navigation, in order to ensure the safety of the built ship lock, the safety monitoring requirements for the ship lock are constantly increasing, and the importance of ship lock slope displacement monitoring is becoming more and more prominent. In recent years, displacement monitoring has been the top priority of safety monitoring of medium and high head ship locks. It not only covers the protection of existing structures, the safety status of new structures, and the changes and development of the surrounding environment, especially the high slopes, but also focuses on displacement observation and early warning. Regardless of the safety factor of the ship lock, displacement monitoring is more commonly required than other monitoring. The complexity of ship lock slope displacement monitoring has gradually increased, mainly reflected in the combined effect of multiple factors, including terrain changes, geological conditions, underground layer displacement, hydrological dynamics, and stress changes. However, the existing ship lock slope displacement monitoring and early warning methods are limited to the observation of a single factor, and cannot fully capture the multi-source dynamic information of slope displacement, resulting in insufficient monitoring coverage and data integrity. The monitoring and early warning feedback of the ship lock slope displacement is poor in timeliness and cannot meet the safety requirements of the ship lock during operation. Summary of the invention

[0003] Based on this, the present invention provides a method for monitoring and early warning of lock slope displacement based on the influence of ship hull operation to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a method for monitoring and early warning of lock slope displacement based on the influence of ship operation includes the following steps:

[0005] Step S1: Deploy multi-source sensors in the lock slope area nodes and construct a sensor monitoring network to generate a lock slope monitoring sensor network; collect lock slope multi-source data in real time from the lock slope area nodes through the lock slope monitoring sensor network to obtain real-time lock slope multi-source displacement factor data;

[0006] Step S2: performing ship lock slope displacement prediction processing based on real-time ship lock slope multi-source displacement factor data to generate ship lock slope displacement prediction data;

[0007] Step S3: Based on the lock slope displacement prediction data, the time-series spatial evolution trend analysis of the lock slope displacement is performed to generate the time-space evolution lock slope displacement data; based on the lock slope time-space evolution lock slope displacement data, the time-series spatial evolution trend analysis of the lock slope deformation is performed to generate the time-space evolution lock slope deformation data;

[0008] Step S4: Perform lock slope displacement monitoring and early warning status assessment processing based on the spatiotemporal evolution of lock slope deformation data to generate lock slope displacement monitoring and early warning status assessment data; transmit the lock slope displacement monitoring and early warning status assessment data to the terminal to execute the lock slope displacement monitoring and early warning status feedback operation.

[0009] Further, step S1 includes the following steps:

[0010] By deploying terrain sensors, geological sensors, formation sensors, hydrological sensors, and stress sensors in the nodes of the lock slope area, and building a lock slope monitoring sensor network through terrain sensors, geological sensors, formation sensors, hydrological sensors, and stress sensors;

[0011] Based on the lock slope monitoring sensor network, real-time monitoring and processing of multi-source displacement factors of the lock slope are performed to generate real-time multi-source displacement factor data of the lock slope, wherein the real-time multi-source displacement factor data of the lock slope includes real-time topographic and geomorphic data of the lock slope, real-time geological structure data of the lock slope, real-time stratigraphic and lithological data of the lock slope, real-time hydrological data of the lock slope, and real-time original stress data of the lock slope.

[0012] Further, step S2 includes the following steps:

[0013] Step S21: performing multi-source displacement factor curve fitting processing on the real-time multi-source displacement factor data of the ship lock slope to obtain the ship lock slope displacement fitting factor data;

[0014] Step S22: performing ship lock slope displacement related characteristic analysis based on the ship lock slope displacement fitting factor data to generate ship lock slope displacement related characteristic data;

[0015] Step S23: designing a ship lock slope displacement prediction factor based on the ship lock slope displacement related characteristic data; performing ship lock slope displacement related probability coefficient analysis on the ship lock slope displacement prediction factor to generate a ship lock slope displacement related probability coefficient;

[0016] Step S24: performing optimization related characteristic analysis processing of the ship lock slope displacement according to the ship lock slope displacement related probability coefficient, so as to design an optimized ship lock slope displacement related characteristic matrix;

[0017] Step S25: performing ship lock slope displacement prediction processing according to the optimized ship lock slope displacement related characteristic matrix to generate ship lock slope displacement prediction data.

[0018] Further, step S22 includes the following steps:

[0019] Step S221: performing periodic trend superposition analysis of the ship lock slope displacement fitting factor based on the ship lock slope displacement fitting factor data to generate ship lock slope displacement fitting factor trend data;

[0020] Step S222: performing fitting factor noise correction processing on the lock slope displacement fitting factor trend data to generate corrected lock slope displacement fitting factor trend data;

[0021] Step S223: performing ship lock slope displacement related characteristic analysis based on the corrected ship lock slope displacement fitting factor trend data to generate ship lock slope displacement related characteristic data.

[0022] Further, step S221 includes the following steps:

[0023] Conduct preliminary ship lock slope displacement fitting factor trend analysis based on the ship lock slope displacement fitting factor data to generate preliminary ship lock slope displacement fitting factor trend data;

[0024] Performing periodic analysis of the ship lock slope displacement fitting factor according to the ship lock slope displacement fitting factor data, and generating periodic data of the ship lock slope displacement fitting factor;

[0025] Based on the preliminary lock slope displacement fitting factor trend data and the lock slope displacement fitting factor periodic data, a lock slope displacement fitting factor trend superposition analysis is performed to generate the lock slope displacement fitting factor trend data.

[0026] Further, step S24 includes the following steps:

[0027] The ship lock slope displacement related characteristic matrix is ​​designed according to the ship lock slope displacement related probability coefficient; the ship lock slope displacement related characteristic matrix is ​​sorted by correlation value, and the target ship lock slope stability related probability coefficient is selected for the ship lock slope displacement related characteristic matrix after correlation value sorting, so as to obtain the target ship lock slope displacement related probability coefficient; the ship lock slope displacement related characteristic matrix is ​​optimized and reconstructed based on the target ship lock slope displacement related probability coefficient, so as to generate the optimized ship lock slope displacement related characteristic matrix.

[0028] Further, step S25 includes the following steps:

[0029] Design the linear equation related to the displacement of the ship lock slope according to the optimized characteristic matrix related to the displacement of the ship lock slope;

[0030] The undetermined coefficients for predicting the displacement of the ship lock slope are calculated based on the linear equations related to the displacement of the ship lock slope, and the undetermined coefficients for predicting the displacement of the ship lock slope are generated;

[0031] Based on the undetermined coefficients of lock slope displacement prediction, nonlinear lock slope displacement trend prediction processing is performed to generate lock slope displacement prediction data.

[0032] Further, step S3 includes the following steps:

[0033] Step S31: performing temporal spatial evolution trend analysis of the ship lock slope displacement based on the ship lock slope displacement prediction data, and generating temporal and spatial evolution ship lock slope displacement data;

[0034] Step S32: extracting the temporal and spatial evolutionary ship lock slope deformation correlation features according to the temporal and spatial evolutionary ship lock slope displacement data, and generating the temporal and spatial evolutionary ship lock slope deformation correlation feature data;

[0035] Step S33: performing a time-space evolution ship lock slope deformation associated characteristic state analysis according to the time-space evolution ship lock slope deformation associated characteristic data, and generating time-space evolution ship lock slope deformation associated characteristic state data;

[0036] Step S34: Based on the preset evolution model of the staged deformation rate of the ship lock slope, the temporal spatial evolution trend of the ship lock slope deformation is analyzed on the temporal and spatial evolution ship lock slope deformation associated characteristic state data to generate the temporal and spatial evolution ship lock slope deformation data.

[0037] Further, step S4 includes the following steps:

[0038] Step S41: performing a time-space evolution ship lock slope stability analysis according to the time-space evolution ship lock slope deformation data, and generating time-space evolution ship lock slope stability data;

[0039] Step S42: marking the instability time of the ship lock slope according to the spatiotemporal evolution ship lock slope deformation data, and generating ship lock slope instability time marking data;

[0040] Step S43: Based on the preset lock slope displacement monitoring and early warning rules, the time-space evolution lock slope deformation data, the time-space evolution lock slope stability data and the lock slope instability time mark data are evaluated and processed to generate lock slope displacement monitoring and early warning status evaluation data;

[0041] Step S44: Transmit the lock slope displacement monitoring early warning status assessment data to the terminal to execute the lock slope displacement monitoring early warning status feedback operation.

