Method and device for determining safety early warning remote monitoring point position of hydraulic gate

Abstract

The invention relates to the technical field of hydraulic gate safety early warning, in particular to a hydraulic gate safety early warning remote monitoring point position determining method and device, and the method comprises the steps: obtaining the first hydraulic gate data of a target hydraulic gate, and recognizing the gate type of the target hydraulic gate; determining second hydraulic gate data of other hydraulic gates of the same category based on the gate category, and further calculating theoretical vulnerable points of the target hydraulic gate and the other hydraulic gates; identifying actual vulnerable points of the target hydraulic gate through the theoretical vulnerable points; and fusing the theoretical vulnerable point and the actual vulnerable point to obtain a safety early warning remote monitoring point position. Therefore, the problems that the data accuracy is low and a reasonable monitoring point position cannot be selected due to the fact that a method for establishing a water system key node database is tedious in the data acquisition process, and the real-time performance is poor and potential safety hazards of a hydraulic gate cannot be found in time due to the fact that a method for determining defects through amplitude extraction in the prior art are solved.

Description

Technical Field

[0001] The present application relates to the technical field of hydraulic gate safety warning, and in particular to a method and device for determining a hydraulic gate safety warning remote monitoring point. Background Art

[0002] In the related technology, a database of key nodes of the water system can be established through field investigation and data review, and then monitoring cameras can be installed at key locations of the water system for real-time monitoring; or an array eddy current sensor can be placed close to an array area on the surface of the component for scanning and detection, and the amplitude data of the eddy current sensing signal of the eddy current sensor at each array point position can be extracted using a time gate method, and then the relative amplitude of the eddy current sensing signal of the eddy current sensor at the array point position in the array area can be calculated to obtain the defect area in the scanning area.

[0003] However, in the related technology, the process of obtaining data by establishing a database of key nodes in the water system is rather cumbersome, resulting in low data accuracy and making it impossible to select reasonable monitoring points. The method of determining defects by extracting amplitudes has poor real-time performance and is unable to promptly detect potential safety hazards of hydraulic gates, which urgently needs to be improved. Summary of the invention

[0004] The present application provides a method and device for determining remote monitoring points for safety warning of hydraulic gates, in order to solve the problems in related technologies, such as the method of establishing a database of key nodes of a water system, which results in a cumbersome process of acquiring data and low data accuracy, and thus makes it impossible to select reasonable monitoring points; and the method of determining defects by extracting amplitudes has poor real-time performance and is unable to promptly discover potential safety hazards of hydraulic gates.

[0005] A first aspect of the present application provides a method for determining a remote monitoring point for safety warning of a hydraulic gate, comprising the following steps: acquiring first hydraulic gate data of a target hydraulic gate, and identifying the gate category to which the target hydraulic gate belongs based on the first hydraulic gate data; determining second hydraulic gate data of other hydraulic gates of the same category based on the gate category, and calculating a first theoretical vulnerable point of the target hydraulic gate and a second theoretical vulnerable point of the other hydraulic gates based on the first hydraulic gate data and the second hydraulic gate data; projecting the second theoretical vulnerable point onto the target hydraulic gate in sequence to identify at least one actual vulnerable point of the target hydraulic gate; and fusing the first theoretical vulnerable point and the at least one actual vulnerable point to obtain at least one remote monitoring point for safety warning of the target hydraulic gate.

[0006] Through the above technical scheme, the gate category of the target hydraulic gate can be identified according to the first hydraulic gate data of the target hydraulic gate, and the second hydraulic gate data of other hydraulic gates of the same category can be determined, and then the first theoretical vulnerable point of the target hydraulic gate and the second theoretical vulnerable points of the other hydraulic gates can be calculated, so as to project the second theoretical vulnerable points onto the target hydraulic gate in turn, identify the actual vulnerable points of the target hydraulic gate, and then integrate the first theoretical vulnerable points and the actual vulnerable points to obtain the safety early warning remote monitoring points of the target hydraulic gate. Through reasonable selection of monitoring points and effective data analysis, potential safety hazards can be discovered in time, providing a scientific basis for safety management decisions of hydraulic gates, providing a new technical path for the safety management of water conservancy facilities, and promoting the improvement of the safety and management efficiency of water conservancy projects.

[0007] Optionally, in one embodiment of the present application, before identifying the gate category to which the target hydraulic gate belongs based on the first hydraulic gate data, it also includes: acquiring third hydraulic gate data of a preset hydraulic gate; identifying performance index information of the preset hydraulic gate based on the third hydraulic gate data, and obtaining an initial performance index set of the preset hydraulic gate based on the performance index information; processing the initial performance index set to obtain a final performance index set after the initial performance index set is processed; inputting the final performance index set into a pre-constructed Bayesian model of variational inference optimization to obtain at least one gate quantitative index of the preset hydraulic gate; obtaining at least one gate quantitative index sequence of the preset hydraulic gate based on the at least one gate quantitative index; obtaining hash values ​​of all gates in the preset hydraulic gate based on the pre-constructed local sensitive hash function and the at least one gate quantitative index sequence; obtaining the initial gate category of all gates based on the hash value; and pre-processing the initial gate category to obtain the gate category of the preset hydraulic gate.

[0008] Through the above technical scheme, the performance index information can be identified through the third hydraulic gate data of a certain hydraulic gate, and then an initial performance index set can be obtained, and the initial performance index set can be processed to obtain the final performance index set, and then the final performance index set can be input into a pre-built Bayesian model of variational inference optimization to obtain at least one gate quantitative index of a certain hydraulic gate, and then at least one gate quantitative index sequence can be generated, and the hash values ​​of all gates can be obtained in combination with the pre-built local sensitive hash function, so as to obtain the gate category of a certain hydraulic gate. By obtaining the third hydraulic gate data of a certain hydraulic gate, the performance status of the hydraulic gate can be more comprehensively understood. Subsequent identification provides a rich information basis. The use of a pre-built variational inference optimized Bayesian model to obtain quantitative indicators of the gate can take advantage of the Bayesian method in dealing with uncertainty and improve the accuracy and reliability of identification. By processing the initial set of performance indicators, it helps to remove redundant information and improve the efficiency of subsequent processing. The use of a pre-built locally sensitive hash function to construct a hash value can accelerate the data retrieval and matching process and improve the overall recognition efficiency. Through a series of processing and recognition steps, it can realize the automatic recognition and classification of the category to which the hydraulic gate belongs, reduce manual intervention and the subjectivity of judgment, and provide convenience for subsequent monitoring, maintenance and management.

[0009] Optionally, in one embodiment of the present application, the final performance indicator set is input into a pre-constructed variational inference optimized Bayesian model to obtain at least one gate quantitative indicator of the preset hydraulic gate, including: determining the prior distribution of each performance indicator in the final performance indicator set based on the Bayesian model in the pre-constructed variational inference optimized Bayesian model and the final performance indicator set; determining the likelihood function of each performance indicator based on the third hydraulic gate data, the Bayesian model and the final performance indicator set; determining the posterior distribution of each performance indicator using the variational inference optimization in the pre-constructed variational inference optimized Bayesian model; and screening out at least one gate quantitative indicator that meets the preset quantitative indicator conditions from the final performance indicator set based on the prior distribution, the likelihood function and the posterior distribution.

[0010] Through the above technical scheme, the prior distribution, likelihood function and posterior distribution of each performance indicator in the final performance indicator set can be determined according to the pre-constructed variational inference optimized Bayesian model, and then at least one gate quantitative indicator that meets certain quantitative indicator conditions can be screened out. Through the pre-constructed variational inference optimized Bayesian model, prior knowledge and observation data can be used to infer the posterior distribution of performance indicators, so as to more accurately evaluate the state and importance of each performance indicator, improve the calculation efficiency and convergence, and quickly screen out indicators that meet certain quantitative indicator conditions from a large number of performance indicators, thereby enhancing the adaptability and robustness of the model and realizing the automatic extraction of gate quantitative indicators.

[0011] Optionally, in one embodiment of the present application, obtaining at least one gate quantitative index sequence of the preset hydraulic gate based on the at least one gate quantitative index includes: calculating the sensitivity and weight value of at least one gate quantitative index corresponding to each gate in the preset hydraulic gate based on the third hydraulic gate data and the at least one gate quantitative index; calculating the contribution value of at least one gate quantitative index corresponding to each gate based on the sensitivity and the weight value; calculating the product of the sensitivity and the contribution value based on the sensitivity and the contribution value; and obtaining the at least one gate quantitative index sequence based on the product of the sensitivity and the contribution value.

[0012] Through the above technical scheme, the sensitivity and weight value of the gate quantitative index corresponding to each gate in a certain hydraulic gate can be calculated according to the third hydraulic gate data and the gate quantitative index, and then the contribution value of the gate quantitative index corresponding to each gate can be calculated, so as to obtain the gate quantitative index sequence. By calculating the sensitivity and weight value of the gate quantitative index corresponding to each gate, it is possible to more accurately reflect the degree and importance of the influence of each indicator on the gate performance, ensure the authenticity and reliability of the data, thereby improving the accuracy and scientificity of the indicator sequence, and can also more objectively evaluate the overall contribution of each indicator to the gate performance.

[0013] Optionally, in one embodiment of the present application, the calculating the first theoretical vulnerable point of the target hydraulic gate and the second theoretical vulnerable point of the other hydraulic gates based on the first hydraulic gate data and the second hydraulic gate data includes: constructing a three-dimensional geometric model of the target hydraulic gate and the other hydraulic gates based on the first hydraulic gate data and the second hydraulic gate data; obtaining the initial stress concentration area of ​​the target hydraulic gate and the other hydraulic gates based on the three-dimensional geometric model; determining the boundary solution condition of the initial stress concentration area based on the actual working condition information of the target hydraulic gate and the other hydraulic gates; screening the initial stress concentration area based on the boundary solution condition to obtain the final stress concentration area after the initial stress concentration area is screened; and obtaining the first theoretical vulnerable point and the second theoretical vulnerable point based on the final stress concentration area.

