A dam body detection control method and system for a smart hydropower station

Abstract

The present invention discloses a dam body detection control method and system for a smart hydropower station, which relates to the technical field of dam safety management, including: obtaining at least one possible damage type of the dam body, and setting a corresponding detection method based on each damage type; determining all possible dam body operation and maintenance events; constructing a damage type risk assessment model; determining the detection time closest to the current time for each damage type, recorded as the initial detection time; statistically analyzing the operation and maintenance events; substituting the analyzed operation and maintenance events into the damage type risk assessment index to obtain the transition assessment index of each damage type; based on the transition assessment index of the damage type, setting the detection accuracy of the detection method corresponding to the damage type. The advantages of the present invention are: realizing the comprehensive analysis of the dam body detection data, being able to reasonably plan the detection accuracy of each detection, and planning the personalized detection of the dam body, which greatly reduces the waste of detection resources and improves the detection efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of dam safety management, and in particular to a dam body detection and control method and system for a smart hydropower station. Background Art

[0002] A dam is a man-made civil engineering structure whose main function is to span a river or other water body to block water flow, store water, raise water levels or regulate water flow. Dams are usually built to meet a variety of socio-economic goals, such as flood control, irrigation, water supply, power generation, and shipping.

[0003] During the operation and maintenance of a dam, there will be many different types of damage. Therefore, it is necessary to carry out reasonable inspection planning for the dam to promptly discover various types of damage that may occur to the dam body and to promptly repair the dam body. The existing technology for dam body inspection lacks comprehensive analysis of dam body inspection data, making it difficult to reasonably plan the inspection accuracy of each inspection, which easily leads to a waste of inspection resources. Summary of the invention

[0004] In order to solve the above-mentioned technical problems, a dam body detection control method and system for a smart hydropower station are provided. This technical solution solves the problem that the above-mentioned existing technology for dam body detection lacks comprehensive analysis of dam body detection data, makes it difficult to reasonably plan the detection accuracy of each detection, and easily causes waste of detection resources.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] A dam body detection and control method for a smart hydropower station, comprising:

[0007] Obtain at least one possible damage type of the dam body, and set a corresponding detection method based on each damage type;

[0008] Based on the historical operation and maintenance management data of the dam, determine all possible dam operation and maintenance events;

[0009] Analyze the correlation between each dam operation and maintenance event and the damage type, and build a damage type risk assessment model;

[0010] Based on the historical operation and maintenance management data of the dam, determine the detection time closest to the current time for each damage type and record it as the initial detection time;

[0011] All dam operation and maintenance events between the initial detection time and the current time are counted and recorded as analysis operation and maintenance events;

[0012] Substitute the analyzed operation and maintenance events into the damage type risk assessment index to obtain the transition assessment index of each damage type;

[0013] Based on the damage type transition evaluation index, the detection accuracy of the detection method corresponding to the damage type is set.

[0014] Preferably, the analysis of the correlation between each dam operation and maintenance event and the damage type and the construction of the damage type risk assessment model specifically includes:

[0015] Based on each test data in the historical test data, analyze the risk probability of the damage type at each test;

[0016] Calculate the difference between the risk probability of the damage type at the time of detection and the risk probability of the damage type at the previous detection;

[0017] Collect statistics on all dam operation and maintenance events that occurred between the time of the inspection and the time of the previous inspection;

[0018] The difference between the risk probability of the damage type at the time of detection and the risk probability of the damage type at the previous detection and all the dam operation and maintenance events that occurred between the time of detection and the time of the previous detection form a sample data;

[0019] Get all sample data to form a sample data set;

[0020] Based on the sample data set, all dam operation and maintenance events that occurred between the time of detection and the time of the previous detection were taken as input, and the difference between the risk probability of the damage type at the time of detection and the risk probability of the damage type at the time of the previous detection was taken as output. A neural network was used to train a damage type risk assessment model.