[0042] This specification provides a ship lock slope displacement monitoring and early warning system based on the influence of ship hull operation, which is used to execute the ship lock slope displacement monitoring and early warning method based on the influence of ship hull operation as described above. The ship lock slope displacement monitoring and early warning system based on the influence of ship hull operation includes:

[0043] The ship lock slope multi-source displacement factor monitoring module is used to generate a ship lock slope monitoring sensor network by deploying multi-source sensors in the ship lock slope area nodes and building a sensor monitoring network; the ship lock slope monitoring sensor network collects the ship lock slope multi-source data in real time at the ship lock slope area nodes to obtain real-time ship lock slope multi-source displacement factor data;

[0044] The ship lock slope displacement prediction module is used to perform ship lock slope displacement prediction processing based on real-time ship lock slope multi-source displacement factor data to generate ship lock slope displacement prediction data;

[0045] The module of temporal and spatial evolution of ship lock slope deformation is used to analyze the temporal and spatial evolution trend of ship lock slope displacement based on the predicted data of ship lock slope displacement, and generate temporal and spatial evolution ship lock slope displacement data; the module of temporal and spatial evolution of ship lock slope deformation is used to analyze the temporal and spatial evolution trend of ship lock slope displacement based on the temporal and spatial evolution ship lock slope, and generate temporal and spatial evolution ship lock slope deformation data;

[0046] The lock slope displacement monitoring and early warning feedback module is used to evaluate and process the lock slope displacement monitoring and early warning status based on the spatiotemporal evolution of the lock slope deformation data, generate the lock slope displacement monitoring and early warning status evaluation data; transmit the lock slope displacement monitoring and early warning status evaluation data to the terminal to execute the lock slope displacement monitoring and early warning status feedback operation.

[0047] The beneficial effect of the present invention is that by deploying multiple types of sensors at key nodes in the lock slope area, a sensor network with comprehensive coverage and high precision can be constructed to realize multi-dimensional monitoring of various influencing factors of the slope. Topographic, geological, stratigraphic, hydrological and stress sensors each focus on different monitoring dimensions, so that comprehensive data of slope terrain changes, geological conditions changes, underground layer movement, hydrological dynamics and internal stress changes can be obtained, which improves the integrity and real-time performance of monitoring. The real-time data of multiple factors such as topography, geology, stratigraphic, hydrological and stress are monitored by the sensor network, providing a dynamic and accurate slope displacement information, timely identifying instability factors, and providing strong data support for risk assessment and emergency response. The generated real-time multi-source displacement factor data of the lock slope can provide multi-dimensional information on the dynamic changes of the slope, including topography, geological structure, stratigraphic lithology, hydrological conditions and original stress state, etc., which is the basis for the safety analysis of the lock slope. Curve fitting processing is performed on the multi-source displacement factor data collected in real time, so that data of different types and dimensions can be unified under a mathematical model, so as to obtain accurate slope displacement fitting factor data. The deviation and inconsistency between data are eliminated, and the slope displacement trend analysis is performed on the slope displacement fitting factor data to quickly capture the potential change law of slope deformation, identify the overall trend of displacement factors, and reflect the trend of stability decline or potential instability, which provides a basis for early warning of slope deformation. By capturing these periodic factors, analysts can better understand the natural fluctuations of slope deformation and the impact of the external environment on slope displacement. In the process of noise correction of displacement trend data, the noise introduced by external factors or equipment errors in the data can be effectively removed to ensure the accuracy and reliability of displacement trend data. By performing relevant feature analysis based on the corrected trend data, the key features of slope displacement, such as displacement rate, acceleration, instability critical point, etc., are extracted. It provides an important basis for in-depth understanding of the dynamic characteristics of slope deformation and identifies potential risk characteristics and signs of instability. By designing slope displacement prediction factors and performing probability coefficient analysis on them, the influence of each prediction factor on slope displacement changes is quantified. Identify the main driving factors of slope instability and evaluate the probability of occurrence of each factor, thereby laying the foundation for the accurate prediction of slope displacement. By using the relevant probability coefficients of lock slope displacement for the design of the characteristic matrix, the multiple factors affecting slope stability can be effectively integrated into a unified analysis framework. This matrix can reflect the relationship between the various factors and their comprehensive impact on slope displacement. The probability coefficients most relevant to the stability of the lock slope are selected after screening and sorting, ensuring that all potential influencing factors are fully considered and the dynamic changes of the slope are fully understood.The linear equations related to the displacement of the ship lock slope are designed through the characteristic matrix, which facilitates the quantification and systematic analysis of the influencing factors of the slope displacement, so as to calculate the undetermined coefficients, accurately determine the specific contribution of each influencing factor to the displacement of the ship lock slope, and quantify the influence of each variable on the slope displacement. When performing nonlinear trend prediction, the undetermined coefficients provide the necessary parameter support for processing complex and nonlinear slope displacement changes. Through this processing, the potential nonlinear change trend in the displacement of the ship lock slope can be better captured and more accurate prediction data can be generated. Nonlinear trend prediction can more accurately reflect the dynamic development process of the slope, especially capturing subtle changes that cannot be explained by traditional linear models. By analyzing the temporal and spatial evolution trends of the predicted data of the ship lock slope displacement, the change process of the slope in different periods and different spatial positions can be fully grasped, the dynamic development law of the slope displacement in time and space can be revealed, and valuable information can be extracted from a large amount of spatiotemporal data, revealing the intrinsic connection between displacement and geological, environmental and other factors, so as to understand the driving mechanism of slope deformation, enhance the explanatory power and applicability of the prediction model, and provide a scientific basis for subsequent monitoring and management. State analysis of the extracted temporal and spatial evolution associated feature data can more comprehensively evaluate the current status and development trend of slope deformation, monitor and evaluate the severity, stability and potential future change direction of slope deformation. Through detailed analysis of the characteristic state, the risk state of the slope can be effectively judged and the impact of slope instability on the safety of the ship lock can be reduced. By using the preset deformation rate evolution model, the deformation rate of the slope is dynamically analyzed in stages to help further refine the deformation process, identify the displacement rate changes in different stages, capture potential accelerated deformation trends, and provide more accurate temporal and spatial evolution data. Based on these analysis results, managers can formulate more detailed prevention and emergency strategies to ensure the long-term stability and safety of the ship lock slope. By performing stability analysis on the temporal and spatial evolution ship lock slope deformation data, the overall stability of the slope is comprehensively evaluated, and the key areas where the slope may be unstable are identified, revealing the stability change trend of the slope under different time and space conditions, ensuring the long-term safety and stability of the ship lock, and achieving global control of the slope displacement state. Therefore, the present invention is a method for monitoring and early warning of ship lock slope displacement based on the influence of ship hull operation, which is not limited to single slope displacement monitoring, and effectively and comprehensively captures dynamic multi-source dynamic information of slope displacement related factors, ensuring the coverage of slope displacement monitoring and data integrity. And through intelligent real-time data analysis, the timeliness of monitoring and early warning feedback of ship lock slope displacement is guaranteed, which can meet the safety requirements of ship locks when the ship hull is in operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments thereof made with reference to the following drawings:

[0049] Figure 1 It is a schematic diagram of the steps of a method for monitoring and early warning of displacement of a ship lock slope based on the influence of ship hull operation according to the present invention;

[0050] Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart;

[0051] Figure 3 for Figure 2 Detailed implementation steps of step S22; DETAILED DESCRIPTION

[0052] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0053] To achieve this, please refer to Figures 1 to 3 The present invention provides a method for monitoring and warning the displacement of a ship lock slope based on the influence of ship movement. In the embodiment of the present invention, please refer to Figure 1 As shown, it is a schematic diagram of the steps of the method for monitoring and early warning of the displacement of the ship lock slope based on the influence of the hull operation of the present invention. The method for monitoring and early warning of the displacement of the ship lock slope based on the influence of the hull operation includes the following steps:

[0054] Step S1: Deploy multi-source sensors in the lock slope area nodes and construct a sensor monitoring network to generate a lock slope monitoring sensor network; collect lock slope multi-source data in real time from the lock slope area nodes through the lock slope monitoring sensor network to obtain real-time lock slope multi-source displacement factor data;

[0055] In the embodiment of the present invention, in the process of deploying sensors at specific regional nodes of the ship lock slope, key locations are selected, and terrain sensors are arranged in areas prone to deformation based on the geological characteristics and hydrological conditions of the slope. These terrain sensors monitor small changes in terrain in real time and record their displacement trends through laser rangefinders and high-resolution inclinometers. The geological sensors are installed inside the slope through drilling holes, and the stress and crack conditions of the geological layer are monitored in real time with the help of high-sensitivity strain gauges and crack extension sensors. The formation sensors are deployed at different formation depths through deep drilling to monitor deep displacement and formation movement, and detect small changes in the deep part of the slope through differential GPS and acceleration sensors. The hydrological sensors are installed in the groundwater seepage channel, and the groundwater level changes and seepage rates are recorded using pressure sensors and water level measuring devices. The stress sensors are installed in the key stress-bearing areas, and the internal stress distribution of the rock and soil is monitored using resistance strain gauges and vibrating wire stress sensors. Through wired and wireless communication technologies, the data of all sensors are collected in real time to the monitoring center to build a stable ship lock slope monitoring network to ensure that both surface and deep information can be captured in real time. After the construction of the ship lock slope monitoring network is completed, the system begins to monitor multi-source displacement data in real time through high-frequency sampling and data synchronization technology. Terrain sensors provide terrain change data, geological sensors record geological structural stress changes, stratum sensors monitor stratum lithology and displacement dynamics at different depths, hydrological sensors feedback groundwater level and seepage changes, and stress sensors record the stress state of each layer of soil and rock. All data are synchronized through a unified timestamp, integrated and processed at the data acquisition terminal, and transmitted to the monitoring center. The processing system analyzes each data type independently to generate real-time multi-source displacement data including terrain, geological structure, stratum lithology, hydrology and original stress data. The data is filtered, denoised, and calibrated to ensure accurate real-time feedback and provide a basis for subsequent displacement warnings.