[0014] Through the above technical scheme, a three-dimensional geometric model can be constructed based on the first hydraulic gate data and the second hydraulic gate data, and then the initial stress concentration area can be obtained based on the three-dimensional geometric model, and the boundary solution conditions of the initial stress concentration area can be determined, so as to screen the final stress concentration area, and then calculate the first theoretical vulnerable point and the second theoretical vulnerable point. By constructing a three-dimensional geometric model, the actual structure and size of the gate can be more accurately reflected, so as to more accurately identify the vulnerable point. The initial stress concentration area obtained based on the three-dimensional geometric model provides a reliable basis for the subsequent boundary solution condition setting and screening, further improves the accuracy of vulnerable point identification, enhances the scientific nature of vulnerable point identification, optimizes the efficiency of vulnerable point identification, and supports subsequent analysis and maintenance.

[0015] Optionally, in one embodiment of the present application, projecting the second theoretical vulnerable point onto the target hydraulic gate in sequence to identify at least one actual vulnerable point of the target hydraulic gate comprises: determining an initial projection direction of the second theoretical vulnerable point onto the target hydraulic gate based on the similarity between the other hydraulic gates and the target hydraulic gate; inputting the other hydraulic gates into a pre-built projection optimization model to obtain a projection vector of the other hydraulic gates; correcting the initial projection direction based on the projection vector to obtain a final projection direction after the initial projection direction is corrected; projecting the second theoretical vulnerable point onto the target hydraulic gate along the final projection direction to obtain a pointing vulnerable point of the other hydraulic gate pointing to the actual hydraulic gate; calculating a pointing weight of the pointing vulnerable point based on the similarity; and obtaining the at least one actual vulnerable point based on the pointing vulnerable point and the pointing weight.

[0016] Through the above technical scheme, the initial projection direction of the second theoretical vulnerable point projected onto the target hydraulic gate can be determined based on the similarity between other hydraulic gates and the target hydraulic gate, and the projection vector for correcting the initial projection direction can be obtained in combination with the pre-constructed projection optimization model, so as to determine the final projection direction, thereby projecting the second theoretical vulnerable point onto the target hydraulic gate along the final projection direction to obtain the pointing vulnerable point, and then combining the pointing weight of the pointing vulnerable point with at least one actual vulnerable point, the initial projection direction is determined based on the similarity between other hydraulic gates and the target hydraulic gate, and the projection vector is obtained by using the pre-constructed projection optimization model, so as to correct the initial projection direction. This process ensures the accuracy and rationality of the projection direction, can more accurately locate the actual vulnerable point of the target hydraulic gate, and improves the accuracy of recognition. The determination of the pointing vulnerable point and the calculation of the pointing weight can also be automatically completed by a computer, which reduces the subjectivity of manual intervention and judgment and further improves efficiency.

[0017] Optionally, in one embodiment of the present application, the fusion of the first theoretical vulnerable point and the at least one actual vulnerable point to obtain at least one safety warning remote monitoring point of the target hydraulic gate includes: inputting the first theoretical vulnerable point and the at least one actual vulnerable point into a plurality of pre-constructed machine learning models to obtain input information of a pre-constructed meta-model; training and optimizing the pre-constructed meta-model using the input information, the pre-constructed meta-model, and the target hyperparameters in the pre-constructed meta-model to obtain a trained optimized meta-model after the pre-constructed meta-model is trained and optimized; inputting the first theoretical vulnerable point and the actual vulnerable point into the training optimized meta-model to obtain the safety warning remote monitoring point.

[0018] Through the above technical scheme, multiple pre-built machine learning models can be combined to obtain the input information of the pre-built meta-model, and then the pre-built meta-model can be trained and optimized to obtain the trained optimized meta-model, and the first theoretical vulnerable point and the actual vulnerable point are input into the trained optimized meta-model to obtain the safety warning remote monitoring point. By combining the first theoretical vulnerable point and the actual vulnerable point, the advantages of theoretical analysis and actual observation data are fully utilized, so that the safety warning remote monitoring point of the target hydraulic gate can be determined more accurately, which helps to reduce false alarms and missed alarms, improve the overall efficiency of the monitoring system, enhance the intelligence of the monitoring system, and improve the timeliness and effectiveness of the warning. By combining cutting-edge technologies such as machine learning and meta-models, the innovation and development of hydraulic gate monitoring technology is promoted, and a more comprehensive, efficient and intelligent solution is provided for the safety monitoring of hydraulic gates, which helps decision makers make more scientific and reasonable decisions, thereby ensuring the safe and stable operation of hydraulic gates.

[0019] The second aspect of the present application provides a device for determining a remote monitoring point for safety warning of a hydraulic gate, comprising: a first identification module, used to obtain first hydraulic gate data of a target hydraulic gate, and identify the gate category to which the target hydraulic gate belongs based on the first hydraulic gate data; a calculation module, used to determine second hydraulic gate data of other hydraulic gates of the same category based on the gate category, and calculate a first theoretical vulnerable point of the target hydraulic gate and a second theoretical vulnerable point of the other hydraulic gates based on the first hydraulic gate data and the second hydraulic gate data; a second identification module, used to project the second theoretical vulnerable point onto the target hydraulic gate in sequence to identify at least one actual vulnerable point of the target hydraulic gate; and a first generation module, used to fuse the first theoretical vulnerable point and the at least one actual vulnerable point to obtain at least one remote monitoring point for safety warning of the target hydraulic gate.

[0020] Through the above technical scheme, the gate category of the target hydraulic gate can be identified according to the first hydraulic gate data of the target hydraulic gate, and the second hydraulic gate data of other hydraulic gates of the same category can be determined, and then the first theoretical vulnerable point of the target hydraulic gate and the second theoretical vulnerable points of the other hydraulic gates can be calculated, so as to project the second theoretical vulnerable points onto the target hydraulic gate in turn, identify the actual vulnerable points of the target hydraulic gate, and then integrate the first theoretical vulnerable points and the actual vulnerable points to obtain the safety early warning remote monitoring points of the target hydraulic gate. Through reasonable selection of monitoring points and effective data analysis, potential safety hazards can be discovered in time, providing a scientific basis for safety management decisions of hydraulic gates, providing a new technical path for the safety management of water conservancy facilities, and promoting the improvement of the safety and management efficiency of water conservancy projects.

[0021] Optionally, in one embodiment of the present application, it further includes: a first acquisition module, used to acquire third hydraulic gate data of a preset hydraulic gate before identifying the gate category to which the target hydraulic gate belongs based on the first hydraulic gate data; a second generation module, used to identify the performance index information of the preset hydraulic gate based on the third hydraulic gate data, and obtain an initial performance index set of the preset hydraulic gate based on the performance index information; a processing module, used to process the initial performance index set to obtain a final performance index set after the initial performance index set is processed; a second acquisition module, used to input the final performance index set into a pre-built In the Bayesian model of variational inference optimization, at least one gate quantitative index of the preset hydraulic gate is obtained; a third generation module is used to obtain at least one gate quantitative index sequence of the preset hydraulic gate based on the at least one gate quantitative index; a fourth generation module is used to obtain the hash value of all gates in the preset hydraulic gate based on the pre-constructed local sensitive hash function and the at least one gate quantitative index sequence; a fifth generation module is used to obtain the initial gate category of all gates based on the hash value; a sixth generation module is used to preprocess the initial gate category to obtain the gate category of the preset hydraulic gate.

[0022] Through the above technical scheme, the performance index information can be identified through the third hydraulic gate data of a certain hydraulic gate, and then an initial performance index set can be obtained, and the initial performance index set can be processed to obtain the final performance index set, and then the final performance index set can be input into a pre-built Bayesian model of variational inference optimization to obtain at least one gate quantitative index of a certain hydraulic gate, and then at least one gate quantitative index sequence can be generated, and the hash values ​​of all gates can be obtained in combination with the pre-built local sensitive hash function, so as to obtain the gate category of a certain hydraulic gate. By obtaining the third hydraulic gate data of a certain hydraulic gate, the performance status of the hydraulic gate can be more comprehensively understood. Subsequent identification provides a rich information basis. The use of a pre-built variational inference optimized Bayesian model to obtain quantitative indicators of the gate can take advantage of the Bayesian method in dealing with uncertainty and improve the accuracy and reliability of identification. By processing the initial set of performance indicators, it helps to remove redundant information and improve the efficiency of subsequent processing. The use of a pre-built locally sensitive hash function to construct a hash value can accelerate the data retrieval and matching process and improve the overall recognition efficiency. Through a series of processing and recognition steps, it can realize the automatic recognition and classification of the category to which the hydraulic gate belongs, reduce manual intervention and the subjectivity of judgment, and provide convenience for subsequent monitoring, maintenance and management.

[0023] Optionally, in one embodiment of the present application, the second acquisition module includes: a first determination unit, used to determine the prior distribution of each performance indicator in the final performance indicator set based on the Bayesian model in the pre-constructed variational inference optimized Bayesian model and the final performance indicator set; a second determination unit, used to determine the likelihood function of each performance indicator based on the third hydraulic gate data, the Bayesian model and the final performance indicator set; a third determination unit, used to determine the posterior distribution of each performance indicator using the variational inference optimization in the pre-constructed variational inference optimized Bayesian model; a screening unit, used to screen out at least one gate quantitative indicator that meets the preset quantitative indicator conditions from the final performance indicator set based on the prior distribution, the likelihood function and the posterior distribution.