[0021] Preferably, the use of a neural network to train the damage type risk assessment model specifically includes:

[0022] Divide all the data in the sample data set into a training set and a validation set in a ratio of 8:2;

[0023] Constructing a loss function, wherein the loss function is a mean square error function;

[0024] Set the regularization coefficient, and introduce the regularization term into the loss function based on the regularization coefficient to obtain the regularized loss function;

[0025] Based on the regularized loss function, several candidate models are trained through the neural network using the training set;

[0026] Use the loss function to evaluate the loss values ​​of several candidate models on the validation set;

[0027] Screen out the candidate model corresponding to the minimum loss value as the training damage type risk assessment model;

[0028] The regularization loss function is specifically:

[0029]

[0030] in, is the regularized loss function, is the loss function, is the regularization coefficient, is the jth parameter of the neural network.

[0031] Preferably, the damage type-based transition evaluation index and the detection accuracy of the detection method corresponding to the damage type are set specifically including:

[0032] Based on the detection data corresponding to the initial detection time, the occurrence risk probability of the damage type at the initial detection is analyzed as the basic risk indicator of the damage type;

[0033] The basic risk index of the damage type plus the change assessment index of the damage type are used as the actual risk assessment value corresponding to the damage type;

[0034] Determine several precision adjustment gears corresponding to the detection method corresponding to the damage type;

[0035] Determine the accuracy adjustment gear based on the actual risk assessment value corresponding to the damage type;

[0036] The dam body is inspected by adjusting the gear according to the set accuracy.

[0037] Preferably, determining the accuracy adjustment gear based on the actual risk assessment value corresponding to the damage type specifically includes:

[0038] Set the actual risk assessment value corresponding to the highest precision adjustment gear, which is recorded as the upper risk assessment threshold;

[0039] Within 0-risk assessment upper threshold, set a number of gradient thresholds corresponding to the number of precision adjustment gears;

[0040] Establish corresponding relationships between all gradient thresholds and precision adjustment gears in order from small to large;

[0041] The actual risk assessment value corresponding to the damage type is compared with the gradient threshold, and the first gradient threshold that is greater than the actual risk assessment value from small to large is determined, and the precision adjustment gear corresponding to the gradient threshold is used as the determined precision adjustment gear.

[0042] Furthermore, a dam body detection control system of a smart hydropower station is proposed, which is used to implement the dam body detection control method of the smart hydropower station as described above, including:

[0043] A model training model, wherein the model training model is used to obtain at least one possible damage type of the dam body, and set a corresponding detection method based on each damage type, determine all possible dam body operation and maintenance events based on the historical operation and maintenance management data of the dam body, analyze the correlation between each dam body operation and maintenance event and the damage type, and construct a damage type risk assessment model;

[0044] An event analysis module, which is used to determine the detection time closest to the current time for each damage type based on the historical operation and maintenance management data of the dam body, record it as the initial detection time, and count all dam body operation and maintenance events between the initial detection time and the current time, record them as analysis operation and maintenance events;

[0045] A detection module is electrically connected to the model training model and the event analysis module. The detection module is used to substitute the analyzed operation and maintenance events into the damage type risk assessment index to obtain the transition assessment index of each damage type, and based on the transition assessment index of the damage type, set the detection accuracy of the detection method corresponding to the damage type.

[0046] Optionally, the model training model includes:

[0047] A data processing unit, the data processing unit is used to analyze the risk probability of the damage type at each detection based on each detection data in the historical detection data, calculate the difference between the risk probability of the damage type at the detection and the risk probability of the damage type at the previous detection, and count all dam operation and maintenance events that occurred between the detection and the previous detection;

[0048] A sample statistics unit, wherein the sample statistics unit is used to form a sample data set by combining the difference between the risk probability of the damage type at the time of detection and the risk probability of the damage type at the previous detection and all dam operation and maintenance events occurring between the time of detection and the time of the previous detection, and obtaining all the sample data to form a sample data set;

[0049] A neural network training unit is used to train a damage type risk assessment model using a neural network based on a sample data set, with all dam operation and maintenance events occurring between the time of detection and the time of the previous detection as input, and with the difference between the risk probability of the damage type occurring at the time of detection and the risk probability of the damage type occurring at the time of the previous detection as output.