[0056] Step S2: performing ship lock slope displacement prediction processing based on real-time ship lock slope multi-source displacement factor data to generate ship lock slope displacement prediction data;

[0057] In an embodiment of the present invention, firstly, real-time multi-source displacement factor data of the ship lock slope is obtained, and the data is input into the multi-source displacement factor curve fitting system. The system regards each type of data (such as topography, geology, etc.) as an independent variable, and performs linear or nonlinear fitting by the least squares method. In the fitting process, piecewise linear regression or polynomial fitting technology is used to ensure that the displacement trend of each variable is accurate. The curve generated by fitting removes noise and reflects the real-time displacement trend. Then, the fitting data is processed by time series analysis, and the key data points are fitted by linear regression to generate a preliminary slope displacement trend, which provides a basis for periodic analysis. The Fourier transform algorithm further decomposes the data, identifies the periodic components, divides the data into multiple time periods to extract periodic features, generates a periodic curve, and determines the periodic effects of water level changes, ship passage, etc. on displacement through spectrum analysis. The preliminary trend is combined with the periodic data, and the weighted superposition model is used to integrate short-term fluctuations and long-term trends to generate a displacement change image, and the influence of periodic and trend factors is quantified by multivariate regression analysis to generate superimposed slope displacement trend data. After Kalman filtering or noise filtering of trend data, principal component analysis (PCA) or support vector machine (SVM) is used for feature analysis, and normalization processing is used to identify the variables that have the greatest impact on displacement, such as groundwater level or impact force of hull operation, to generate relevant feature data, providing a basis for early warning modeling. Then, by analyzing the historical changes of each feature variable, the prediction factor of the ship lock slope displacement is designed, and its change rate, cumulative value, etc. are calculated. The probability coefficient is generated by regression analysis, and the influence intensity of each factor is determined by Bayesian probability or maximum likelihood estimation. Subsequently, the probability coefficients of relevant factors are extracted from the multi-source displacement data collected by the sensor, and a feature matrix is ​​constructed to quantify the slope stability characteristics. The matrix is ​​sorted by correlation, and the probability coefficients most relevant to the instability risk are screened out for optimization and reconstruction. Based on the optimization matrix, a linear equation is constructed by linear regression, the undetermined coefficients of each feature are estimated, and a nonlinear regression model is used to predict the slope displacement trend, capture complex dynamic changes, and generate more accurate slope displacement prediction data. In particular, when dealing with short-term sudden changes, the nonlinear model can provide more representative trend prediction results.

[0058] Step S3: Based on the lock slope displacement prediction data, the time-series spatial evolution trend analysis of the lock slope displacement is performed to generate the time-space evolution lock slope displacement data; based on the lock slope time-space evolution lock slope displacement data, the time-series spatial evolution trend analysis of the lock slope deformation is performed to generate the time-space evolution lock slope deformation data;

[0059] In an embodiment of the present invention, after obtaining the displacement prediction data of the ship lock slope, these data are first sorted according to the time and space dimensions to generate a time-series spatial data set. The time evolution law of the slope displacement is identified by time series analysis methods, such as the autoregressive integrated moving average model (ARIMA). Subsequently, the spatial displacement data is analyzed using a geographic information system (GIS) to determine the displacement changes of different nodes. After integrating the data, the spatiotemporal statistical analysis technology (such as the STC model) is used to analyze the spatiotemporal evolution trend of the ship lock slope displacement, and the high-risk areas and their changing trends within a specific period are identified in combination with the geological characteristics of the slope in the actual project. A spatiotemporal evolution diagram is generated by visualization software to show the changing law of the slope displacement at different time points and locations, and the displacement acceleration and accumulation at key locations are marked for subsequent risk assessment and decision-making. The generated spatiotemporal evolution data not only reflects the displacement trend of the slope in the short term, but also reveals the potential risks of long-term displacement evolution. On this basis, the displacement data of different time and space positions are clustered and analyzed using spatiotemporal clustering algorithms (such as K-means or DBSCAN), and the correlation characteristics between deformation and external factors (such as water level changes, rainfall, ship passing frequency, etc.) are extracted. The core driving factors of deformation are identified through joint modeling through a time-weighted regression model. Through feature extraction technology, periodicity, trend, geological structure, stress distribution and other factors are extracted to generate spatiotemporal evolution ship lock slope deformation correlation characteristic data. These data can not only reveal the key characteristics of slope deformation, but also provide input for subsequent early warning models. After obtaining the spatiotemporal evolution ship lock slope deformation correlation characteristic data, time series analysis technology (such as ARIMA model or LSTM long short-term memory network) is used to model the dynamic changes of correlation characteristics. Combined with the state space model and geographical weighted regression method, the deformation state at different positions is analyzed to extract key state characteristics, such as displacement rate, stress concentration area and cumulative effect. The finally generated spatiotemporal evolution ship lock slope deformation correlation characteristic state data can clearly reflect the stability state of the slope and provide a basis for subsequent risk warning and engineering decision-making. Finally, the preset staged deformation rate evolution model is applied, and the deformation rate law identified in the historical monitoring data is used to divide the slope deformation process into multiple stages, and the rate change curves of each stage are generated using multi-segment linear regression method or nonlinear function fitting technology. Based on the temporal and spatial evolution of the ship lock slope deformation correlation characteristic state data, the displacement rate of each stage is predicted using time series regression analysis (such as seasonal autoregressive model SARIMA), and the deformation rate of each node is superimposed and processed in combination with GIS to generate a three-dimensional spatiotemporal evolution diagram, accurately depicting the deformation trend of the slope, and revealing the potential instability risk in different areas, providing scientific support for monitoring and early warning during the operation of the ship hull.

[0060] Step S4: Perform lock slope displacement monitoring and early warning status assessment processing based on the spatiotemporal evolution of lock slope deformation data to generate lock slope displacement monitoring and early warning status assessment data; transmit the lock slope displacement monitoring and early warning status assessment data to the terminal to execute the lock slope displacement monitoring and early warning status feedback operation.

[0061] In an embodiment of the present invention, after obtaining the deformation data of the time-space evolution ship lock slope, the stress-strain state of the slope is first analyzed using a finite element analysis (FEA) model, and the stress distribution model of the slope is established by inputting the displacement and stress data of different time nodes and spatial positions in the finite element model. Then, the stability coefficient (FS) of the slope is calculated by combining the geological parameters and the stress distribution to measure the overall stability of the slope. At the same time, combined with the changes in hydrological conditions and the dynamics of the groundwater level, the influence of hydrological factors on the stability of the slope is simulated by the seepage-stress coupling model. The historical deformation data is used for time series regression analysis to predict the future stability trend and generate the time-space evolution stability data of the ship lock slope. The generated stability data provides input for the early warning system, especially when the hull is running, by detecting the change in the stability coefficient, the potential instability area is identified and a real-time early warning is issued. Based on the deformation data of the time-space evolution ship lock slope, the deformation rate acceleration model is used to analyze the deformation rate change trend and determine the possibility of slope instability. Through the time series analysis method of displacement rate and acceleration (such as sliding window regression analysis), the inflection point of deformation acceleration is monitored, and combined with historical data and stress change law, the critical time node of slope instability is calculated using the critical instability time model (such as Voight model) to generate instability time identification data. Based on the preset ship lock slope displacement monitoring and early warning rules, the spatiotemporal evolution slope deformation data, stability data and instability time identification data are integrated and processed, and fuzzy logic reasoning or decision tree algorithm is used to evaluate layer by layer. The matching degree between the data and the early warning rule is judged by the threshold. If the displacement rate exceeds the safety threshold, it is marked as a potential dangerous area, and the stability coefficient is further verified by the limit equilibrium analysis method (LEA). The time window is determined by the instability time identification, and the monitoring and early warning status evaluation data is generated by combining the deformation rate and stability coefficient. The generated evaluation data is transmitted to the monitoring terminal via optical fiber communication or wireless network, and the integrity of data transmission is ensured by TCP / IP protocol. The system identifies the warning level and risk information through the parser, and performs feedback operations such as triggering alarms and adjusting ship lock operations according to the set automatic feedback logic to ensure rapid emergency response and ensure the safety of ship locks and hulls.