[0024] Through the above technical scheme, the prior distribution, likelihood function and posterior distribution of each performance indicator in the final performance indicator set can be determined according to the pre-constructed variational inference optimized Bayesian model, and then at least one gate quantitative indicator that meets certain quantitative indicator conditions can be screened out. Through the pre-constructed variational inference optimized Bayesian model, prior knowledge and observation data can be used to infer the posterior distribution of performance indicators, so as to more accurately evaluate the state and importance of each performance indicator, improve the calculation efficiency and convergence, and quickly screen out indicators that meet certain quantitative indicator conditions from a large number of performance indicators, thereby enhancing the adaptability and robustness of the model and realizing the automatic extraction of gate quantitative indicators.

[0025] Optionally, in one embodiment of the present application, the third generation module includes: a first calculation unit, used to calculate the sensitivity and weight value of at least one gate quantitative index corresponding to each gate in the preset hydraulic gate based on the third hydraulic gate data and the at least one gate quantitative index; a second calculation unit, used to calculate the contribution value of at least one gate quantitative index corresponding to each gate based on the sensitivity and the weight value; a third calculation unit, used to calculate the product of the sensitivity and the contribution value based on the sensitivity and the contribution value; the first generation unit, used to obtain the at least one gate quantitative index sequence based on the product of the sensitivity and the contribution value.

[0026] Through the above technical scheme, the sensitivity and weight value of the gate quantitative index corresponding to each gate in a certain hydraulic gate can be calculated according to the third hydraulic gate data and the gate quantitative index, and then the contribution value of the gate quantitative index corresponding to each gate can be calculated, so as to obtain the gate quantitative index sequence. By calculating the sensitivity and weight value of the gate quantitative index corresponding to each gate, it is possible to more accurately reflect the degree and importance of the influence of each indicator on the gate performance, ensure the authenticity and reliability of the data, thereby improving the accuracy and scientificity of the indicator sequence, and can also more objectively evaluate the overall contribution of each indicator to the gate performance.

[0027] Optionally, in one embodiment of the present application, the calculation module includes: a construction unit, which is used to construct a three-dimensional geometric model of the target hydraulic gate and the other hydraulic gates based on the first hydraulic gate data and the second hydraulic gate data; a second generation unit, which is used to obtain the initial stress concentration area of ​​the target hydraulic gate and the other hydraulic gates based on the three-dimensional geometric model; a fourth determination unit, which is used to determine the boundary solution condition of the initial stress concentration area based on the actual working condition information of the target hydraulic gate and the other hydraulic gates; a third generation unit, which is used to screen the initial stress concentration area based on the boundary solution condition to obtain the final stress concentration area after the initial stress concentration area is screened; and an acquisition unit, which is used to acquire the first theoretical vulnerable point and the second theoretical vulnerable point based on the final stress concentration area.

[0028] Through the above technical scheme, a three-dimensional geometric model can be constructed based on the first hydraulic gate data and the second hydraulic gate data, and then the initial stress concentration area can be obtained based on the three-dimensional geometric model, and the boundary solution conditions of the initial stress concentration area can be determined, so as to screen the final stress concentration area, and then calculate the first theoretical vulnerable point and the second theoretical vulnerable point. By constructing a three-dimensional geometric model, the actual structure and size of the gate can be more accurately reflected, so as to more accurately identify the vulnerable point. The initial stress concentration area obtained based on the three-dimensional geometric model provides a reliable basis for the subsequent boundary solution condition setting and screening, further improves the accuracy of vulnerable point identification, enhances the scientific nature of vulnerable point identification, optimizes the efficiency of vulnerable point identification, and supports subsequent analysis and maintenance.

[0029] Optionally, in one embodiment of the present application, the second identification module includes: a fifth determination unit, used to determine the initial projection direction of the second theoretical vulnerable point projected onto the target hydraulic gate based on the similarity between the other hydraulic gates and the target hydraulic gate; a fourth generation unit, used to input the other hydraulic gates into a pre-built projection optimization model to obtain the projection vector of the other hydraulic gates; a fifth generation unit, used to correct the initial projection direction based on the projection vector to obtain the final projection direction after the initial projection direction is corrected; a sixth generation unit, used to project the second theoretical vulnerable point onto the target hydraulic gate along the final projection direction to obtain the pointing vulnerable point of the other hydraulic gate pointing to the actual hydraulic gate; a fourth calculation unit, used to calculate the pointing weight of the pointing vulnerable point based on the similarity; and a seventh generation unit, used to obtain the at least one actual vulnerable point based on the pointing vulnerable point and the pointing weight.

[0030] Through the above technical scheme, the initial projection direction of the second theoretical vulnerable point projected onto the target hydraulic gate can be determined based on the similarity between other hydraulic gates and the target hydraulic gate, and the projection vector for correcting the initial projection direction can be obtained in combination with the pre-constructed projection optimization model, so as to determine the final projection direction, thereby projecting the second theoretical vulnerable point onto the target hydraulic gate along the final projection direction to obtain the pointing vulnerable point, and then combining the pointing weight of the pointing vulnerable point with at least one actual vulnerable point, the initial projection direction is determined based on the similarity between other hydraulic gates and the target hydraulic gate, and the projection vector is obtained by using the pre-constructed projection optimization model, so as to correct the initial projection direction. This process ensures the accuracy and rationality of the projection direction, can more accurately locate the actual vulnerable point of the target hydraulic gate, and improves the accuracy of recognition. The determination of the pointing vulnerable point and the calculation of the pointing weight can also be automatically completed by a computer, which reduces the subjectivity of manual intervention and judgment and further improves efficiency.

[0031] Optionally, in one embodiment of the present application, the first generation module includes: an eighth generation unit, used to input the first theoretical vulnerable point and the at least one actual vulnerable point into a plurality of pre-constructed machine learning models to obtain input information of a pre-constructed meta-model; a ninth generation unit, used to train and optimize the pre-constructed meta-model using the input information, the pre-constructed meta-model and the target hyperparameters in the pre-constructed meta-model to obtain a trained optimized meta-model after the pre-constructed meta-model is trained and optimized; and a tenth generation unit, used to input the first theoretical vulnerable point and the actual vulnerable point into the trained optimized meta-model to obtain the safety warning remote monitoring point.

[0032] Through the above technical scheme, multiple pre-built machine learning models can be combined to obtain the input information of the pre-built meta-model, and then the pre-built meta-model can be trained and optimized to obtain the trained optimized meta-model, and the first theoretical vulnerable point and the actual vulnerable point are input into the trained optimized meta-model to obtain the safety warning remote monitoring point. By combining the first theoretical vulnerable point and the actual vulnerable point, the advantages of theoretical analysis and actual observation data are fully utilized, so that the safety warning remote monitoring point of the target hydraulic gate can be determined more accurately, which helps to reduce false alarms and missed alarms, improve the overall efficiency of the monitoring system, enhance the intelligence of the monitoring system, and improve the timeliness and effectiveness of the warning. By combining cutting-edge technologies such as machine learning and meta-models, the innovation and development of hydraulic gate monitoring technology is promoted, and a more comprehensive, efficient and intelligent solution is provided for the safety monitoring of hydraulic gates, which helps decision makers make more scientific and reasonable decisions, thereby ensuring the safe and stable operation of hydraulic gates.

[0033] The third aspect of the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for determining the remote monitoring point of the hydraulic gate safety warning as described in the above embodiment.

[0034] The fourth aspect of the present application provides a computer-readable storage medium, which stores a computer program. When the program is executed by a processor, it implements the above method for determining the remote monitoring point of hydraulic gate safety warning.

[0035] The fifth aspect of the present application provides a computer program product, including a computer program, which, when executed, implements the above-mentioned method for determining the remote monitoring point of hydraulic gate safety warning.

[0036] The embodiment of the present application can identify the gate category of the target hydraulic gate according to the first hydraulic gate data of the target hydraulic gate, and determine the second hydraulic gate data of other hydraulic gates of the same category, and then calculate the first theoretical vulnerable point of the target hydraulic gate and the second theoretical vulnerable points of the other hydraulic gates, so as to project the second theoretical vulnerable points onto the target hydraulic gate in turn, identify the actual vulnerable points of the target hydraulic gate, and then fuse the first theoretical vulnerable points and the actual vulnerable points to obtain the remote monitoring point of the safety warning of the target hydraulic gate. Through reasonable monitoring point selection and effective data analysis, potential safety hazards can be discovered in time, providing a scientific basis for the safety management decision of the hydraulic gate, providing a new technical path for the safety management of water conservancy facilities, and promoting the improvement of the safety and management efficiency of water conservancy projects. Therefore, the method of establishing a database of key nodes of the water system in the related technology solves the problem that the process of obtaining data is relatively cumbersome, resulting in low data accuracy, and thus it is impossible to select reasonable monitoring points, and the method of determining defects by extracting amplitudes has poor real-time performance and cannot timely discover the potential safety hazards of the hydraulic gate.