[0050] Optionally, the detection module includes:

[0051] A reference state analysis unit, the reference state analysis unit is used to analyze the occurrence risk probability of the damage type at the time of the initial detection based on the detection data corresponding to the initial detection time as a basic risk indicator of the damage type;

[0052] A transition analysis unit, which is used to substitute the analysis operation and maintenance events into the damage type risk assessment index to obtain a transition assessment index for each damage type;

[0053] A comprehensive assessment unit, the comprehensive assessment unit is used to add a basic risk index of the damage type to a change assessment index of the damage type as an actual risk assessment value corresponding to the damage type;

[0054] The precision setting unit is used to determine a number of precision adjustment gears corresponding to the detection method corresponding to the damage type, determine the precision adjustment gear based on the actual risk assessment value corresponding to the damage type, and detect the dam body according to the set precision adjustment gear.

[0055] Compared with the prior art, the present invention has the following beneficial effects:

[0056] The present invention proposes a dam body detection control scheme for a smart hydropower station. Based on each detection data and the operation and maintenance events in adjacent detection intervals, a comprehensive analysis is performed on the risk indicators of dam body damage. The detection accuracy is set in a targeted manner based on the risk indicators. The detection accuracy is improved under high risk to ensure a comprehensive detection of the dam body. The detection accuracy can be appropriately reduced under low risk, thereby improving the detection efficiency and reducing the waste of detection resources. Through this scheme, a comprehensive analysis of the dam body detection data is achieved, the detection accuracy of each detection can be reasonably planned, and personalized detection planning for the dam body can greatly reduce the waste of detection resources and improve the detection efficiency while ensuring the detection accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 Flow chart of the dam body detection and control method of the smart hydropower station proposed in this scheme;

[0058] Figure 2 This is a flow chart of the method for constructing a damage type risk assessment model in this scheme;

[0059] Figure 3 This is a flow chart of the method for using a neural network to train a damage type risk assessment model in this scheme;

[0060] Figure 4 A flow chart of the method for setting the detection accuracy of the detection method corresponding to the damage type in this solution;

[0061] Figure 5 This is a flow chart of a method for determining the accuracy adjustment gear position based on the actual risk assessment value corresponding to the damage type in this solution;

[0062] Figure 6 It is a schematic diagram of the structure of the electronic device of the present invention;

[0063] Figure 7 It is a schematic diagram of the computer-readable storage medium structure of the present invention. DETAILED DESCRIPTION

[0064] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0065] Reference Figure 1 As shown, a dam body detection and control method for a smart hydropower station includes:

[0066] Obtain at least one possible damage type of the dam body, and set a corresponding detection method based on each damage type;

[0067] Based on the historical operation and maintenance management data of the dam, determine all possible dam operation and maintenance events;

[0068] Analyze the correlation between each dam operation and maintenance event and the damage type, and build a damage type risk assessment model;

[0069] Based on the historical operation and maintenance management data of the dam, determine the detection time closest to the current time for each damage type and record it as the initial detection time;

[0070] All dam operation and maintenance events between the initial detection time and the current time are counted and recorded as analysis operation and maintenance events;

[0071] Substitute the analyzed operation and maintenance events into the damage type risk assessment index to obtain the transition assessment index of each damage type;

[0072] Based on the damage type transition evaluation index, the detection accuracy of the detection method corresponding to the damage type is set.

[0073] Based on each detection data and the operation and maintenance events in the adjacent detection intervals, a comprehensive analysis is conducted on the risk indicators of dam damage. The detection accuracy is set based on the risk indicators. The detection accuracy is improved under high risk to ensure a comprehensive detection of the dam body. The detection accuracy is appropriately reduced under low risk, thereby improving detection efficiency and reducing the waste of detection resources.