[0062] Further, step S1 includes the following steps:

[0063] By deploying terrain sensors, geological sensors, formation sensors, hydrological sensors, and stress sensors in the nodes of the lock slope area, and building a lock slope monitoring sensor network through terrain sensors, geological sensors, formation sensors, hydrological sensors, and stress sensors;

[0064] In the embodiment of the present invention, in the process of deploying sensors at specific regional nodes of the ship lock slope, key locations are selected, and terrain sensors are arranged in areas prone to deformation based on the geological characteristics and hydrological conditions of the slope. These terrain sensors monitor small changes in terrain in real time and record their displacement trends through precise laser rangefinders and high-resolution inclinometers. The geological sensors are installed inside the slope through drilling holes, and the stress and crack conditions of the geological layer are monitored in real time with the help of highly sensitive strain gauges and crack extension sensors. The formation sensors are deployed at different formation depths through deep drilling, and are mainly used to monitor deep displacement and formation movement, and detect small changes in the deep part of the slope through differential GPS technology and acceleration sensors. The hydrological sensor is installed in the groundwater seepage channel of the slope, and the groundwater level changes and seepage rate are recorded in real time using pressure sensors and water level measuring devices. The stress sensor is installed in the key stress-bearing area of ​​the slope, and the stress distribution inside the rock and soil is monitored using resistance strain gauges and vibrating wire stress sensors. Through wired and wireless communication technologies, data from all sensors are collected in real time to the monitoring center to build an efficient and stable lock slope monitoring sensor network, ensuring that both surface and deep displacement information can be captured in real time.

[0065] Based on the lock slope monitoring sensor network, real-time monitoring and processing of multi-source displacement factors of the lock slope are performed to generate real-time multi-source displacement factor data of the lock slope, wherein the real-time multi-source displacement factor data of the lock slope includes real-time topographic and geomorphic data of the lock slope, real-time geological structure data of the lock slope, real-time stratigraphic and lithological data of the lock slope, real-time hydrological data of the lock slope, and real-time original stress data of the lock slope.

[0066] In the embodiment of the present invention, after the construction of the sensor network for monitoring the ship lock slope is completed, the system starts to monitor the multi-source displacement data in real time through high-frequency sampling and data synchronization technology. The terrain sensor provides accurate topographic change data, the geological sensor records the geological structural stress changes inside the slope, the formation sensor monitors the formation lithology and displacement dynamics at different depths, the hydrological sensor feeds back the changes in groundwater level, water pressure and seepage in real time, and the stress sensor records the stress distribution state of each layer of soil and rock mass on the slope. All these data are synchronized through a unified timestamp, integrated and processed at the data acquisition terminal, and transmitted to the monitoring center through a dedicated transmission protocol. At the monitoring center, the processing system analyzes each data type independently and generates real-time multi-source displacement factor data of the ship lock slope, including topographic data, geological structural data, formation lithology data, hydrological data and original stress data. Each data is filtered, denoised, calibrated and other steps to ensure that the real-time feedback data is accurate and correct, and provide a solid foundation for the subsequent ship lock slope displacement warning.

[0067] Further, as an embodiment of the present invention, refer to Figure 2 As shown, Figure 1 Detailed step flow diagram of step S2 in FIG. 1 , in this embodiment, step S2 includes the following steps:

[0068] Step S21: performing multi-source displacement factor curve fitting processing on the real-time multi-source displacement factor data of the ship lock slope to obtain the ship lock slope displacement fitting factor data;

[0069] In an embodiment of the present invention, real-time multi-source displacement factor data of the ship lock slope is first obtained, and the data is input into the multi-source displacement factor curve fitting system. The system regards each type of data (such as terrain data, geological data, etc.) as an independent variable, and performs linear or nonlinear fitting on it through the least squares method. In the fitting process, piecewise linear regression or polynomial fitting technology is used to ensure that the displacement trend of each variable within its specific time range is accurately described. After the fitting process, the curve of each variable generated not only reflects the real-time displacement trend, but also eliminates random fluctuations and noise data. Finally, a ship lock slope displacement fitting factor data set containing multi-source displacement information is generated by comprehensively fitting the data of various factors. This data set can reflect the overall displacement trend and dynamic changes of the slope, and provide accurate and reliable basic data support for subsequent risk assessment and early warning.

[0070] Step S22: performing ship lock slope displacement related characteristic analysis based on the ship lock slope displacement fitting factor data to generate ship lock slope displacement related characteristic data;

[0071] In an embodiment of the present invention, after obtaining the fitting factor data of the displacement of the ship lock slope, it is first processed by a time series analysis algorithm. The linear regression method is used to fit each key data point to generate a preliminary trend of slope displacement changes. This trend is based on the displacement information of the topography, geology, and strata provided by the sensor. The linear trend in the displacement data is fitted by the least squares method, and random noise is filtered to ensure that the change trajectory of the data points can accurately reflect the preliminary displacement trend of the slope, providing a basis for subsequent periodic analysis. Then, the Fourier transform algorithm is used to decompose the fitting data, identify the periodic components, divide the data into multiple time periods to extract periodic features, and generate periodic curves. This process converts the data recorded by the sensor into frequency domain signals, determines the periodic fluctuation amplitude and frequency of the displacement through spectrum analysis, and clarifies the periodic effects of seasonal water level changes, ship passage, etc. on slope displacement. The recursive algorithm continuously detects periodic changes, generates accurate periodic data, and evaluates the long-term dynamic changes of the slope. Subsequently, the preliminary trend data is combined with the periodic data, and the weighted superposition model is used to integrate the short-term fluctuations and long-term trend characteristics to generate a displacement change image. The influence of periodic and trend factors is quantified through multivariate regression analysis, and the weights are calculated to generate superimposed slope displacement trend data, providing a basis for future displacement warnings. Subsequently, the trend data is subjected to Kalman filtering or adaptive noise filtering to remove abnormal fluctuations and ensure that it accurately reflects the actual changes. After noise correction, the principal component analysis (PCA) or support vector machine (SVM) algorithm is used for feature analysis. After normalization, the variables that have the greatest impact on displacement, such as groundwater level changes or impact forces caused by hull operation, are identified, the most critical influencing factors are screened out, and relevant feature data are generated to provide a basis for risk assessment and early warning modeling.

[0072] Step S23: designing a ship lock slope displacement prediction factor based on the ship lock slope displacement related characteristic data; performing ship lock slope displacement related probability coefficient analysis on the ship lock slope displacement prediction factor to generate a ship lock slope displacement related probability coefficient;

[0073] In an embodiment of the present invention, after obtaining the characteristic data related to the slope displacement, the historical change law of each characteristic variable is analyzed to design the prediction factor of the ship lock slope displacement. First, the change rate, cumulative value and extreme value of each characteristic at different time points are calculated to establish the prediction factor related to the slope displacement. Then, the regression analysis method is used to calculate the probability of each prediction factor affecting the slope displacement and generate the probability coefficient. The influence intensity of each prediction factor is determined by the Bayesian probability or maximum likelihood estimation method to ensure that the prediction factor can accurately reflect the dynamic changes of the slope displacement.

[0074] Step S24: performing optimization related characteristic analysis processing of the ship lock slope displacement according to the ship lock slope displacement related probability coefficient, so as to design an optimized ship lock slope displacement related characteristic matrix;

[0075] In an embodiment of the present invention, probability coefficients of relevant factors such as topography, geology, strata, hydrology, and stress are extracted from displacement monitoring data collected by multi-source sensors. The probability coefficient of each factor is calculated by statistical analysis and regression analysis, and the specific operation includes using correlation analysis method (such as Pearson correlation coefficient) to evaluate the correlation strength of each variable with slope displacement. According to the weight of each factor and its influence on displacement change, a ship lock slope displacement related feature matrix is ​​constructed. In the design process, each row of the feature matrix represents a monitoring node, and each column of the matrix represents a different displacement influencing factor. The feature matrix quantifies the overall slope stability characteristics by accurately calculating the relationship between each variable and slope displacement, providing a basis for further sorting analysis. After the feature matrix is ​​constructed, the features in the matrix are sorted by correlation values. The correlation coefficient sorting algorithm is used to sort the features in descending order according to the degree of influence of each feature on the slope displacement. The specific steps include first normalizing the correlation of each feature to ensure the accuracy of the sorting. Then, according to the correlation strength of each feature, the features are sorted using a quick sorting algorithm. After the sorting is completed, the features that are most closely related to the slope displacement are displayed first and placed at the front end of the matrix. This sorting process helps identify the features that have the most significant impact on slope displacement, ensuring that subsequent analysis focuses on the most critical factors. After the feature matrix is ​​sorted, the probability coefficients related to the stability of the target ship lock slope are selected. By screening the sorted feature matrix and combining historical monitoring data, the probability coefficients that are most closely related to the risk of ship lock slope instability are selected. This process uses the threshold method to take the features with correlation coefficients greater than a preset threshold as the probability coefficients related to the target stability. These selected coefficients can reflect the key factors directly related to slope displacement, ensuring that only the most representative data are used in subsequent analysis, thereby improving the accuracy of monitoring and early warning. The original feature matrix is ​​optimized and reconstructed using the selected target probability coefficients. First, the rows and columns of the matrix are adjusted according to the target coefficients, and the variables with less impact on slope displacement are eliminated to retain the key features. Then, the matrix is ​​further simplified using dimensionality reduction algorithms such as principal component analysis (PCA), reducing the dimension while retaining the most important information in the data. This optimization and reconstruction process effectively improves the computational efficiency of the feature matrix, making the slope displacement monitoring model more concise and accurate, thereby generating an optimized feature matrix for subsequent displacement prediction and early warning.