[0037] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0039] Figure 1 A flowchart of a method for determining a hydraulic gate safety warning remote monitoring point according to an embodiment of the present application;

[0040] Figure 2 A flowchart of obtaining a gate category according to an embodiment of the present application;

[0041] Figure 3 A flowchart of generating gate quantitative indicators according to an embodiment of the present application;

[0042] Figure 4 A flowchart of generating a gate quantitative index sequence according to an embodiment of the present application;

[0043] Figure 5 A flowchart of calculating a theoretical vulnerable point according to an embodiment of the present application;

[0044] Figure 6 A flowchart of calculating an actual vulnerable point according to an embodiment of the present application;

[0045] Figure 7A flowchart of generating a remote monitoring point for safety warning according to an embodiment of the present application;

[0046] Figure 8 A flowchart of the working principle of a method for determining a hydraulic gate safety early warning remote monitoring point according to an embodiment of the present application;

[0047] Fig. 9 A schematic block diagram of a device for determining a hydraulic gate safety early warning remote monitoring point according to an embodiment of the present application;

[0048] Fig.10 It is a schematic diagram of the structure of an electronic device provided according to an embodiment of the present application. Description of the drawings:

[0050] Among them, 90-hydraulic gate safety warning remote monitoring point determination device; 100-first identification module, 200-calculation module, 300-second identification module, 400-first generation module; 1001-memory, 1002-processor, 1003-communication interface. DETAILED DESCRIPTION

[0051] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0052] The following describes the method and device for determining the remote monitoring point for the safety warning of hydraulic gates according to the embodiment of the present application with reference to the accompanying drawings. With regard to the method mentioned in the background technology mentioned above, the process of obtaining data by establishing a database of key nodes of the water system is relatively cumbersome, resulting in low data accuracy, and thus the inability to select reasonable monitoring points. The method of determining defects by extracting amplitudes has poor real-time performance and is unable to promptly discover potential safety hazards of hydraulic gates. The present application provides a method for determining the remote monitoring point for the safety warning of hydraulic gates. In this method, the gate category of the target hydraulic gate can be identified based on the first hydraulic gate data of the target hydraulic gate, and the second hydraulic gate data of other hydraulic gates of the same category can be determined to perform a remote monitoring of the hydraulic gate safety warning. The first theoretical vulnerable point of the target hydraulic gate and the second theoretical vulnerable point of other hydraulic gates are calculated, and the second theoretical vulnerable point is projected onto the target hydraulic gate in turn, the actual vulnerable point of the target hydraulic gate is identified, and then the first theoretical vulnerable point and the actual vulnerable point are integrated to obtain the remote monitoring point of the safety warning of the target hydraulic gate. Through reasonable selection of monitoring points and effective data analysis, potential safety hazards can be discovered in time, providing a scientific basis for safety management decisions of hydraulic gates, providing a new technical path for the safety management of water conservancy facilities, and promoting the improvement of safety and management efficiency of water conservancy projects. In this way, the problem that the method of establishing a database of key nodes of the water system in the related technology is cumbersome, resulting in low data accuracy, and thus unable to select reasonable monitoring points, and the method of determining defects by extracting amplitudes has poor real-time performance and cannot timely discover potential safety hazards of hydraulic gates is solved.

[0053] Specifically, Figure 1 The present invention is a flowchart of a method for determining remote monitoring points for safety warning of hydraulic gates provided according to an embodiment of the present application.

[0054] like Figure 1 As shown, the method for determining the remote monitoring point position of the hydraulic gate safety early warning includes the following steps:

[0055] In step S101, first hydraulic gate data of a target hydraulic gate is acquired, and the gate category of the target hydraulic gate is identified based on the first hydraulic gate data.

[0056] Among them, in the embodiment of the present application, the first hydraulic gate data may include but is not limited to the design parameters of the hydraulic gate, working environment influencing factors, operation data and maintenance records, etc., and the present application does not make specific restrictions.

[0057] Furthermore, in the embodiments of the present application, the design parameters may include but are not limited to gate size, material, type, etc., and the present application does not make specific restrictions; the working environment influencing factors may include but are not limited to pressure, flow rate, temperature, etc., and the present application does not make specific restrictions; the operating data may include but are not limited to opening frequency, closing frequency, flow rate, operating status; the maintenance records may include but are not limited to fault type, maintenance time, maintenance cost, etc., and the present application does not make specific restrictions.

[0058] In addition, the gate categories belonging to the embodiments of the present application are divided according to the nature of their work, which may include but are not limited to working gates, accident gates, maintenance gates, etc., and the present application does not make specific restrictions; divided according to the type, it may include but is not limited to plane gates, arc gates, miter gates, flap gates, revolving gates, plane arc gates, etc., and the present application does not make specific restrictions; divided according to the position during operation, it may include but is not limited to exposed top type, submerged hole type, submerged type, etc., and the present application does not make specific restrictions. It is attached to buildings such as dams, sluices, pumping stations, hydropower water diversion, spillways, and ship locks. According to its location, it may be at surface holes, deep holes, bottom holes, inlets / outlets, tunnels, pressure regulating wells, etc. where gates are required for flow or water level control. In terms of its function, it may have flood control, water retaining, tide blocking, flood discharge, sand discharge, emptying, water transfer, rapid opening and closing, etc., and the present application does not make specific restrictions.

[0059] In some embodiments, the embodiments of the present application may first obtain first hydraulic gate data of a target hydraulic gate, and then use the first hydraulic gate data to calculate a quantitative index sequence of the target hydraulic gate, thereby identifying the gate category to which the target hydraulic gate belongs.

[0060] For example, the embodiment of the present application can obtain the first hydraulic gate data of the target hydraulic gate, such as the design parameters of the hydraulic gate, working environment influencing factors, operation data, etc., and calculate the quantitative index sequence of the target hydraulic gate based on the acquired first hydraulic gate data, and identify the gate category of the target hydraulic gate as a radial gate according to the quantitative index sequence.

[0061] Optionally, in one embodiment of the present application, before identifying the gate category to which the target hydraulic gate belongs based on the first hydraulic gate data, it also includes: acquiring third hydraulic gate data of a preset hydraulic gate; identifying performance indicator information of the preset hydraulic gate based on the third hydraulic gate data, and obtaining an initial performance indicator set of the preset hydraulic gate based on the performance indicator information; processing the initial performance indicator set to obtain a final performance indicator set after the initial performance indicator set is processed; inputting the final performance indicator set into a pre-constructed Bayesian model of variational inference optimization to obtain at least one gate quantitative indicator of the preset hydraulic gate; obtaining at least one gate quantitative indicator sequence of the preset hydraulic gate based on at least one gate quantitative indicator; obtaining hash values ​​of all gates in the preset hydraulic gate based on a pre-constructed local sensitive hash function and at least one gate quantitative indicator sequence; obtaining initial gate categories of all gates based on the hash values; and pre-processing the initial gate category to obtain the gate category of the preset hydraulic gate.

[0062] It should be noted that the embodiments of the present application are biased towards planning for different projects, and the relevant factors involved mainly include: coordination with the upper-level planning, water management concepts, flood control systems, standards, criteria, engineering standards and levels, function determination, gate site selection, overall project layout, gate type selection, operation mode, investment estimation, technical difficulty estimation, etc., and the present application does not make specific restrictions; biased towards design, the relevant factors involved mainly include: project location, historical investigation, flood characteristics, various design load selection, special load selection, overall project and water building layout, gate design, navigable channel or lock design, water quality and aquatic life protection design, reliability calculation, etc., and the present application does not make specific restrictions; biased towards environmental impact assessment, the relevant factors involved mainly include: project location, economic, social and cultural, water quality, fishery resources, biology, seabed and river morphology, flow rate and flow, birds, nature reserves, etc., and the present application does not make specific restrictions.

[0063] In addition, in the embodiment of the present application, the gate category of a certain hydraulic gate includes the gate category to which the target hydraulic gate belongs.

[0064] In some embodiments, before identifying the gate category of the target hydraulic gate, the embodiment of the present application may first obtain the gate category of a certain hydraulic gate, the main contents of which are as follows: Figure 2 As shown, it mainly includes the following steps:

[0065] Step S201: Acquire the third hydraulic gate data of a certain hydraulic gate.

[0066] Step S202: Identify the performance index information of a certain hydraulic gate and obtain an initial performance index set.

[0067] Among them, the embodiment of the present application can identify all performance indicator information that affects the performance of a certain hydraulic gate and obtain an initial performance indicator set.

[0068] Step S203: Process the initial performance indicator set to obtain a final performance indicator set.

[0069] Among them, the embodiment of the present application can process the initial performance indicator set, such as standardizing and converting the units of all indicators in the initial performance indicator set, and then obtaining the processed final performance indicator set.

[0070] Step S204: using a pre-built variational inference optimized Bayesian model to obtain at least one gate quantitative index of a certain hydraulic gate.

[0071] Among them, the embodiment of the present application can use the third hydraulic gate data to screen and obtain at least one gate quantitative index using a pre-built variational inference optimized Bayesian model.

[0072] Step S205: obtaining at least one gate quantitative index sequence of a certain hydraulic gate based on at least one gate quantitative index.

[0073] Among them, the embodiment of the present application can calculate the sensitivity and contribution value of at least one gate quantitative indicator corresponding to all gates in sequence, sort the at least one gate quantitative indicator of each gate according to the product of the sensitivity and contribution value of the indicator, and obtain at least one gate quantitative indicator sequence corresponding to each gate.

[0074] Step S206: Obtain hash values ​​of all gates according to the pre-constructed local sensitive hash function.

[0075] Among them, the embodiment of the present application can input at least one gate quantitative indicator sequence of each gate into a pre-constructed local sensitive hash function in turn, construct a hash table, and obtain the hash values ​​of all gates in the preset hydraulic gates based on the hash table.

[0076] Step S207: Obtaining initial gate categories of all gates based on the hash values.

[0077] Among them, the embodiment of the present application can screen out gates with the same hash value, and classify the gates with the same hash value into the same candidate set, that is, obtain the initial gate category of all gates.

[0078] Step S208: pre-process the initial gate category to obtain the gate category.

[0079] Among them, the embodiment of the present application can pre-process the initial gate category to obtain the gate category of all gates.

[0080] Exemplarily, the embodiment of the present application can perform cosine similarity calculation based on local sensitive hashing on all gates in the same candidate set, set a similarity threshold, classify gates with similarity greater than the similarity threshold into the same category, and cluster all gate pairs using K-means clustering to obtain N gate classifications, where N is a positive integer greater than 5. In addition, the similarity threshold can be set by a person skilled in the art according to actual conditions, and this application does not impose any specific restrictions.

