Intelligent early warning method and system applied to dam safety monitoring

Abstract

The invention discloses an intelligent early warning method and system applied to dam safety monitoring, and relates to the technical field of dam safety detection.The intelligent early warning method comprises the following steps that sensing nodes are installed on the surface of a dam, and data collected by the sensing nodes are transmitted to a centralized processing center through the Internet of Things technology; establishing a deep learning model to perform pattern recognition and anomaly detection on the data collected by the sensing nodes, and judging whether the dam is abnormal or not; and an intelligent decision model is established, analysis is performed in combination with a large number of abnormal signals, the abnormal degree and trend are evaluated, and a corresponding coping strategy is formulated. According to the method, the machine analysis model and the expert evaluation model are set, the specific condition of the dam is synchronously calculated in two modes, the reasonability and accuracy of the calculation result are ensured, effective and reasonable calculation is performed again according to the specific condition when the calculated abnormal result of the dam is different until the abnormal result of the dam is obtained, and the accuracy of the dam is improved. And acceptance of operators is facilitated.

Description

Technical Field

[0001] This invention relates to the field of dam safety monitoring technology, and in particular to an intelligent early warning method and system for dam safety monitoring. Background Technology

[0002] Due to its geographical environment, my country has gradually become a major dam-building nation in the world. These projects have brought benefits and mitigated harm, playing a significant role in the development of the national economy. Reservoirs and dams, as crucial water conservancy projects, provide enormous engineering benefits and bear the heavy responsibility of supporting people's daily lives and industrial and agricultural production.

[0003] However, in practical applications, relying on regular patrols to inspect dams presents challenges due to the wide inspection scope, numerous devices, heavy workload, and uneven experience and skill levels among inspection personnel. These issues include non-standard inspections, low efficiency, missed inspections, and misjudgments. Therefore, it is necessary to utilize AI systems to assist inspection personnel in monitoring dam safety. Summary of the Invention

[0004] In view of the problems existing in the intelligent early warning and control systems applied to dam safety monitoring, this invention is proposed.

[0005] Therefore, the problem to be solved by this invention is how to detect dam safety and how to make certain judgments and early warnings about potential dangers.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0007] In a first aspect, embodiments of the present invention provide an intelligent early warning method for dam safety monitoring, comprising the following steps:

[0008] Sensing nodes are installed on the surface of the dam, and the data collected by these nodes is transmitted to a centralized processing center via Internet of Things (IoT) technology.

[0009] A deep learning model is established to perform pattern recognition and anomaly detection on the data collected by the sensing nodes to determine whether the dam is abnormal.

[0010] Establish an intelligent decision-making model, analyze a large number of abnormal signals, assess the degree and trend of abnormality, and formulate corresponding response strategies.

[0011] As a preferred embodiment of the intelligent early warning method for dam safety monitoring described in this invention, when the data collected by the sensing nodes is transmitted to the centralized processing center, the data is cleaned, noise and outliers are removed, and the data is standardized for subsequent analysis and comparison.

[0012] The sensing nodes include real-time data and historical data, wherein both real-time data and historical data are multi-source data integration models of groundwater level, rainfall, dam displacement, stress and temperature difference sensors.

[0013] The sensing node obtains a comprehensive view of the dam's safety status to grasp the dam's real-time condition and potential risks, and its expression includes:

[0014]

[0015] In the formula, μD i Represented as a data source, D i Expressed as the average value, δD i It is expressed as standard deviation.

[0016] As a preferred embodiment of the intelligent early warning method for dam safety monitoring described in this invention, the establishment of the deep learning model includes:

[0017] Y = φ(W*X + b)

[0018] In the formula, X represents the input data, Y represents the output data, W represents the weight, and b represents the bias term;

[0019] The output data is adjusted by modifying the weights and biases. The methods for adjusting the weights and biases are as follows:

[0020]

[0021]

[0022] In the formula, a represents the learning rate, a hyperparameter used to control the adjustment magnitude, and L represents the loss function to be minimized.

[0023] As a preferred embodiment of the intelligent early warning method for dam safety monitoring described in this invention, the deep learning model further includes a machine analysis model and an expert evaluation model.