[0076] Step S25: performing ship lock slope displacement prediction processing according to the optimized ship lock slope displacement related characteristic matrix to generate ship lock slope displacement prediction data.

[0077] In an embodiment of the present invention, on the basis of optimizing the characteristic matrix related to the displacement of the ship lock slope, a linear equation is constructed through the relationship between the characteristic value of the matrix and the displacement of the slope. The main features in the optimized characteristic matrix are used as independent variables, and the displacement change is used as the dependent variable. The coefficients of each feature are estimated by the linear regression method to reflect the contribution of each feature to the displacement change of the slope. During the construction process, the coefficients are fitted by the ordinary least squares (OLS) method to ensure that the equation can accurately describe the relationship between the characteristic matrix and the slope displacement, and finally a linear equation is formed to describe the linear relationship between each feature and the displacement change. The linear equation is used to calculate the undetermined coefficients, and the coefficients are inferred by inputting historical monitoring data to gradually calculate the undetermined coefficients of each feature. The multivariate regression analysis method is used to ensure the accuracy of each undetermined coefficient, and the stepwise approximation algorithm is used until the coefficient converges to a stable value, providing key parameters for subsequent displacement prediction. After obtaining the undetermined coefficients, the nonlinear regression model is used to predict the displacement trend of the ship lock slope. The linear equation structure is expanded by introducing nonlinear functions (such as polynomials or logarithmic functions), the undetermined coefficients and independent variable features are incorporated into the nonlinear model, and the nonlinear trend is fitted through historical data. Bayesian estimation or Monte Carlo simulation methods are used to capture complex dynamic changes and generate more accurate slope displacement prediction data. Especially when dealing with short-term sudden or accelerated displacement changes, nonlinear models provide more representative trend prediction results.

[0078] Further, as an embodiment of the present invention, refer to Figure 3 As shown, Figure 2 FIG. 2 is a schematic diagram of a detailed step flow chart of step S22 in FIG. 1 . In this embodiment, step S22 includes the following steps:

[0079] Step S221: performing periodic trend superposition analysis of the ship lock slope displacement fitting factor based on the ship lock slope displacement fitting factor data to generate ship lock slope displacement fitting factor trend data;

[0080] In an embodiment of the present invention, after obtaining the fitting factor data of the displacement of the ship lock slope, the data is first processed by a time series analysis algorithm. Each key data point is fitted by a linear regression method to generate a preliminary trend of slope displacement changes. This trend analysis is based on the displacement information of topography, geology, strata, etc. provided by the sensor. The linear trend in the displacement data is fitted by the least squares method, and random noise is filtered to ensure that the change trajectory of the data point can accurately reflect the preliminary displacement trend of the slope, providing a basis for subsequent periodic analysis. Next, the fitting factor data is decomposed using the Fourier transform algorithm to identify the periodic components in the displacement data of the ship lock slope. In the specific operation, the data is divided into multiple time periods, the periodic features are extracted, and the corresponding periodic curves are generated. This process converts the data recorded by the sensor into a frequency domain signal, determines the periodic fluctuation amplitude and frequency of the displacement by spectrum analysis, and clarifies the periodic effects of seasonal water level changes, ship passage, etc. on the slope displacement. The recursive algorithm continuously detects periodic changes, generates accurate periodic data, and evaluates the long-term dynamic changes of the slope. Finally, the preliminary trend data and periodic data are combined, and the weighted superposition model is used to integrate the characteristics of short-term fluctuations and long-term trends to generate a comprehensive displacement change image. This process uses a multivariate regression analysis method to quantify the combined impact of periodic and trend factors, and by calculating the weights of each factor, the superimposed slope displacement trend data is generated, which not only better reflects the current status, but also provides a more accurate basis for future displacement warnings.

[0081] Step S222: performing fitting factor noise correction processing on the lock slope displacement fitting factor trend data to generate corrected lock slope displacement fitting factor trend data;

[0082] In an embodiment of the present invention, after obtaining preliminary ship lock slope displacement trend data, the noise in the data is corrected by Kalman filtering or adaptive noise filtering algorithm. First, a smoothing algorithm is used to preliminarily filter out the high-frequency noise in the original data, and then a noise model is constructed based on historical data and environmental characteristics. By iteratively calculating the fitting data, abnormal fluctuations and irrelevant data interference are eliminated. Ensure that the processed trend data can more accurately reflect the actual changes in slope displacement. The corrected data finally generated will be used as high-precision ship lock slope displacement trend data for subsequent analysis.

[0083] Step S223: performing ship lock slope displacement related characteristic analysis based on the corrected ship lock slope displacement fitting factor trend data to generate ship lock slope displacement related characteristic data.

[0084] In an embodiment of the present invention, based on the trend data after noise correction, principal component analysis (PCA) or support vector machine (SVM) algorithm is used to perform characteristic analysis of the ship lock slope displacement. First, the data is normalized to ensure that each characteristic variable is compared at the same scale. Then, the variables that have the most significant impact on the slope displacement are identified, such as groundwater level changes, impact forces caused by hull operation, etc. Through characteristic analysis, the weight values ​​of each variable are calculated, and the most critical factors affecting slope displacement are screened out to generate relevant characteristic data of the ship lock slope displacement, providing a basis for subsequent risk assessment and early warning modeling.

[0085] Further, step S221 includes the following steps:

[0086] Conduct preliminary ship lock slope displacement fitting factor trend analysis based on the ship lock slope displacement fitting factor data to generate preliminary ship lock slope displacement fitting factor trend data;

[0087] In an embodiment of the present invention, after obtaining the fitting factor data of the ship lock slope displacement, the data is first processed by a time series analysis algorithm. The linear regression method is used to fit each key data point to generate a preliminary slope displacement change trend. The trend analysis is based on the data provided by each sensor, including displacement information of factors such as terrain, geology, and strata. The linear trend in the displacement data is fitted by the least squares method, and random noise is filtered out to ensure that the change trajectory of each data point can accurately reflect the preliminary displacement trend of the slope. Through this preliminary analysis, the trend data generated provides a basis for subsequent periodic analysis.

[0088] Performing periodic analysis of the ship lock slope displacement fitting factor according to the ship lock slope displacement fitting factor data, and generating periodic data of the ship lock slope displacement fitting factor;

[0089] In an embodiment of the present invention, when performing periodic analysis, the fitting factor data is decomposed using a Fourier transform algorithm to identify the periodic components in the displacement data of the ship lock slope. In the specific operation, the data is divided into multiple time periods, and the periodic features of each data segment are extracted to generate corresponding periodic curves. This operation uses the data recorded by the sensor, converts it into a frequency domain signal, and determines the periodic fluctuation amplitude and frequency of the displacement through spectrum analysis, and clarifies the periodic impact of the slope displacement on the slope with seasonal water level changes and the passage of the ship. During the analysis process, various periodic changes are continuously detected through a recursive algorithm, and accurate periodic data is generated to evaluate the long-term dynamic changes of the slope.

[0090] Based on the preliminary lock slope displacement fitting factor trend data and the lock slope displacement fitting factor periodic data, a lock slope displacement fitting factor trend superposition analysis is performed to generate the lock slope displacement fitting factor trend data.

[0091] In an embodiment of the present invention, after the preliminary trend data and periodic data are generated, the two are comprehensively processed by a superposition analysis algorithm. First, the periodic data is matched with the trend data to ensure the synchronization of the two data sets on the time axis. Using a weighted superposition model, the characteristics of trend changes and periodic changes are integrated to generate a displacement change image containing short-term fluctuations and long-term trends. In this step, a multivariate regression analysis method is used to quantify the comprehensive impact of periodic and trend factors on slope displacement. By calculating the weight of each factor, the superimposed slope displacement trend data is finally generated. This data can not only better reflect the current state of the slope, but also provide a more accurate basis for future displacement warnings.

[0092] Further, step S24 includes the following steps:

[0093] The ship lock slope displacement related characteristic matrix is ​​designed according to the ship lock slope displacement related probability coefficient; the ship lock slope displacement related characteristic matrix is ​​sorted by correlation value, and the target ship lock slope stability related probability coefficient is selected for the ship lock slope displacement related characteristic matrix after correlation value sorting, so as to obtain the target ship lock slope displacement related probability coefficient; the ship lock slope displacement related characteristic matrix is ​​optimized and reconstructed based on the target ship lock slope displacement related probability coefficient, so as to generate the optimized ship lock slope displacement related characteristic matrix.