[0081] It should be noted that the cosine similarity calculation based on local sensitive hashing in the embodiment of the present application may include: converting feature data into a high-dimensional vector representation and calculating the cosine similarity for each gate; processing all gate data, hash mapping the feature vectors, and clustering similar gates together to quickly retrieve gates with higher similarity.

[0082] In addition, the characteristics and monitoring data of the gate in the embodiment of the present application are usually high-dimensional. Locally sensitive hashing can map high-dimensional data to low-dimensional space while maintaining similarity, and keep similar data relatively close during mapping, so that cosine similarity calculation can be performed quickly on large-scale data sets, avoiding the high overhead of calculating the similarity of each pair of data points in traditional methods; cosine similarity calculation based on local sensitive hashing optimization has significant advantages in gate similarity analysis, especially when processing high-dimensional and sparse data. It has high efficiency and accuracy, improves the scalability of calculation, and after using local sensitive hashing, similarity estimates can be obtained through fewer comparisons, significantly reducing calculation time, maintaining the local structure of the data, and making similar cases maintain a certain degree of proximity after mapping, which can more effectively identify potential problems and help engineers quickly identify and analyze similar gate characteristics and failure modes.

[0083] Optionally, in one embodiment of the present application, the final performance indicator set is input into a pre-built variational inference optimized Bayesian model to obtain at least one gate quantitative indicator of a preset hydraulic gate, including: determining the prior distribution of each performance indicator in the final performance indicator set based on the Bayesian model in the pre-built variational inference optimized Bayesian model and the final performance indicator set; determining the likelihood function of each performance indicator based on the third hydraulic gate data, the Bayesian model and the final performance indicator set; determining the posterior distribution of each performance indicator using the variational inference optimization in the pre-built variational inference optimized Bayesian model; and screening out at least one gate quantitative indicator that meets the preset quantitative indicator conditions from the final performance indicator set based on the prior distribution, the likelihood function and the posterior distribution.

[0084] In some embodiments, the present application can use a pre-built variational inference optimized Bayesian model to obtain at least one gate quantitative index of a certain hydraulic gate, the main contents of which are as follows: Figure 3 As shown, it mainly includes the following steps:

[0085] Step S301: Determine the prior distribution of each performance indicator.

[0086] Among them, the embodiment of the present application can be based on the Bayesian model in the pre-constructed variational inference optimized Bayesian model, using existing literature and the prior distribution of each performance indicator in the previously set final performance indicator set.

[0087] In addition, the Bayesian model optimized based on the pre-built variational inference in the embodiment of the present application is an efficient machine learning method. By introducing prior knowledge, it effectively handles and quantifies uncertainty. When analyzing gates, data and model noise will affect the results. Bayesian inference can better manage these uncertainties; variational inference optimization uses the variational principle to approximate the true posterior distribution by optimizing a simple distribution. Compared with traditional methods, variational inference is faster and can process data of higher dimensions; the Bayesian model can not only fuse the prediction results of multiple models, but also assign weights to different models. In model training, the Bayesian model can automatically select important features for the target variable through evidence inference. In the process of collecting gate data, changes in the environment and usage conditions will affect the importance of the indicators. The Bayesian model can dynamically adjust the weights of each indicator according to these changes and adapt to new data. The Bayesian model based on the pre-built variational inference optimization can provide decision makers with interpretability of indicator selection by using prior knowledge and posterior inference, integrate information from different sources, and optimize the selection of quantitative indicators to ensure that not only historical data is used, but also potential future risks are taken into account.

[0088] For example, in the gate management of a certain large reservoir in the embodiment of the present application, the management team hopes to screen out the most critical gate quantitative indicators to improve the efficiency of its maintenance and monitoring. The main contents may be: first collect gate data including historical monitoring data, environmental conditions, material properties and gate service year indicators; then use the traditional linear regression model to perform a preliminary vulnerable point analysis, and obtain the initial gate quantitative indicators based on the analysis results, wherein the initial gate quantitative indicators have important factors that are not considered; use a Bayesian model based on a pre-built variational inference optimization to improve the linear regression model, introduce prior information from different models, perform variational inference to obtain the posterior distribution, and then obtain the importance of several key indicators predicted by the linear regression model, which may include but are not limited to stress ratio, number of fatigue cycles and degree of corrosion, etc., and this application does not make specific restrictions.

[0089] Step S302: Determine the likelihood function of each performance indicator.

[0090] Among them, the embodiment of the present application can be based on the Bayesian model in the pre-constructed variational inference optimized Bayesian model, and use the third hydraulic gate data to set the influence relationship of each performance indicator in the final performance indicator set on the result as a likelihood function.

[0091] Step S303: Determine the posterior distribution of each performance indicator.

[0092] Among them, the embodiments of the present application can optimize the approximate posterior distribution based on variational inference in a pre-constructed variational inference optimized Bayesian model.

[0093] Step S304: screening at least one gate quantitative index that meets certain quantitative index conditions.

[0094] Among them, the embodiment of the present application can set the variational distribution based on the prior distribution, likelihood function and posterior distribution, optimize the variational parameters, update through the iterative algorithm until convergence, and screen out the indicators that meet certain quantitative index conditions based on the posterior distribution (such as the indicators that have an impact on gate performance greater than a threshold in the posterior distribution as gate quantitative indicators), and then obtain the gate quantitative indicator set. Among them, certain quantitative indicator conditions can be set by technicians in this field according to actual conditions, and this application does not make specific restrictions.

[0095] Optionally, in one embodiment of the present application, at least one gate quantitative index sequence of a preset hydraulic gate is obtained based on at least one gate quantitative index, including: calculating the sensitivity and weight value of at least one gate quantitative index corresponding to each gate in the preset hydraulic gate based on the third hydraulic gate data and at least one gate quantitative index; calculating the contribution value of at least one gate quantitative index corresponding to each gate based on the sensitivity and the weight value; calculating the product of the sensitivity and the contribution value based on the sensitivity and the contribution value; and obtaining at least one gate quantitative index sequence based on the product of the sensitivity and the contribution value.

[0096] In some embodiments, the present application can obtain at least one gate quantitative indicator sequence based on at least one gate quantitative indicator, the main contents of which are as follows: Figure 4 As shown, it mainly includes the following steps:

[0097] Step S401: Calculate the sensitivity of at least one gate quantitative index corresponding to each gate.

[0098] Among them, the embodiment of the present application can use the Monte Carlo simulation method to analyze the gate quantitative index corresponding to each gate in turn, and obtain the sensitivity of the gate quantitative index corresponding to each gate.

[0099] Specifically, the Monte Carlo simulation method of the embodiment of the present application is a powerful and practical method in the analysis of quantitative indicators of gates. It evaluates the behavior of models and systems through random sampling and thousands or even millions of simulations, and can quantify and analyze uncertainty well. The quantitative indicators of gates may have uncertainty. Monte Carlo simulation can capture uncertainty through multiple random samplings and provide a probability distribution of output indicators. In addition, the Monte Carlo simulation method can comprehensively consider the relationship between multiple variables. By simultaneously analyzing multiple input variables and their interactions, the Monte Carlo simulation method can provide a more comprehensive sensitivity analysis and identify the factors that are most likely to have a significant impact on the indicators. In the embodiment of the present application, the behavior of the gate is usually affected by multiple factors, and these factors may have nonlinear relationships. The Monte Carlo simulation method can handle complex and nonlinear systems to ensure that the performance of the gate under different conditions can be more accurately reflected. Therefore, in the embodiment of the present application, the Monte Carlo simulation method is used to analyze the quantitative indicators of the gate.

[0100] For example, the embodiments of the present application can collect input gate data, which may include but is not limited to inflow flow, gate material properties, installation errors, soil conditions, flood water levels, etc. The present application does not make specific restrictions. Furthermore, the embodiments of the present application randomly samples the input gate data, simulates a large number of different condition combinations, calculates the failure probability and structural response of the gate under different conditions, and analyzes the failure probability of the gate under extreme conditions, and evaluates the sensitivity of different input gate data to the gate's quantitative indicators.

[0101] Step S402: Determine the weight value of the gate quantitative index corresponding to each gate.

[0102] Among them, the embodiments of the present application can, but are not limited to, determine the weight value of the gate quantitative index corresponding to each gate in each gate performance index by collecting literature and expert opinions, with the aim of assigning different weights to different gate quantitative indicators corresponding to each gate, and then calculating the contribution value of each gate quantitative indicator.

[0103] Step S403: Calculate the contribution value of the gate quantitative index corresponding to each gate.

[0104] Among them, the embodiment of the present application can calculate the contribution value of each gate quantitative indicator based on the sensitivity and weight value of the gate quantitative indicator corresponding to each gate.

[0105] Step S404: Generate a gate quantitative index sequence.

[0106] Among them, the embodiment of the present application can calculate the product of sensitivity and contribution value for each gate quantitative indicator of each gate, and sort the products of sensitivity and contribution value of all gate quantitative indicators of the gate, so as to obtain the gate quantitative indicator sequence of the gate, and calculate the gate quantitative indicator sequence of all gates in sequence.

[0107] In step S102, based on the gate category, the second hydraulic gate data of other hydraulic gates of the same category are determined, and based on the first hydraulic gate data and the second hydraulic gate data, the first theoretical vulnerable point of the target hydraulic gate and the second theoretical vulnerable points of other hydraulic gates are calculated.

[0108] As a possible implementation method, the embodiment of the present application can extract the second hydraulic gate data of other hydraulic gates in the same category as the target hydraulic gate in the gate category to which the target hydraulic gate belongs, perform finite element static analysis on the target hydraulic gate and the other hydraulic gates in turn, and obtain the first theoretical vulnerable point of the target hydraulic gate and the second theoretical vulnerable points of the other hydraulic gates.