[0024] When both the machine analysis model and the expert evaluation model output that the dam is abnormal, an alarm is triggered and a signal is sent to the staff via the APP platform.

[0025] If both the machine analysis model and the expert evaluation model output that the dam is normal, no action will be taken, and regular inspections will continue.

[0026] When the output structure of the machine analysis model indicates that the dam is normal, but the output result of the expert evaluation model indicates that the dam is abnormal, the output result is one of three types.

[0027] When the output structure of the machine analysis model is dam anomaly, but the output result of the expert evaluation model is dam normal, the output result is one of four categories;

[0028] The interval between regular inspections is directly proportional to the difference between the probability of a dam hazard and the critical value. Specific methods include:

[0029] The greater the difference between the probability of a dam malfunction and the critical value, the longer the interval between regular inspections should be set.

[0030] The smaller the difference between the probability of a dam malfunction and the critical value, the shorter the interval between regular inspections should be.

[0031] As a preferred embodiment of the intelligent early warning method for dam safety monitoring described in this invention, the judgment methods for the three types of results include:

[0032] The data is recalibrated to ensure its quality and accuracy. The machine analysis model and the expert evaluation model are recalculated. If the output results change, the output results of the dam are reassessed according to the above steps.

[0033] When the output remains unchanged, the output of the expert evaluation model is added to the machine analysis model, using the following formula:

[0034] Y new =Y old *(1-c)+β*c

[0035] In the formula, Y new Represented as the predicted value, Y old This represents the original output data, β represents the new value, and c represents the proportion of the new value.

[0036] The predicted output is adjusted by changing the weight of the new value. The calculation is performed 5 times, and the majority result of the 5 calculations is taken.

[0037] As a preferred embodiment of the intelligent early warning method for dam safety monitoring described in this invention, the judgment methods for the four types of results include:

[0038] The data is recalibrated to ensure its quality and accuracy. The machine analysis model and the expert evaluation model are recalculated. If the output results change, the output results of the dam are reassessed according to the above steps.

[0039] When the output remains unchanged, the following method is generated by combining two adjacent sets of machine analysis models:

[0040] Y new =Y n / 2+Yn-1 *e+Y n+1 *(0.5-e)

[0041] In the formula, Y new Represented as the predicted value, Y n Y represents the result of the nth machine analysis model. n+1 and Y n-1 'e' represents the results of two adjacent machine analysis models, and 'e' represents the weight value.

[0042] As a preferred embodiment of the intelligent early warning method for dam safety monitoring described in this invention, the assessment of the degree of anomaly includes:

[0043] Mild abnormality with a predicted value of 0%–30%, moderate abnormality with a predicted value of 31%–70%, and severe abnormality with a predicted value of 71%–100%;

[0044] The strategy for dealing with mild anomalies is to monitor the dam in real time, shorten the computation interval of the deep learning model, and record the computation data.

[0045] The strategy for dealing with moderate anomalies is to establish a corresponding plan based on the strategy for dealing with mild anomalies, including the division of responsibilities, response plans, and emergency contacts.

[0046] The response strategy for severe anomalies is to trigger emergency plans, including a comprehensive assessment and repair of the dam, evacuation of personnel, and closure of nearby areas.

[0047] Secondly, embodiments of the present invention provide an intelligent early warning system for dam safety monitoring, comprising:

[0048] The detection module is used to connect to the sensing node, process and judge the data received by the sensing node, eliminate abnormal values, and finally transmit the data.

[0049] The judgment module builds different models based on the data to perform calculations on the data. It realizes the use of different calculation methods for different dam conditions, which plays a role in detecting whether the dam is abnormal and ensuring the safety of the dam.

[0050] The output module can transmit the results from the judgment module to different types of staff based on the APP, so that staff of different types can operate their own work in a timely manner and ensure the rational and orderly operation of the staff.

[0051] Thirdly, embodiments of the present invention provide a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement any of the steps of the above-described intelligent early warning method for dam safety monitoring.

[0052] Fourthly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the above-described intelligent early warning method for dam safety monitoring.