[0094] In an embodiment of the present invention, probability coefficients of relevant factors such as topography, geology, strata, hydrology, and stress are extracted from displacement monitoring data collected by multi-source sensors. The probability coefficient of each factor is calculated by statistical analysis and regression analysis, and the specific operation includes using correlation analysis method (such as Pearson correlation coefficient) to evaluate the correlation strength of each variable with slope displacement. According to the weight of each factor and its influence on displacement change, a ship lock slope displacement related feature matrix is ​​constructed. In the design process, each row of the feature matrix represents a monitoring node, and each column of the matrix represents a different displacement influencing factor. The feature matrix quantifies the overall slope stability characteristics by accurately calculating the relationship between each variable and slope displacement, providing a basis for further sorting analysis. After the feature matrix is ​​constructed, the features in the matrix are sorted by correlation values. The correlation coefficient sorting algorithm is used to sort the features in descending order according to the degree of influence of each feature on the slope displacement. The specific steps include first normalizing the correlation of each feature to ensure the accuracy of the sorting. Then, according to the correlation strength of each feature, the features are sorted using a quick sorting algorithm. After the sorting is completed, the features that are most closely related to the slope displacement are displayed first and placed at the front end of the matrix. This sorting process helps identify the features that have the most significant impact on slope displacement, ensuring that subsequent analysis focuses on the most critical factors. After the feature matrix is ​​sorted, the probability coefficients related to the stability of the target ship lock slope are selected. By screening the sorted feature matrix and combining historical monitoring data, the probability coefficients that are most closely related to the risk of ship lock slope instability are selected. This process uses the threshold method to take the features with correlation coefficients greater than a preset threshold as the probability coefficients related to the target stability. These selected coefficients can reflect the key factors directly related to slope displacement, ensuring that only the most representative data are used in subsequent analysis, thereby improving the accuracy of monitoring and early warning. The original feature matrix is ​​optimized and reconstructed using the selected target probability coefficients. First, the rows and columns of the matrix are adjusted according to the target coefficients, and the variables with less impact on slope displacement are eliminated to retain the key features. Then, the matrix is ​​further simplified using dimensionality reduction algorithms such as principal component analysis (PCA), reducing the dimension while retaining the most important information in the data. This optimization and reconstruction process effectively improves the computational efficiency of the feature matrix, making the slope displacement monitoring model more concise and accurate, thereby generating an optimized feature matrix for subsequent displacement prediction and early warning.

[0095] Further, step S25 includes the following steps:

[0096] Design the linear equation related to the displacement of the ship lock slope according to the optimized characteristic matrix related to the displacement of the ship lock slope;

[0097] In an embodiment of the present invention, on the basis of optimizing the characteristic matrix related to the displacement of the ship lock slope, a linear equation is constructed through the relationship between each eigenvalue of the matrix and the slope displacement. First, the main features in the optimized characteristic matrix are used as the independent variables of the equation, and the displacement change is used as the dependent variable. The coefficients of each feature in the characteristic matrix are estimated using the linear regression method. The coefficient of each variable reflects the contribution of the feature to the displacement change of the ship lock slope. During the construction process, the ordinary least squares (OLS) method is used to fit the coefficients of the linear equation to ensure that the equation can accurately describe the relationship between the characteristic matrix and the slope displacement. Finally, a clear linear equation is formed to describe the linear relationship between each feature and the slope displacement change.

[0098] The undetermined coefficients for predicting the displacement of the ship lock slope are calculated based on the linear equations related to the displacement of the ship lock slope, and the undetermined coefficients for predicting the displacement of the ship lock slope are generated;

[0099] In the embodiment of the present invention, the linear equation established in the previous step is used to calculate the undetermined coefficients. The undetermined coefficients of each characteristic variable are gradually calculated by inputting the historical monitoring data into the linear equation and inferring the coefficients using the known displacement data. The algorithm used in this process is the multivariate regression analysis method, which accurately calculates the undetermined coefficients of each characteristic to ensure that it can reflect the specific impact intensity of the characteristic on the slope displacement. To ensure the accuracy of the coefficients, the calculation process of the undetermined coefficients adopts a stepwise approximation algorithm until the coefficients converge to a stable value. Finally, the undetermined coefficients of each characteristic are obtained, providing key parameters for subsequent displacement prediction.

[0100] Based on the undetermined coefficients of lock slope displacement prediction, nonlinear lock slope displacement trend prediction processing is performed to generate lock slope displacement prediction data.

[0101] In an embodiment of the present invention, after obtaining the unknown coefficients, a nonlinear regression model is used to perform ship lock slope displacement trend prediction processing. First, by introducing nonlinear functions (such as polynomials or logarithmic functions), the structure of the linear equation is expanded, and the characteristics of each unknown coefficient and independent variable are incorporated into the nonlinear model. Then, the historical monitoring data is used to fit the model and identify the nonlinear trend in the ship lock slope displacement. Bayesian estimation or Monte Carlo simulation methods are used in nonlinear trend prediction to capture the complex dynamic changes in slope displacement. Through this nonlinear prediction model, more accurate ship lock slope displacement prediction data can be generated, especially when dealing with short-term sudden or accelerated displacement changes, the nonlinear model provides more representative trend prediction results.

[0102] Further, step S3 includes the following steps:

[0103] Step S31: performing temporal spatial evolution trend analysis of the ship lock slope displacement based on the ship lock slope displacement prediction data, and generating temporal and spatial evolution ship lock slope displacement data;

[0104] In an embodiment of the present invention, after obtaining the displacement prediction data of the ship lock slope, it is first necessary to organize these prediction data according to the two dimensions of time and space to generate a time-series spatial data set. Through time series analysis methods, such as the autoregressive integrated moving average model (ARIMA), the time evolution law of the slope displacement is identified. Then, the spatial displacement data is spatially analyzed through a geographic information system (GIS) to determine the displacement changes of nodes at different positions. After integrating the two types of data, the spatiotemporal statistical analysis technology (such as the STC model) is used to analyze the spatiotemporal evolution trend of the ship lock slope displacement, and combined with the geological characteristics of the slope in the actual project, the high-risk areas of the slope and their changing trends in a specific period of time are identified. The spatiotemporal evolution diagram is generated by visualization software to show the changing law of the slope displacement at different time points and positions, and the displacement acceleration and cumulative displacement of the key positions are marked for subsequent risk assessment and decision-making. The generated spatiotemporal evolution data not only reflects the displacement trend of the slope in the short term, but also reveals the potential risks of long-term displacement evolution.

[0105] Step S32: extracting the temporal and spatial evolutionary ship lock slope deformation correlation features according to the temporal and spatial evolutionary ship lock slope displacement data, and generating the temporal and spatial evolutionary ship lock slope deformation correlation feature data;

[0106] In an embodiment of the present invention, based on the displacement data of the spatiotemporal evolution ship lock slope, the displacement data at different time points and spatial positions are first clustered and analyzed by a spatiotemporal clustering algorithm (such as K-means or DBSCAN) to identify regions and time periods with similar displacement change patterns. Then, a correlation analysis method (such as Pearson correlation coefficient or grey correlation analysis) is used to calculate the correlation between the deformation data of the ship lock slope and environmental factors (such as water level changes, rainfall, ship passing frequency, etc.), and extract the correlation characteristics between deformation and external factors. In order to ensure the accuracy of feature extraction, a time-weighted regression model is used to jointly model the time series and spatial factors, so as to identify the core driving factors of deformation. Through feature extraction technology, the periodicity and trend characteristics of displacement changes, as well as related factors such as geological structure and stress distribution are refined to generate the correlation feature data of the spatiotemporal evolution ship lock slope deformation. Ultimately, these data can not only reveal the key features of slope deformation, but also provide input for subsequent early warning models to ensure that the close correlation between deformation features and the ship hull operating environment is fully captured.

[0107] Step S33: performing a time-space evolution ship lock slope deformation associated characteristic state analysis according to the time-space evolution ship lock slope deformation associated characteristic data, and generating time-space evolution ship lock slope deformation associated characteristic state data;

[0108] In an embodiment of the present invention, after obtaining the associated characteristic data of the spatiotemporal evolution of the ship lock slope deformation, firstly, the dynamic changes of the associated characteristics are modeled by time series analysis technology (such as ARIMA model or LSTM long short-term memory network), and the evolution law of the slope deformation in different time periods is analyzed. The state-space model is used in combination with the associated characteristic data to construct a state evolution model of the ship lock slope deformation to capture the changes of various factors in the slope deformation process and their mutual influence. In the spatial dimension, the deformation state of different positions of the ship lock is analyzed by the geographical weighted regression (GWR) method, and the differences in stress distribution, stratum changes and hydrological conditions of each spatial node are identified. Combining the analysis results of the two dimensions of time and space, the key state characteristics of the ship lock slope deformation, such as displacement rate, stress concentration area and deformation accumulation effect, are extracted. The finally generated spatiotemporal evolution ship lock slope deformation associated characteristic state data can clearly reflect the stability state of the slope and provide a basis for subsequent risk warning and engineering decision-making.