[0109] In addition, the discrepancy between the vulnerable points found during maintenance of the target hydraulic gate in the embodiment of the present application and the finite element static analysis results may be caused by the following reasons: material fatigue and aging, differences between actual working conditions and theoretical models, setting of boundary conditions, changes in loads, construction quality and maintenance, and model simplification, etc. This application does not make specific restrictions.

[0110] Among them, material fatigue and aging can be understood as the fact that during the long-term use of the gate, the material may become fatigued and aged. These factors are usually assumed to be ideal and uniform in finite element static analysis, but in reality there may be changes in material properties.

[0111] The difference between actual working conditions and theoretical models can be understood as finite element static analysis is usually based on idealized assumptions and simplified models, while actual working conditions may be more complicated, such as the impact of water flow, the influence of sediments, temperature changes, etc., which may lead to inconsistencies between actual stress conditions and theoretical analysis.

[0112] The setting of boundary conditions can be understood as the fact that in finite element static analysis, the setting of boundary conditions has a great influence on the results. If the boundary conditions are not set accurately, the analysis results may not match the actual situation.

[0113] The change of load can be understood as that in actual operation, the load borne by the gate may change over time, such as water level fluctuations, flow changes, etc., and finite element static analysis is usually performed based on a specific state.

[0114] Construction quality and maintenance can be understood as quality problems that may exist during the construction process, or failure to promptly discover and deal with problems during subsequent maintenance, which may result in the gate's vulnerable points not being reflected in the theoretical analysis.

[0115] Model simplification can be understood as the simplification of the model for the convenience of calculation in finite element static analysis, ignoring some details and complex geometric shapes, which may cause the analysis results to be inconsistent with the actual situation.

[0116] Optionally, in one embodiment of the present application, based on the first hydraulic gate data and the second hydraulic gate data, calculating the first theoretical vulnerable point of the target hydraulic gate and the second theoretical vulnerable point of the other hydraulic gates includes: constructing a three-dimensional geometric model of the target hydraulic gate and the other hydraulic gates based on the first hydraulic gate data and the second hydraulic gate data; obtaining the initial stress concentration area of ​​the target hydraulic gate and the other hydraulic gates based on the three-dimensional geometric model; determining the boundary solution condition of the initial stress concentration area based on the actual working condition information of the target hydraulic gate and the other hydraulic gates; screening the initial stress concentration area based on the boundary solution condition to obtain the final stress concentration area after the initial stress concentration area is screened; and obtaining the first theoretical vulnerable point and the second theoretical vulnerable point based on the final stress concentration area.

[0117] In some embodiments, the present application embodiment can obtain the first theoretical vulnerable point of the target hydraulic gate and the second theoretical vulnerable point of other hydraulic gates through the first hydraulic gate data and the second hydraulic gate data. The main contents are as follows: Figure 5 As shown, it mainly includes the following steps:

[0118] Step S501: Determine the gate category to which the target hydraulic gate belongs, and extract the second hydraulic gate data of other hydraulic gates.

[0119] Among them, the embodiments of the present application can be combined with Figure 2 As shown, the gate category of the target hydraulic gate is determined, and all gate data of the gate category are extracted.

[0120] Step S502: construct a three-dimensional geometric model.

[0121] Among them, the embodiment of the present application can use ANSYS to sequentially construct three-dimensional geometric models of the target hydraulic gate and other hydraulic gates based on the first hydraulic gate data and the second hydraulic gate data.

[0122] Step S503: Calculate the initial stress concentration area.

[0123] Among them, the embodiment of the present application can perform finite element meshing on the three-dimensional geometric model and determine the mesh scale based on the initial stress concentration area.

[0124] Step S504: Determine the boundary solution conditions of the initial stress concentration area.

[0125] Among them, the embodiment of the present application can set boundary conditions and static loads based on the actual working condition information of the target hydraulic gate and other hydraulic gates, set solver parameters based on the static analysis type, and then determine the boundary solution conditions of the initial stress concentration area.

[0126] Step S505: Obtain the final stress concentration area.

[0127] Among them, the embodiment of the present application can start finite element solution, screen the initial stress concentration area, and then obtain the final stress concentration area.

[0128] Step S506: Calculate the first theoretical vulnerable point and the second theoretical vulnerable point.

[0129] Among them, the embodiment of the present application can identify the theoretical vulnerable points of all gates based on the final stress concentration area, and then obtain the first theoretical vulnerable point of the target hydraulic gate and the second theoretical vulnerable points of other hydraulic gates.

[0130] In step S103, the second theoretical vulnerable points are sequentially projected onto the target hydraulic gate to identify at least one actual vulnerable point of the target hydraulic gate.

[0131] In the actual implementation process, the embodiment of the present application can sequentially project the second theoretical vulnerable points of all gates in other hydraulic gates onto the target hydraulic gate, and then identify the actual vulnerable points of the target hydraulic gate.

[0132] Optionally, in one embodiment of the present application, the second theoretical vulnerable point is sequentially projected onto the target hydraulic gate to identify at least one actual vulnerable point of the target hydraulic gate, including: determining an initial projection direction of the second theoretical vulnerable point projected onto the target hydraulic gate based on the similarity between other hydraulic gates and the target hydraulic gate; inputting the other hydraulic gates into a pre-built projection optimization model to obtain projection vectors of the other hydraulic gates; correcting the initial projection direction based on the projection vector to obtain a final projection direction after the initial projection direction is corrected; projecting the second theoretical vulnerable point onto the target hydraulic gate along the final projection direction to obtain a pointing vulnerable point of the other hydraulic gate pointing to the actual hydraulic gate; calculating a pointing weight of the pointing vulnerable point based on the similarity; and obtaining at least one actual vulnerable point based on the pointing vulnerable point and the pointing weight.

[0133] In some embodiments, the main contents of the embodiment of the present application identifying at least one actual vulnerable point of the target hydraulic gate are as follows: Figure 6 As shown, it mainly includes the following steps:

[0134] Step S601: determining an initial projection direction of the second theoretical vulnerable point onto a target hydraulic gate.

[0135] Among them, the embodiment of the present application can select the initial projection direction based on the similarity between the target hydraulic gate and each gate of other hydraulic gates.

[0136] Step S602: Obtain projection vectors of other hydraulic gates.

[0137] Among them, the embodiment of the present application can input each gate of other hydraulic gates into a pre-built projection optimization model to obtain the projection vector of each gate.

[0138] Step S603: obtaining the vulnerable point of other hydraulic gates pointing to the actual hydraulic gate.

[0139] Among them, the embodiment of the present application can use the projection vector to correct the initial projection direction to obtain the vulnerable point that each gate points to the actual hydraulic gate.

[0140] Step S604: Calculate the directional weight pointing to the vulnerable point.

[0141] Among them, the embodiment of the present application can calculate the directional weight of each gate based on the similarity between each gate in other hydraulic gates and the target hydraulic gate.

[0142] Step S605: Generate at least one actual vulnerable point.

[0143] Among them, the embodiment of the present application can assign the directional weight of each gate to the corresponding directional vulnerable point, and then merge to obtain the actual vulnerable point of the target hydraulic gate.

[0144] In step S104, the first theoretical vulnerable point and at least one actual vulnerable point are integrated to obtain at least one safety warning remote monitoring point of the target hydraulic gate.

[0145] It can be understood by those skilled in the art that the embodiment of the present application can use the stacking method to fuse the first theoretical vulnerable point and the actual vulnerable point of the target hydraulic gate, and then obtain the safety warning remote monitoring point of the target hydraulic gate.

[0146] It can be understood that the stacking method is an integrated learning method that combines the prediction results of multiple models to improve the accuracy of the final prediction. In the embodiments of the present application, by combining multiple machine learning models and utilizing the advantages of different models, a more comprehensive perspective can be provided by fusing the predictions of different models, thereby reducing the deviations that may be caused by a single model. When using multiple models for prediction, the stacking method can reduce the risk of overfitting. Different models may be sensitive to different aspects of the training data. By combining their outputs, the generalization ability of the model can be improved.

[0147] Optionally, in one embodiment of the present application, the first theoretical vulnerable point and at least one actual vulnerable point are integrated to obtain at least one safety warning remote monitoring point of the target hydraulic gate, including: inputting the first theoretical vulnerable point and at least one actual vulnerable point into multiple pre-built machine learning models to obtain input information of a pre-built metamodel; training and optimizing the pre-built metamodel using the input information, the pre-built metamodel, and the target hyperparameters in the pre-built metamodel to obtain a training optimized metamodel after the pre-built metamodel is trained and optimized; inputting the first theoretical vulnerable point and the actual vulnerable point into the training optimized metamodel to obtain the safety warning remote monitoring point.

[0148] In some embodiments, the main contents of at least one safety warning remote monitoring point of the target hydraulic gate generated by the embodiment of the present application are as follows: Figure 7 As shown, it mainly includes the following steps:

[0149] Step S701: Construct multiple machine learning models and meta-models.

[0150] Step S702: Obtain input information of a pre-built meta-model.

[0151] Among them, the embodiment of the present application can input the first theoretical vulnerable point and actual vulnerable point data of the target hydraulic gate into multiple pre-built machine learning models in sequence, and use the outputs of the multiple machine learning models as input information of the pre-built meta-model to train the meta-model.

[0152] Step S703: training and optimizing the pre-built meta-model.

[0153] Among them, the embodiment of the present application can use the Random Search method to optimize the hyperparameters of the meta-model to obtain a trained optimized meta-model.

[0154] Step S704: Generate safety warning remote monitoring points.