[0074] Reference Figure 2 As shown in the figure, the correlation between each dam operation and maintenance event and the damage type is analyzed, and the damage type risk assessment model is constructed, which specifically includes:

[0075] Based on each test data in the historical test data, analyze the risk probability of the damage type at each test;

[0076] Calculate the difference between the risk probability of the damage type at the time of detection and the risk probability of the damage type at the previous detection;

[0077] Collect statistics on all dam operation and maintenance events that occurred between the time of the inspection and the time of the previous inspection;

[0078] The difference between the risk probability of the damage type at the time of detection and the risk probability of the damage type at the previous detection and all the dam operation and maintenance events that occurred between the time of detection and the time of the previous detection form a sample data;

[0079] Get all sample data to form a sample data set;

[0080] Based on the sample data set, all dam operation and maintenance events that occurred between the time of detection and the time of the previous detection were taken as input, and the difference between the risk probability of the damage type at the time of detection and the risk probability of the damage type at the time of the previous detection was taken as output. A neural network was used to train a damage type risk assessment model.

[0081] Neural Networks is a computational model that mimics the structure and function of biological neural networks. They are composed of a large number of processing units connected to each other through weighted connections, and can process and learn complex nonlinear relationships and data patterns. In this scheme, based on the neural network model, a large number of operation and maintenance events and the change rate of risk indicators are used as training data to explore the data relationship between the change rate of operation and maintenance events and risk indicators, and then build a damage type risk assessment model.

[0082] Reference Figure 3 As shown in FIG. 1 , the damage type risk assessment model trained by a neural network specifically includes:

[0083] Divide all the data in the sample data set into a training set and a validation set in a ratio of 8:2;

[0084] Construct a loss function, which is a mean square error function;

[0085] Set the regularization coefficient, and introduce the regularization term into the loss function based on the regularization coefficient to obtain the regularized loss function;

[0086] Based on the regularized loss function, several candidate models are trained through the neural network using the training set;

[0087] Use the loss function to evaluate the loss values ​​of several candidate models on the validation set;

[0088] Screen out the candidate model corresponding to the minimum loss value as the training damage type risk assessment model;

[0089] The regularization loss function is specifically:

[0090]

[0091] in, is the regularized loss function, is the loss function, is the regularization coefficient, is the jth parameter of the neural network.

[0092] In the regularized loss value function, the regularization coefficient is added to the loss function as a regularization term. This regularization term is a constraint or penalty on the model parameters, which aims to reduce the complexity of the model. Therefore, the size of the regularization coefficient will directly affect the value of the loss function. When the regularization coefficient is small, the model complexity is relatively high, and overfitting may be more likely to occur. At this time, the loss value may be very low on the training set, but may be high on the validation set or test set. In this scheme, multiple regularization coefficients are pre-set to obtain multiple regularized loss functions. The loss performance of the candidate model trained by each regularized loss function on the validation set is used to screen the best training damage type risk assessment model.

[0093] Reference Figure 4 As shown in FIG. 1 , based on the damage type transition evaluation index, the detection accuracy of the detection method corresponding to the damage type is set to include:

[0094] Based on the detection data corresponding to the initial detection time, the occurrence risk probability of the damage type at the initial detection is analyzed as the basic risk indicator of the damage type;

[0095] The basic risk index of the damage type plus the change assessment index of the damage type are used as the actual risk assessment value corresponding to the damage type;

[0096] Determine several precision adjustment gears corresponding to the detection method corresponding to the damage type;

[0097] Determine the accuracy adjustment gear based on the actual risk assessment value corresponding to the damage type;

[0098] The dam body is inspected by adjusting the gear according to the set accuracy.

[0099] Reference Figure 5 As shown, based on the actual risk assessment value corresponding to the damage type, determining the precision adjustment gear specifically includes:

[0100] Set the actual risk assessment value corresponding to the highest precision adjustment gear, which is recorded as the upper risk assessment threshold;

[0101] Within 0-risk assessment upper threshold, set a number of gradient thresholds corresponding to the number of precision adjustment gears;

[0102] Establish corresponding relationships between all gradient thresholds and precision adjustment gears in order from small to large;

[0103] The actual risk assessment value corresponding to the damage type is compared with the gradient threshold, and the first gradient threshold that is greater than the actual risk assessment value from small to large is determined, and the precision adjustment gear corresponding to the gradient threshold is used as the determined precision adjustment gear.