[0109] Step S34: Based on the preset evolution model of the staged deformation rate of the ship lock slope, the temporal spatial evolution trend of the ship lock slope deformation is analyzed on the temporal and spatial evolution ship lock slope deformation associated characteristic state data to generate the temporal and spatial evolution ship lock slope deformation data.

[0110] In an embodiment of the present invention, when performing a temporal spatial evolution trend analysis of the deformation of the ship lock slope, a preset staged deformation rate evolution model is first applied. The model divides the slope deformation process into multiple stages based on the deformation rate change law identified in the historical monitoring data. The model uses a multi-segment linear regression method or a nonlinear function fitting technique to model the displacement rate of the slope at different stages and generate rate change curves for each stage. Then, based on the temporal and spatial evolution ship lock slope deformation associated characteristic state data, a temporal regression analysis (such as seasonal autoregressive model SARIMA) is used to predict the displacement rate of each stage, and the deformation rate of each spatial node is superimposed in combination with a spatial analysis tool (such as a geographic information system GIS). This process integrates the two dimensions of time and space to generate a three-dimensional temporal and spatial evolution diagram of the ship lock slope deformation, accurately depicting the deformation trend of the slope at a specific time and location. The generated temporal and spatial evolution ship lock slope deformation data can reflect the change of deformation rate over time, reveal the potential instability risk of different regions at each stage, and provide scientific support for slope monitoring and early warning during the operation of the ship.

[0111] Further, step S4 includes the following steps:

[0112] Step S41: performing a time-space evolution ship lock slope stability analysis according to the time-space evolution ship lock slope deformation data, and generating time-space evolution ship lock slope stability data;

[0113] In an embodiment of the present invention, after obtaining the deformation data of the time-space evolution ship lock slope, the stress-strain state of the slope is first analyzed using a finite element analysis (FEA) model. By inputting the displacement and stress data of different time nodes and spatial positions in the finite element model, a stress distribution model of the slope is established. Then, the stability coefficient (FS) of the slope is calculated by combining the geological parameters and the stress distribution using the limit equilibrium analysis (LEA). This coefficient measures the overall stability of the slope by reflecting the ratio of the anti-sliding force to the sliding force of the slope. In this process, it is also necessary to combine the changes in hydrological conditions and the dynamic changes in groundwater levels, and simulate the influence of hydrological factors on slope stability through a seepage-stress coupling model (such as a two-way coupling analysis model). Time series regression analysis is performed using historical deformation data to predict future slope stability trends, and finally generate the time-space evolution stability data of the ship lock slope. The generated stability data will provide input for the early warning system, especially when the hull is running, by detecting the changes in the stability coefficient, identifying potential unstable areas and making real-time early warnings. This analysis can help determine the overall safety status of the ship lock slope and provide data support for preventing potential landslides.

[0114] Step S42: marking the instability time of the ship lock slope according to the spatiotemporal evolution ship lock slope deformation data, and generating ship lock slope instability time marking data;

[0115] In an embodiment of the present invention, based on the deformation data of the ship lock slope evolving in time and space, the deformation rate acceleration model is first applied to judge the possibility of slope instability by analyzing the variation trend of the deformation rate. The time series analysis method of displacement rate and acceleration (such as sliding window regression analysis) is used to monitor the deformation rate changes in different time periods, with special attention paid to the inflection points of deformation acceleration, which usually mark the beginning of the instability process. Combined with the historical deformation data and the law of stress change, the critical time node of slope instability is deduced using the critical instability time model (such as the Voight model). The potential time window of instability is identified through model analysis and marked as the instability time mark. In order to improve the accuracy of the mark, it is also necessary to combine the external environmental factors during the operation of the hull, such as the external force factors such as the water level change of the ship lock and rainfall, and further correct the instability time mark by statistically analyzing the influence of these factors on the instability time. Finally, the instability time mark data of the ship lock slope is generated, and the critical time point of slope instability is clearly pointed out. These data provide key inputs for the early warning system, which helps to monitor the risk of slope instability in real time during the operation of the hull and ensure that protective measures are taken in time.

[0116] Step S43: Based on the preset lock slope displacement monitoring and early warning rules, the time-space evolution lock slope deformation data, the time-space evolution lock slope stability data and the lock slope instability time mark data are evaluated and processed to generate lock slope displacement monitoring and early warning status evaluation data;

[0117] In an embodiment of the present invention, based on the preset ship lock slope displacement monitoring and early warning rules, the spatiotemporal evolution ship lock slope deformation data, spatiotemporal evolution slope stability data and ship lock slope instability time mark data are first integrated and processed. Fuzzy logic reasoning or decision tree algorithm is used to evaluate these data layer by layer according to the critical values ​​in the early warning rules (such as displacement rate, instability time node, stability coefficient, etc.). The system first determines whether the deformation data matches the critical value in the early warning rule through the threshold. If the displacement rate exceeds the set safety threshold, the evaluation system marks the area as a potential dangerous area. Then, combined with the stability data of the ship lock slope, the limit equilibrium analysis method (LEA) or the slip surface stress analysis method is used to further verify the stability of the area and calculate the current stability coefficient. If the stability coefficient is lower than the safety standard, the early warning system further confirms that the slope may be in an unstable state. Finally, the time window of potential instability is determined through the instability time mark, and the overall ship lock slope displacement monitoring early warning state evaluation data is generated in combination with the deformation rate and stability coefficient. The assessment data includes specific warning levels, instability time periods and deformation trend analysis results, which are used by the decision-making system for automated warning and risk management.

[0118] Step S44: Transmit the lock slope displacement monitoring early warning status assessment data to the terminal to execute the lock slope displacement monitoring early warning status feedback operation.

[0119] In an embodiment of the present invention, after the lock slope displacement monitoring and early warning status evaluation data is generated, the data is transmitted to the terminal device of the monitoring center in real time through optical fiber communication or wireless network. The transmission process uses TCP / IP protocol for stable data transmission to ensure the integrity and accuracy of the data. During the transmission process, the system first performs packet processing on the evaluation data and flows the data to the remote server through the sensor network gateway. After the server receives the early warning status data, it uses a dedicated data parser to parse the data to ensure that key information such as displacement early warning level, time node, and instability risk area can be correctly identified by the terminal. The terminal system performs corresponding feedback operations through pre-set automatic feedback logic. The feedback operation includes alarm triggering, lock operation adjustment suggestions, and automatic activation of on-site emergency plans. For example, when the early warning level reaches a critical value, the system will automatically close the lock or slow down the water level change to reduce further pressure on the slope. At the same time, the feedback operation will also send the alarm information to the on-site operators and management by SMS or email to ensure rapid response in emergency situations. This process ensures the efficient feedback and emergency handling capabilities of the lock slope displacement monitoring and early warning system during the operation of the hull, ensuring the safe operation of the lock and hull.

[0120] This specification provides a ship lock slope displacement monitoring and early warning system based on the influence of ship hull operation, which is used to execute the ship lock slope displacement monitoring and early warning method based on the influence of ship hull operation as described above. The ship lock slope displacement monitoring and early warning system based on the influence of ship hull operation includes:

[0121] The ship lock slope multi-source displacement factor monitoring module is used to generate a ship lock slope monitoring sensor network by deploying multi-source sensors in the ship lock slope area nodes and building a sensor monitoring network; the ship lock slope monitoring sensor network collects the ship lock slope multi-source data in real time at the ship lock slope area nodes to obtain real-time ship lock slope multi-source displacement factor data;

[0122] The ship lock slope displacement prediction module is used to perform ship lock slope displacement prediction processing based on real-time ship lock slope multi-source displacement factor data to generate ship lock slope displacement prediction data;

[0123] The module of temporal and spatial evolution of ship lock slope deformation is used to analyze the temporal and spatial evolution trend of ship lock slope displacement based on the predicted data of ship lock slope displacement, and generate temporal and spatial evolution ship lock slope displacement data; the module of temporal and spatial evolution of ship lock slope deformation is used to analyze the temporal and spatial evolution trend of ship lock slope displacement based on the temporal and spatial evolution ship lock slope, and generate temporal and spatial evolution ship lock slope deformation data;

[0124] The lock slope displacement monitoring and early warning feedback module is used to evaluate and process the lock slope displacement monitoring and early warning status based on the spatiotemporal evolution of the lock slope deformation data, generate the lock slope displacement monitoring and early warning status evaluation data; transmit the lock slope displacement monitoring and early warning status evaluation data to the terminal to execute the lock slope displacement monitoring and early warning status feedback operation.