[0155] Among them, the embodiment of the present application can input the first theoretical vulnerable point and the actual vulnerable point of the target hydraulic gate into the training optimization meta-model to obtain the safety warning remote monitoring point of the target hydraulic gate.

[0156] The working principle of the method for determining the remote monitoring point for safety warning of hydraulic gates proposed in the embodiment of the present application is introduced below in conjunction with a specific embodiment.

[0157] in, Figure 8 The present invention is a flowchart of the working principle of a method for determining remote monitoring points for safety warning of hydraulic gates provided according to an embodiment of the present application.

[0158] Step S801: obtaining the third hydraulic gate data of a certain hydraulic gate, screening the gate quantitative index of the certain hydraulic gate, calculating the hash value of all gates in the certain hydraulic gate, and then dividing the certain hydraulic gate based on the gates with the same hash value, and then obtaining the gate category of all gates in the certain hydraulic gate.

[0159] Step S802: Calculate the gate quantitative index sequence of the target hydraulic gate, extract the second hydraulic gate data of other hydraulic gates of the same category, perform finite element static analysis on the target hydraulic gate and other hydraulic gates in turn, and obtain the first theoretical vulnerable point of the target hydraulic gate and the second theoretical vulnerable points of other hydraulic gates.

[0160] Step S803: sequentially projecting the second theoretical vulnerable points of all gates in other hydraulic gates onto the target hydraulic gate, and then identifying the actual vulnerable points of the target hydraulic gate.

[0161] Step S804: The first theoretical vulnerable point and the actual vulnerable point of the target hydraulic gate are integrated by using the stacking method, thereby obtaining the safety warning remote monitoring point of the target hydraulic gate.

[0162] According to the method for determining the remote monitoring point position for safety early warning of hydraulic gates proposed in the embodiment of the present application, the gate category of the target hydraulic gate can be identified according to the first hydraulic gate data of the target hydraulic gate, and the second hydraulic gate data of other hydraulic gates of the same category can be determined, and then the first theoretical vulnerable point of the target hydraulic gate and the second theoretical vulnerable points of the other hydraulic gates can be calculated, so as to project the second theoretical vulnerable points onto the target hydraulic gate in turn, identify the actual vulnerable points of the target hydraulic gate, and then integrate the first theoretical vulnerable points and the actual vulnerable points to obtain the remote monitoring point position for safety early warning of the target hydraulic gate. Through reasonable selection of monitoring points and effective data analysis, potential safety hazards can be discovered in time, providing a scientific basis for safety management decisions of hydraulic gates, providing a new technical path for the safety management of water conservancy facilities, and promoting the improvement of the safety and management efficiency of water conservancy projects. This solves the problem in related technologies that the process of acquiring data by establishing a database of key nodes in the water system is rather cumbersome, resulting in low data accuracy and making it impossible to select reasonable monitoring points; and the method of determining defects by extracting amplitudes has poor real-time performance and is unable to promptly detect potential safety hazards of hydraulic gates.

[0163] Next, a device for determining the remote monitoring point position of a hydraulic gate safety warning proposed in accordance with an embodiment of the present application will be described with reference to the accompanying drawings.

[0164] Fig. 9 It is a block diagram of a device for determining a hydraulic gate safety warning remote monitoring point according to an embodiment of the present application.

[0165] like Fig. 9 As shown, the hydraulic gate safety early warning remote monitoring point determination device 90 includes: a first identification module 100, a calculation module 200, a second identification module 300 and a first generation module 400.

[0166] The first identification module 100 is used to obtain first hydraulic gate data of a target hydraulic gate, and identify the gate category of the target hydraulic gate based on the first hydraulic gate data.

[0167] The calculation module 200 is used to determine the second hydraulic gate data of other hydraulic gates of the same category based on the gate category, and calculate the first theoretical vulnerable point of the target hydraulic gate and the second theoretical vulnerable points of other hydraulic gates based on the first hydraulic gate data and the second hydraulic gate data.

[0168] The second identification module 300 is used to project the second theoretical vulnerable points onto the target hydraulic gate in sequence to identify at least one actual vulnerable point of the target hydraulic gate.

[0169] The first generating module 400 is used to fuse the first theoretical vulnerable point and at least one actual vulnerable point to obtain at least one safety warning remote monitoring point of the target hydraulic gate.

[0170] Optionally, in one embodiment of the present application, it also includes: a first acquisition module, a second generation module, a processing module, a second acquisition module, a third generation module, a fourth generation module, a fifth generation module and a sixth generation module.

[0171] The first acquisition module is used to acquire the third hydraulic gate data of the preset hydraulic gate before identifying the gate category of the target hydraulic gate based on the first hydraulic gate data.

[0172] The second generating module is used to identify the performance index information of the preset hydraulic gate based on the third hydraulic gate data, and obtain the initial performance index set of the preset hydraulic gate based on the performance index information.

[0173] The processing module is used to process the initial performance indicator set to obtain a final performance indicator set after the initial performance indicator set is processed.

[0174] The second acquisition module is used to input the final performance indicator set into a pre-built Bayesian model of variational inference optimization to obtain at least one gate quantitative indicator of a preset hydraulic gate.

[0175] The third generating module is used to obtain at least one gate quantitative index sequence of a preset hydraulic gate based on at least one gate quantitative index.

[0176] The fourth generation module is used to obtain hash values ​​of all gates in the preset hydraulic gates based on a pre-built local sensitive hash function and at least one gate quantitative indicator sequence.

[0177] The fifth generation module is used to obtain initial gate categories of all gates based on the hash values.

[0178] The sixth generation module is used to pre-process the initial gate category to obtain the gate category of the preset hydraulic gate.

[0179] Optionally, in one embodiment of the present application, the second acquisition module includes: a first determination unit, a second determination unit, a third determination unit and a screening unit.

[0180] The first determination unit is used to determine the prior distribution of each performance indicator in the final performance indicator set based on the Bayesian model in the pre-built variational inference optimized Bayesian model and the final performance indicator set.

[0181] The second determination unit is used to determine the likelihood function of each performance indicator based on the third hydraulic gate data, the Bayesian model and the final performance indicator set.

[0182] The third determination unit is used to determine the posterior distribution of each performance indicator by using the variational inference optimization in the pre-built variational inference optimization Bayesian model.

[0183] The screening unit is used to screen out at least one gate quantitative index that meets the preset quantitative index conditions from the final performance index set based on the prior distribution, the likelihood function and the posterior distribution.

[0184] Optionally, in one embodiment of the present application, the third generating module includes: a first calculating unit, a second calculating unit, a third calculating unit and a first generating unit.

[0185] Among them, the first calculation unit is used to calculate the sensitivity and weight value of at least one gate quantitative index corresponding to each gate in the preset hydraulic gates based on the third hydraulic gate data and at least one gate quantitative index.

[0186] The second calculation unit is used to calculate the contribution value of at least one gate quantitative index corresponding to each gate based on the sensitivity and the weight value.

[0187] The third calculation unit is used to calculate the product of the sensitivity and the contribution value based on the sensitivity and the contribution value.

[0188] The first generating unit is used to obtain at least one gate quantitative indicator sequence based on the product of the sensitivity and the contribution value.

[0189] Optionally, in one embodiment of the present application, the calculation module 200 includes: a construction unit, a second generation unit, a fourth determination unit, a third generation unit and an acquisition unit.

[0190] The construction unit is used to construct a three-dimensional geometric model of the target hydraulic gate and other hydraulic gates based on the first hydraulic gate data and the second hydraulic gate data.

[0191] The second generation unit is used to obtain the initial stress concentration area of ​​the target hydraulic gate and other hydraulic gates based on the three-dimensional geometric model.

[0192] The fourth determination unit is used to determine the boundary solution condition of the initial stress concentration area based on the actual working condition information of the target hydraulic gate and other hydraulic gates.

[0193] The third generation unit is used to screen the initial stress concentration area based on the boundary solution condition to obtain the final stress concentration area after the initial stress concentration area is screened.

[0194] The acquisition unit is used to acquire the first theoretical vulnerable point and the second theoretical vulnerable point based on the final stress concentration area.

[0195] Optionally, in one embodiment of the present application, the second identification module 300 includes: a fifth determination unit, a fourth generation unit, a fifth generation unit, a sixth generation unit, a fourth calculation unit and a seventh generation unit.

[0196] The fifth determining unit is used to determine an initial projection direction of the second theoretical vulnerable point onto the target hydraulic gate based on the similarity between other hydraulic gates and the target hydraulic gate.

[0197] The fourth generating unit is used to input other hydraulic gates into the pre-built projection optimization model to obtain the projection vectors of other hydraulic gates.

[0198] The fifth generating unit is used to correct the initial projection direction based on the projection vector to obtain a final projection direction after the initial projection direction is corrected.

[0199] The sixth generating unit is used to project the second theoretical vulnerable point onto the target hydraulic gate along the final projection direction to obtain the pointing vulnerable point of other hydraulic gates pointing to the actual hydraulic gate.

[0200] The fourth calculation unit is used to calculate the directional weight pointing to the vulnerable point based on the similarity.

[0201] The seventh generating unit is used to obtain at least one actual vulnerable point based on the pointing vulnerable point and the pointing weight.

[0202] Optionally, in one embodiment of the present application, the first generation module 400 includes: an eighth generation unit, a ninth generation unit and a tenth generation unit.

[0203] Among them, the eighth generation unit is used to input the first theoretical vulnerable point and at least one actual vulnerable point into multiple pre-built machine learning models to obtain input information of the pre-built meta-model.

[0204] The ninth generation unit is used to train and optimize the pre-built meta-model using the input information, the pre-built meta-model and the target hyperparameters in the pre-built meta-model to obtain a training optimized meta-model after the pre-built meta-model is trained and optimized.