[0053] The beneficial effects of this invention are as follows: It sets up a machine analysis model and an expert evaluation model, and calculates the specific situation of the dam simultaneously through the two methods, ensuring the rationality and accuracy of the calculation results. When the calculated abnormal results of the dam are different, it performs effective and reasonable calculations again according to the specific situation until the abnormal result of the dam is obtained, which facilitates the handling of the problem by the operators.

[0054] Different approaches will be used to develop early warning and response strategies for dams in response to different abnormal outcomes, in order to minimize losses, protect property, and prevent larger accidents. Attached Figure Description

[0055] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein:

[0056] Figure 1 This is a flowchart of an intelligent early warning method applied to dam safety monitoring.

[0057] Figure 2 This is a scenario diagram illustrating an intelligent early warning method applied to dam safety monitoring.

[0058] Figure 3 This is a diagram showing the installation of sensing nodes for an intelligent early warning method applied to dam safety monitoring. Detailed Implementation

[0059] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0060] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0061] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0062] This invention is described in detail with reference to the schematic diagrams. When detailing the embodiments of this invention, for ease of explanation, the cross-sectional views illustrating the device structure may be partially enlarged, not adhering to the usual scale. Furthermore, the schematic diagrams are merely examples and should not be construed as limiting the scope of protection of this invention. In actual fabrication, the three-dimensional spatial dimensions of length, width, and depth should be included.

[0063] Furthermore, in the description of this invention, it should be noted that the terms "upper," "lower," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. These terms are used solely for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. In addition, the terms "first," "second," or "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0064] Unless otherwise explicitly specified and limited, the terms "installation," "connection," and "joining" in this invention should be interpreted broadly. For example, they can refer to fixed connections, detachable connections, or integral connections; similarly, they can refer to mechanical connections, electrical connections, or direct connections, or indirect connections through an intermediate medium, or internal connections between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0065] Example 1

[0066] Reference Figures 1-3 This is the first embodiment of the present invention, which provides an intelligent early warning method for dam safety monitoring, comprising the following steps:

[0067] S1. Install sensing nodes on the dam surface. The data collected by the sensing nodes is transmitted to a centralized processing center via Internet of Things (IoT) technology.

[0068] When the data collected by the sensing nodes is transmitted to the centralized processing center, the data is cleaned, noise and outliers are removed, and the data is standardized for subsequent analysis and comparison.

[0069] The sensing nodes include real-time data and historical data, wherein both real-time data and historical data are multi-source data integration models of groundwater level, rainfall, dam displacement, stress and temperature difference sensors.

[0070] When installing the sensing nodes, one sensing node needs to be installed on each dam body, with each dam body corresponding to a sensing node. The installation diagram is attached to the instruction manual. Figure 2 As shown;

[0071] The sensing node obtains a comprehensive view of the dam's safety status to grasp the dam's real-time condition and potential risks, and its expression includes:

[0072]

[0073] In the formula, μD i Represented as a data source, D i Expressed as the average value, δD i It is expressed as standard deviation.

[0074] S2. Establish a deep learning model to perform pattern recognition and anomaly detection on the data collected by the sensing nodes, and determine whether the dam is abnormal.

[0075] Building the deep learning model includes:

[0076] Y = φ(W*X + b)

[0077] In the formula, X represents the input data, Y represents the output data, W represents the weight, b represents the bias term, and φ represents the activation function, which can be Sigmoid, Tanh, or ReLU, but is not limited in this embodiment.

[0078] Furthermore, the model is a computational model of one dam body within a dam, and the input data is the data detected by the sensing nodes installed corresponding to that dam body.

[0079] The output data is adjusted by modifying the weights and biases. The methods for adjusting the weights and biases are as follows:

[0080]

[0081]

[0082] In the formula, a represents the learning rate, a hyperparameter used to control the adjustment magnitude, and L represents the loss function to be minimized.

[0083] The establishment of the deep learning model also includes machine analysis models and expert evaluation models;

[0084] When both the machine analysis model and the expert evaluation model output that the dam is abnormal, an alarm is triggered and a signal is sent to the staff via the APP platform.

[0085] If both the machine analysis model and the expert evaluation model output that the dam is normal, no action will be taken, and regular inspections will continue.