[0125] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for monitoring and early warning of ship lock slope displacement based on the influence of ship hull operation, characterized in that: The following steps are involved: Step S1: Deploy multi-source sensors in the nodes of the lock slope area and construct a sensor monitoring network to generate a lock slope monitoring sensor network; Through the lock slope monitoring sensor network, multi-source data of the lock slope is collected in real time at the nodes in the lock slope area to obtain real-time multi-source displacement factor data of the lock slope; Step S2: performing ship lock slope displacement prediction processing based on real-time ship lock slope multi-source displacement factor data to generate ship lock slope displacement prediction data; Step S21: performing multi-source displacement factor curve fitting processing on the real-time multi-source displacement factor data of the ship lock slope to obtain the ship lock slope displacement fitting factor data; Step S22: performing ship lock slope displacement related characteristic analysis based on the ship lock slope displacement fitting factor data to generate ship lock slope displacement related characteristic data; Step S23: designing a ship lock slope displacement prediction factor based on the ship lock slope displacement related characteristic data; Carry out the ship lock slope displacement related probability coefficient analysis on the ship lock slope displacement prediction factor to generate the ship lock slope displacement related probability coefficient; Step S24: performing optimization related characteristic analysis processing of the ship lock slope displacement according to the ship lock slope displacement related probability coefficient, so as to design an optimized ship lock slope displacement related characteristic matrix; Step S25: performing ship lock slope displacement prediction processing according to the optimized ship lock slope displacement related characteristic matrix to generate ship lock slope displacement prediction data; Step S3: Based on the lock slope displacement prediction data, the time-series spatial evolution trend analysis of the lock slope displacement is performed to generate the time-space evolution lock slope displacement data; based on the lock slope time-space evolution lock slope displacement data, the time-series spatial evolution trend analysis of the lock slope deformation is performed to generate the time-space evolution lock slope deformation data; Step S4: performing ship lock slope displacement monitoring and early warning status assessment processing based on the spatiotemporal evolution ship lock slope deformation data to generate ship lock slope displacement monitoring and early warning status assessment data; The lock slope displacement monitoring and early warning status assessment data is transmitted to the terminal to execute the lock slope displacement monitoring and early warning status feedback operation.

2. The method for monitoring and early warning of ship lock slope displacement based on the influence of ship hull operation according to claim 1 is characterized in that: Step S1 includes the following steps: By deploying terrain sensors, geological sensors, formation sensors, hydrological sensors, and stress sensors in the nodes of the lock slope area, and building a lock slope monitoring sensor network through terrain sensors, geological sensors, formation sensors, hydrological sensors, and stress sensors; Based on the lock slope monitoring sensor network, real-time monitoring and processing of multi-source displacement factors of the lock slope are performed to generate real-time multi-source displacement factor data of the lock slope, wherein the real-time multi-source displacement factor data of the lock slope includes real-time topographic and geomorphic data of the lock slope, real-time geological structure data of the lock slope, real-time stratigraphic and lithological data of the lock slope, real-time hydrological data of the lock slope, and real-time original stress data of the lock slope.

3. The method for monitoring and early warning of ship lock slope displacement based on the influence of ship hull operation according to claim 1 is characterized in that: Step S22 includes the following steps: Step S221: performing periodic trend superposition analysis of the ship lock slope displacement fitting factor based on the ship lock slope displacement fitting factor data to generate ship lock slope displacement fitting factor trend data; Step S222: performing fitting factor noise correction processing on the lock slope displacement fitting factor trend data to generate corrected lock slope displacement fitting factor trend data; Step S223: performing ship lock slope displacement related characteristic analysis based on the corrected ship lock slope displacement fitting factor trend data to generate ship lock slope displacement related characteristic data.

4. The method for monitoring and early warning of ship lock slope displacement based on the influence of ship hull operation according to claim 3 is characterized in that: Step S221 includes the following steps: Conduct preliminary ship lock slope displacement fitting factor trend analysis based on the ship lock slope displacement fitting factor data to generate preliminary ship lock slope displacement fitting factor trend data; Performing periodic analysis of the ship lock slope displacement fitting factor according to the ship lock slope displacement fitting factor data, and generating periodic data of the ship lock slope displacement fitting factor; Based on the preliminary lock slope displacement fitting factor trend data and the lock slope displacement fitting factor periodic data, a lock slope displacement fitting factor trend superposition analysis is performed to generate the lock slope displacement fitting factor trend data.

5. The method for monitoring and early warning of ship lock slope displacement based on the influence of ship movement according to claim 1 is characterized in that: Step S24 includes the following steps: The ship lock slope displacement related characteristic matrix is ​​designed according to the ship lock slope displacement related probability coefficient; the ship lock slope displacement related characteristic matrix is ​​sorted by correlation value, and the target ship lock slope stability related probability coefficient is selected for the ship lock slope displacement related characteristic matrix after correlation value sorting, so as to obtain the target ship lock slope displacement related probability coefficient; the ship lock slope displacement related characteristic matrix is ​​optimized and reconstructed based on the target ship lock slope displacement related probability coefficient, so as to generate the optimized ship lock slope displacement related characteristic matrix.

6. The method for monitoring and early warning of ship lock slope displacement based on the influence of ship hull operation according to claim 1 is characterized in that: Step S25 includes the following steps: Design the linear equation related to the displacement of the ship lock slope according to the optimized characteristic matrix related to the displacement of the ship lock slope; The undetermined coefficients for predicting the displacement of the ship lock slope are calculated based on the linear equations related to the displacement of the ship lock slope, and the undetermined coefficients for predicting the displacement of the ship lock slope are generated; Based on the undetermined coefficients of lock slope displacement prediction, nonlinear lock slope displacement trend prediction processing is performed to generate lock slope displacement prediction data.

7. The method for monitoring and early warning of ship lock slope displacement based on the influence of ship movement according to claim 1 is characterized in that: Step S3 includes the following steps: Step S31: performing temporal spatial evolution trend analysis of the ship lock slope displacement based on the ship lock slope displacement prediction data, and generating temporal and spatial evolution ship lock slope displacement data; Step S32: extracting the temporal and spatial evolutionary ship lock slope deformation correlation features according to the temporal and spatial evolutionary ship lock slope displacement data, and generating the temporal and spatial evolutionary ship lock slope deformation correlation feature data; Step S33: performing a time-space evolution ship lock slope deformation associated characteristic state analysis according to the time-space evolution ship lock slope deformation associated characteristic data, and generating time-space evolution ship lock slope deformation associated characteristic state data; Step S34: Based on the preset lock slope stage deformation rate evolution model, the temporal spatial evolution trend of the lock slope deformation is analyzed on the temporal and spatial evolution lock slope deformation associated characteristic state data to generate the temporal and spatial evolution lock slope deformation data.

8. The method for monitoring and early warning of ship lock slope displacement based on the influence of ship movement according to claim 1 is characterized in that: Step S4 includes the following steps: Step S41: performing a time-space evolution ship lock slope stability analysis according to the time-space evolution ship lock slope deformation data, and generating time-space evolution ship lock slope stability data; Step S42: marking the instability time of the ship lock slope according to the spatiotemporal evolution ship lock slope deformation data, and generating ship lock slope instability time marking data; Step S43: Based on the preset lock slope displacement monitoring and early warning rules, the time-space evolution lock slope deformation data, the time-space evolution lock slope stability data and the lock slope instability time mark data are evaluated and processed to generate lock slope displacement monitoring and early warning status evaluation data; Step S44: Transmit the lock slope displacement monitoring early warning status assessment data to the terminal to execute the lock slope displacement monitoring early warning status feedback operation.

9. A ship lock slope displacement monitoring and early warning system based on the influence of ship movement, characterized in that: Used to execute the ship lock slope displacement monitoring and early warning method based on the influence of hull operation as claimed in claim 1, the ship lock slope displacement monitoring and early warning system based on the influence of hull operation comprises: The ship lock slope multi-source displacement factor monitoring module is used to generate a ship lock slope monitoring sensor network by deploying multi-source sensors in the ship lock slope area nodes and building a sensor monitoring network; the ship lock slope monitoring sensor network collects the ship lock slope multi-source data in real time at the ship lock slope area nodes to obtain real-time ship lock slope multi-source displacement factor data; The ship lock slope displacement prediction module is used to perform ship lock slope displacement prediction processing based on real-time ship lock slope multi-source displacement factor data to generate ship lock slope displacement prediction data; The module of temporal and spatial evolution of ship lock slope deformation is used to analyze the temporal and spatial evolution trend of ship lock slope displacement based on the predicted data of ship lock slope displacement, and generate temporal and spatial evolution ship lock slope displacement data; the module of temporal and spatial evolution of ship lock slope deformation is used to analyze the temporal and spatial evolution trend of ship lock slope displacement based on the temporal and spatial evolution ship lock slope, and generate temporal and spatial evolution ship lock slope deformation data; The lock slope displacement monitoring and early warning feedback module is used to evaluate and process the lock slope displacement monitoring and early warning status based on the spatiotemporal evolution of the lock slope deformation data, generate the lock slope displacement monitoring and early warning status evaluation data; transmit the lock slope displacement monitoring and early warning status evaluation data to the terminal to execute the lock slope displacement monitoring and early warning status feedback operation.

Images