[0205] The tenth generating unit is used to input the first theoretical vulnerable point and the actual vulnerable point into the training optimization meta-model to obtain the safety warning remote monitoring point.

[0206] It should be noted that the above explanation of the embodiment of the method for determining the remote monitoring point position of the hydraulic gate safety warning is also applicable to the device for determining the remote monitoring point position of the hydraulic gate safety warning of this embodiment, and will not be repeated here.

[0207] According to the hydraulic gate safety early warning remote monitoring point determination device proposed in the embodiment of the present application, the gate category of the target hydraulic gate can be identified according to the first hydraulic gate data of the target hydraulic gate, and the second hydraulic gate data of other hydraulic gates of the same category can be determined, and then the first theoretical vulnerable point of the target hydraulic gate and the second theoretical vulnerable points of the other hydraulic gates are calculated, so as to project the second theoretical vulnerable points onto the target hydraulic gate in turn, identify the actual vulnerable points of the target hydraulic gate, and then integrate the first theoretical vulnerable points and the actual vulnerable points to obtain the safety early warning remote monitoring points of the target hydraulic gate. Through reasonable monitoring point selection and effective data analysis, potential safety hazards can be discovered in time, providing a scientific basis for safety management decisions of hydraulic gates, providing a new technical path for the safety management of water conservancy facilities, and promoting the improvement of the safety and management efficiency of water conservancy projects. This solves the problem in related technologies that the process of acquiring data by establishing a database of key nodes in the water system is rather cumbersome, resulting in low data accuracy and making it impossible to select reasonable monitoring points; and the method of determining defects by extracting amplitudes has poor real-time performance and is unable to promptly detect potential safety hazards of hydraulic gates.

[0208] Fig.10 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of the present application. The electronic device may include:

[0209] A memory 1001 , a processor 1002 , and a computer program stored in the memory 1001 and executable on the processor 1002 .

[0210] When the processor 1002 executes the program, the method for determining the remote monitoring point of the hydraulic gate safety warning provided in the above embodiment is implemented.

[0211] Furthermore, the electronic device also includes:

[0212] The communication interface 1003 is used for communication between the memory 1001 and the processor 1002 .

[0213] The memory 1001 is used to store computer programs that can be executed on the processor 1002 .

[0214] The memory 1001 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0215] If the memory 1001, the processor 1002 and the communication interface 1003 are implemented independently, the communication interface 1003, the memory 1001 and the processor 1002 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig.10 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0216] Optionally, in a specific implementation, if the memory 1001, the processor 1002 and the communication interface 1003 are integrated on a chip, the memory 1001, the processor 1002 and the communication interface 1003 can communicate with each other through an internal interface.

[0217] The processor 1002 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0218] An embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the above method for determining the remote monitoring point position of a hydraulic gate safety warning is implemented.

[0219] An embodiment of the present application also provides a computer program product, including a computer program, which, when executed, implements the above method for determining remote monitoring points for hydraulic gate safety warning.

[0220] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0221] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0222] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0223] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or N wirings (electronic devices), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways as necessary and then storing it in a computer memory.

[0224] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented by hardware, as in another embodiment, it can be implemented by any one or a combination of multiple of the following technologies known in the art: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0225] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0226] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0227] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for determining the remote monitoring point position of hydraulic gate safety early warning, characterized in that: The following steps are involved: Acquire first hydraulic gate data of a target hydraulic gate, and identify the gate category to which the target hydraulic gate belongs based on the first hydraulic gate data; Based on the gate category, determine the second hydraulic gate data of other hydraulic gates of the same category, and based on the first hydraulic gate data and the second hydraulic gate data, calculate the first theoretical vulnerable point of the target hydraulic gate and the second theoretical vulnerable points of the other hydraulic gates; Projecting the second theoretical vulnerable points onto the target hydraulic gate in sequence to identify at least one actual vulnerable point of the target hydraulic gate; The first theoretical vulnerable point and the at least one actual vulnerable point are integrated to obtain at least one safety warning remote monitoring point of the target hydraulic gate.

2. The method according to claim 1, characterized in that Before identifying the gate category of the target hydraulic gate based on the first hydraulic gate data, the method further includes: Acquire the third hydraulic gate data of the preset hydraulic gate; Identifying performance index information of the preset hydraulic gate based on the third hydraulic gate data, and obtaining an initial performance index set of the preset hydraulic gate based on the performance index information; Processing the initial performance indicator set to obtain a final performance indicator set after the initial performance indicator set is processed; Inputting the final performance index set into a pre-built Bayesian model of variational inference optimization to obtain at least one gate quantitative index of the preset hydraulic gate; Obtaining at least one gate quantitative index sequence of the preset hydraulic gate based on the at least one gate quantitative index; Based on the pre-constructed local sensitive hash function and the at least one gate quantitative index sequence, obtaining hash values ​​of all gates in the preset hydraulic gates; Obtaining initial gate categories of all the gates based on the hash value; The initial gate category is preprocessed to obtain the gate category of the preset hydraulic gate.

3. The method according to claim 2, characterized in that The step of inputting the final performance index set into a pre-built Bayesian model of variational inference optimization to obtain at least one gate quantitative index of the preset hydraulic gate comprises: Determine a priori distribution of each performance indicator in the final performance indicator set based on the Bayesian model in the pre-built variational inference optimized Bayesian model and the final performance indicator set; Determining a likelihood function of each performance indicator based on the third hydraulic gate data, the Bayesian model and the final performance indicator set; Determine the posterior distribution of each performance indicator using variational inference optimization in the pre-built variational inference optimized Bayesian model; At least one gate quantitative index that meets a preset quantitative index condition is selected from the final performance index set based on the prior distribution, the likelihood function and the posterior distribution.

4. The method according to claim 2, characterized in that: The step of obtaining at least one gate quantitative index sequence of the preset hydraulic gate based on the at least one gate quantitative index comprises: Calculate the sensitivity and weight value of at least one gate quantitative index corresponding to each gate in the preset hydraulic gates based on the third hydraulic gate data and the at least one gate quantitative index; Based on the sensitivity and the weight value, calculating a contribution value of at least one gate quantitative index corresponding to each gate; Based on the sensitivity and the contribution value, calculating the product of the sensitivity and the contribution value; Based on the product of the sensitivity and the contribution value, the at least one gate quantitative indicator sequence is obtained.

5. The method according to claim 1, characterized in that The calculating, based on the first hydraulic gate data and the second hydraulic gate data, the first theoretical vulnerable point of the target hydraulic gate and the second theoretical vulnerable points of the other hydraulic gates comprises: Based on the first hydraulic gate data and the second hydraulic gate data, constructing a three-dimensional geometric model of the target hydraulic gate and the other hydraulic gates; Obtaining initial stress concentration areas of the target hydraulic gate and the other hydraulic gates based on the three-dimensional geometric model; Determining the boundary solution condition of the initial stress concentration area based on the actual working condition information of the target hydraulic gate and the other hydraulic gates; Screening the initial stress concentration region based on the boundary solution condition to obtain a final stress concentration region after the initial stress concentration region is screened; The first theoretical vulnerable point and the second theoretical vulnerable point are obtained based on the final stress concentration area.

6. The method according to claim 1, characterized in that The projecting the second theoretical vulnerable points onto the target hydraulic gate in sequence to identify at least one actual vulnerable point of the target hydraulic gate comprises: Based on the similarity between the other hydraulic gates and the target hydraulic gate, determining an initial projection direction of the second theoretical vulnerable point onto the target hydraulic gate; Inputting the other hydraulic gates into a pre-built projection optimization model to obtain projection vectors of the other hydraulic gates; Correct the initial projection direction based on the projection vector to obtain a final projection direction after the initial projection direction is corrected; Projecting the second theoretical vulnerable point onto the target hydraulic gate along the final projection direction to obtain the vulnerable point pointed by the other hydraulic gates to the actual hydraulic gate; Calculating the directional weight pointing to the vulnerable point based on the similarity; Based on the pointing vulnerable point and the pointing weight, the at least one actual vulnerable point is obtained.

7. The method according to claim 1, characterized in that The fusing of the first theoretical vulnerable point and the at least one actual vulnerable point to obtain at least one safety warning remote monitoring point of the target hydraulic gate includes: Inputting the first theoretical vulnerable point and the at least one actual vulnerable point into a plurality of pre-built machine learning models to obtain input information of a pre-built meta-model; Performing training optimization on the pre-constructed meta-model using the input information, the pre-constructed meta-model and the target hyper-parameters in the pre-constructed meta-model to obtain a training optimized meta-model after the pre-constructed meta-model is trained and optimized; The first theoretical vulnerable point and the actual vulnerable point are input into the training optimization meta-model to obtain the safety warning remote monitoring point.

8. A hydraulic gate safety early warning remote monitoring point determination device, characterized in that: include: A first identification module is used to obtain first hydraulic gate data of a target hydraulic gate, and identify the gate category of the target hydraulic gate based on the first hydraulic gate data; A calculation module, for determining, based on the gate category, second hydraulic gate data of other hydraulic gates of the same category, and calculating, based on the first hydraulic gate data and the second hydraulic gate data, a first theoretical vulnerable point of the target hydraulic gate and a second theoretical vulnerable point of the other hydraulic gates; a second identification module, configured to project the second theoretical vulnerable points onto the target hydraulic gate in sequence to identify at least one actual vulnerable point of the target hydraulic gate; A generation module is used to fuse the first theoretical vulnerable point and the at least one actual vulnerable point to obtain at least one safety warning remote monitoring point of the target hydraulic gate.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for determining the remote monitoring point of a hydraulic gate safety warning as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the method for determining the remote monitoring point position of a hydraulic gate safety warning as described in any one of claims 1 to 7.

Images