[0086] When the output structure of the machine analysis model indicates that the dam is normal, but the output result of the expert evaluation model indicates that the dam is abnormal, the output result is one of three types.

[0087] When the output structure of the machine analysis model is dam anomaly, but the output result of the expert evaluation model is dam normal, the output result is one of four categories;

[0088] The interval between regular inspections is directly proportional to the difference between the probability of a dam hazard and the critical value. Specific methods include:

[0089] The greater the difference between the probability of a dam malfunction and the critical value, the longer the interval between regular inspections should be set.

[0090] The smaller the difference between the probability of a dam malfunction and the critical value, the shorter the interval between regular inspections should be.

[0091] The methods for judging the three types of results include:

[0092] The data is recalibrated to ensure its quality and accuracy. The machine analysis model and the expert evaluation model are recalculated. If the output results change, the output results of the dam are reassessed according to the above steps.

[0093] When the output remains unchanged, the output of the expert evaluation model is added to the machine analysis model, using the following formula:

[0094] Y new =Y old *(1-c)+β*c

[0095] In the formula, Y new Represented as the predicted value, Y old This represents the original output data, β represents the new value, and c represents the proportion of the new value.

[0096] Specifically, the predicted output value is adjusted by changing the weight of the new value, and the majority of the five results is taken. When the weight of the new value is changed, the value is adjusted up twice and down twice, for a total of five calculations.

[0097] The four types of results are judged as follows:

[0098] The data is recalibrated to ensure its quality and accuracy. The machine analysis model and the expert evaluation model are recalculated. If the output results change, the output results of the dam are reassessed according to the above steps.

[0099] When the output remains unchanged, the following method is generated by combining two adjacent sets of machine analysis models:

[0100] Y new =Y n / 2+Y n-1 *e+Y n+1 *(0.5-e)

[0101] In the formula, Y new Represented as the predicted value, Y n Y represents the result of the nth machine analysis model. n+1 and Y n-1 'e' represents the results of two adjacent machine analysis models, and 'e' represents the weight value.

[0102] In specific calculations, as per the instruction manual... Figure 3 As shown, taking the third group of machine analysis models as an example, the third group of machine analysis models first receives data through the third group of sensing nodes corresponding to the third group of dam bodies. Then, the data is transmitted to the machine analysis models established by the second group of sensing nodes and the fourth group of sensing nodes respectively. The machine analysis models established by the second group of sensing nodes and the fourth group of sensing nodes calculate the data. Because the second group of sensing nodes and the fourth group of sensing nodes are adjacent to the third group of sensing nodes, the machine analysis models established by the second group of sensing nodes and the fourth group of sensing nodes perform more specific calculations on the data. When the calculation structures of the machine analysis models established by the second group of sensing nodes, the third group of sensing nodes, and the fourth group of sensing nodes are the same, the abnormal results of the dam are judged as abnormal. When two of the machine analysis models are abnormal, and one machine analysis model and the expert evaluation model are normal, the abnormal result of the dam is output as normal, but it is marked for the convenience of staff to verify it a second time.

[0103] S3. Establish an intelligent decision-making model, analyze a large number of abnormal signals, assess the degree and trend of abnormality, and formulate corresponding response strategies.

[0104] The assessment of anomalies includes:

[0105] Mild abnormality with a predicted value of 0%–30%, moderate abnormality with a predicted value of 31%–70%, and severe abnormality with a predicted value of 71%–100%;

[0106] The strategy for dealing with mild anomalies is to monitor the dam in real time, shorten the computation interval of the deep learning model, and record the computation data.

[0107] The strategy for dealing with moderate anomalies is to establish a corresponding plan based on the strategy for dealing with mild anomalies, including the division of responsibilities, response plans, and emergency contacts.

[0108] The response strategy for severe anomalies is to trigger emergency plans, including a comprehensive assessment and repair of the dam, evacuation of personnel, and closure of nearby areas.

[0109] In summary, both machine analysis and expert evaluation models were established to simultaneously calculate the specific conditions of the dam, ensuring the rationality and accuracy of the calculation results. When the calculated abnormal results for the dam differed, effective and reasonable calculations were performed again based on the specific circumstances until the abnormal result for the dam was obtained, facilitating the handling of the situation by operators. When the abnormal results for the dam differed, different methods were used to implement early warning and response strategies for the dam, greatly reducing losses, protecting property, and preventing larger accidents.

[0110] Example 2

[0111] Based on the first embodiment, this embodiment further provides an intelligent early warning system for dam safety monitoring, including:

[0112] The detection module is used to connect to the sensing node, process and judge the data received by the sensing node, eliminate abnormal values, and finally transmit the data.

[0113] The judgment module builds different models based on the data to perform calculations on the data. It realizes the use of different calculation methods for different dam conditions, which plays a role in detecting whether the dam is abnormal and ensuring the safety of the dam.

[0114] The output module can transmit the results from the judgment module to different types of staff based on the APP, so that staff of different types can operate their own work in a timely manner and ensure the rational and orderly operation of the staff.

[0115] This embodiment also provides a computer device applicable to the intelligent early warning method for dam safety monitoring, including a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to realize the intelligent early warning method for dam safety monitoring as proposed in the above embodiment.

[0116] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0117] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, it implements the intelligent early warning method for dam safety monitoring as proposed in the above embodiments.

[0118] The storage medium proposed in this embodiment and the data storage method proposed in the above embodiments belong to the same inventive concept. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0119] Example 3

[0120] The third embodiment of the present invention, based on the first two embodiments, provides an intelligent early warning method for dam safety monitoring. To verify the beneficial effects of the present invention, a simulation experiment is conducted for scientific demonstration.

[0121] Comparative Example 1: Only machine analysis models were used to identify dam anomalies, without the use of expert evaluation models;

[0122] Comparative Example 2: Only the expert evaluation model was used, without the use of machine analysis models to identify dam anomalies;

[0123] The verification method is as follows: historical data is input into Comparative Example 1, Comparative Example 2 and Example 1 respectively. Based on different calculation methods, it is determined whether the dam is abnormal. Then, the actual results of the dam in the historical data are used for reverse verification. The accuracy rate of Comparative Example 1, Comparative Example 2 and Example 1 is calculated, and the uncertainty rate is calculated. The data is input a total of 10,000 times.

[0124] accuracy Uncertainty Comparative Example 1 82.37％ 6.7％ Comparative Example 2 87.51％ 4.6％ Example 1 99.75％ 0.03％

[0125] The table above shows that relying on a single model identification calculation, whether for Comparative Example 1 or Comparative Example 2, is prone to errors and cannot determine whether the dam is abnormal based on some data. Therefore, by combining the two model identification calculations and performing secondary identification on uncertain judgment results, the accuracy of dam anomaly judgment can be greatly increased and uncertain factors can be reduced.

[0126] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. An intelligent early warning method for dam safety monitoring, characterized in that: Includes the following steps, Sensing nodes are installed on the surface of the dam, and the data collected by these nodes is transmitted to a centralized processing center via Internet of Things (IoT) technology. A deep learning model is established to perform pattern recognition and anomaly detection on the data collected by the sensing nodes to determine whether the dam is abnormal. Establish an intelligent decision-making model, analyze a large number of abnormal signals, assess the degree and trend of abnormality, and formulate corresponding response strategies.

2. The intelligent early warning method for dam safety monitoring as described in claim 1, characterized in that: When the data collected by the sensing nodes is transmitted to the centralized processing center, the data is cleaned, noise and outliers are removed, and the data is standardized for subsequent analysis and comparison. The sensing nodes include real-time data and historical data, wherein both real-time data and historical data are multi-source data integration models of groundwater level, rainfall, dam displacement, stress and temperature difference sensors. The sensing node obtains a comprehensive view of the dam's safety status to grasp the dam's real-time condition and potential risks, and its expression includes: In the formula, μD i Represented as a data source, D i Expressed as the average value, δD i It is expressed as standard deviation.

3. The intelligent early warning method for dam safety monitoring as described in claim 2, characterized in that: Building the deep learning model includes: Y = φ(W*X + b) In the formula, X represents the input data, Y represents the output data, W represents the weight, and b represents the bias term; The output data is adjusted by modifying the weights and biases. The methods for adjusting the weights and biases are as follows: In the formula, a represents the learning rate, a hyperparameter used to control the adjustment magnitude, and L represents the loss function to be minimized.

4. The intelligent early warning method for dam safety monitoring as described in claim 3, characterized in that: The establishment of the deep learning model also includes machine analysis models and expert evaluation models; When both the machine analysis model and the expert evaluation model output that the dam is abnormal, an alarm is triggered and a signal is sent to the staff via the APP platform. If both the machine analysis model and the expert evaluation model output that the dam is normal, no action will be taken, and regular inspections will continue. When the output structure of the machine analysis model indicates that the dam is normal, but the output result of the expert evaluation model indicates that the dam is abnormal, the output result is one of three types. When the output structure of the machine analysis model is dam anomaly, but the output result of the expert evaluation model is dam normal, the output result is one of four categories; The interval between regular inspections is directly proportional to the difference between the probability of a dam hazard and the critical value. Specific methods include: The greater the difference between the probability of a dam malfunction and the critical value, the longer the interval between regular inspections should be set. The smaller the difference between the probability of a dam malfunction and the critical value, the shorter the interval between regular inspections should be.

5. The intelligent early warning method for dam safety monitoring as described in claim 4, characterized in that: The methods for judging the three types of results include: The data is recalibrated to ensure its quality and accuracy. The machine analysis model and the expert evaluation model are recalculated. If the output results change, the output results of the dam are reassessed according to the above steps. When the output remains unchanged, the output of the expert evaluation model is added to the machine analysis model, using the following formula: Y new =Y old *(1-c)+β*c In the formula, Y new Represented as the predicted value, Y old This represents the original output data, β represents the new value, and c represents the proportion of the new value. The predicted output is adjusted by changing the weight of the new value. The calculation is performed 5 times, and the majority result of the 5 calculations is taken.

6. The intelligent early warning method for dam safety monitoring as described in claim 5, characterized in that: The methods for judging the four types of results include: The data is recalibrated to ensure its quality and accuracy. The machine analysis model and the expert evaluation model are recalculated. If the output results change, the output results of the dam are reassessed according to the above steps. When the output remains unchanged, the following method is generated by combining two adjacent sets of machine analysis models: AND new And n / 2+Y n-1 *e+Y n+1 *(0.5-e) In the formula, Y new Represented as the predicted value, Y n Y represents the result of the nth machine analysis model. n+1 and Y n-1 'e' represents the results of two adjacent machine analysis models, and 'e' represents the weight value.

7. The intelligent early warning method for dam safety monitoring as described in claim 6, characterized in that: The assessment of anomalies includes: Mild abnormality with a predicted value of 0%–30%, moderate abnormality with a predicted value of 31%–70%, and severe abnormality with a predicted value of 71%–100%; The strategy for dealing with mild anomalies is to monitor the dam in real time, shorten the computation interval of the deep learning model, and record the computation data. The strategy for dealing with moderate anomalies is to establish a corresponding plan based on the strategy for dealing with mild anomalies, including the division of responsibilities, response plans, and emergency contacts. The response strategy for severe anomalies is to trigger emergency plans, including a comprehensive assessment and repair of the dam, evacuation of personnel, and closure of nearby areas.

8. An intelligent early warning system for dam safety monitoring, based on the intelligent early warning method for dam safety monitoring as described in any one of claims 1 to 7, characterized in that: include, The detection module is used to connect to the sensing node, process and judge the data received by the sensing node, eliminate abnormal values, and finally transmit the data. The judgment module builds different models based on the data to perform calculations on the data. It realizes the use of different calculation methods for different dam conditions, which plays a role in detecting whether the dam is abnormal and ensuring the safety of the dam. The output module can output the results from the judgment module to different types of staff based on the APP, so that staff of different types can perform their work in a timely manner and ensure the rational and orderly operation of the staff.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the intelligent early warning method for dam safety monitoring 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: When the computer program is executed by the processor, it implements the steps of the intelligent early warning method for dam safety monitoring as described in any one of claims 1 to 7.

Images