[0104] It can be understood that the detection system has its upper limit of accuracy and several determined accuracy levels, which are determined by the equipment. In this scheme, a correspondence is established between the upper limit of accuracy and the accuracy level and the risk probability of damage to the dam body. The greater the risk probability of damage to the dam body, the higher the corresponding accuracy level.

[0105] Furthermore, based on the same inventive concept as the dam body detection and control method of the above-mentioned smart hydropower station, a dam body detection and control system of a smart hydropower station is also proposed, comprising:

[0106] Model training model: The model training model is used to obtain at least one possible damage type of the dam body, and set a corresponding detection method based on each damage type. Based on the historical operation and maintenance management data of the dam body, all possible dam body operation and maintenance events are determined, and the correlation between each dam body operation and maintenance event and the damage type is analyzed, and a damage type risk assessment model is constructed;

[0107] Event analysis module: The event analysis module is used to determine the detection time closest to the current time for each damage type based on the historical operation and maintenance management data of the dam body, record it as the initial detection time, and count all dam body operation and maintenance events between the initial detection time and the current time, record them as analysis operation and maintenance events;

[0108] The detection module is electrically connected to the model training model and the event analysis module. The detection module is used to substitute the analyzed operation and maintenance events into the damage type risk assessment index to obtain the transition assessment index of each damage type. Based on the transition assessment index of the damage type, the detection accuracy of the detection method corresponding to the damage type is set.

[0109] Model training The model includes:

[0110] The data processing unit is used to analyze the risk probability of the damage type at each detection based on each detection data in the historical detection data, calculate the difference between the risk probability of the damage type at the detection and the risk probability of the damage type at the previous detection, and count all dam operation and maintenance events that occurred between the detection and the previous detection;

[0111] The sample statistical unit is used to combine the difference between the risk probability of the damage type at the time of detection and the risk probability of the damage type at the previous detection and all the dam operation and maintenance events that occurred between the time of detection and the time of the previous detection into a sample data, obtain all the sample data, and form a sample data set;

[0112] The neural network training unit is used to train the damage type risk assessment model using a neural network based on a sample data set, with all dam operation and maintenance events occurring between the time of detection and the time of the previous detection as input, and with the difference between the risk probability of the damage type occurring at the time of detection and the risk probability of the damage type occurring at the time of the previous detection as output.

[0113] The detection module includes:

[0114] A reference state analysis unit, which is used to analyze the occurrence risk probability of the damage type at the time of the initial detection based on the detection data corresponding to the initial detection time, as a basic risk indicator of the damage type;

[0115] The transition analysis unit is used to substitute the analysis operation and maintenance events into the damage type risk assessment index to obtain the transition assessment index of each damage type;

[0116] A comprehensive assessment unit, which is used to add the basic risk index of the damage type to the change assessment index of the damage type as the actual risk assessment value corresponding to the damage type;

[0117] The precision setting unit is used to determine a number of precision adjustment gears corresponding to the detection method corresponding to the damage type, determine the precision adjustment gear based on the actual risk assessment value corresponding to the damage type, and detect the dam body according to the set precision adjustment gear.

[0118] Furthermore, the method according to the embodiment of the present application can also be performed by Figure 6 The electronic device architecture shown in FIG. Figure 6 As shown, the electronic device 500 may include a bus 501, one or more CPUs 502, a read-only memory (ROM) 503, a random access memory (RAM) 504, a communication port 505 connected to a network, an input / output component 506, a hard disk 507, etc. The storage device in the electronic device 500, such as the ROM 503 or the hard disk 507, may store a dam body detection control method for a smart hydropower station provided in the present application. The electronic device 500 may also include a user interface 508. Of course, Figure 6 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Figure 6 One or more components of an electronic device are shown.

[0119] Figure 7 Schematic diagram of a computer-readable storage medium structure provided by an embodiment of the present application. Figure 7 As shown, a computer-readable storage medium 600 according to an embodiment of the present application is shown. Computer-readable instructions are stored on the computer-readable storage medium 600. When the computer-readable instructions are executed by the processor, a dam detection control method for a smart hydropower station according to an embodiment of the present application described with reference to the above figures can be executed. The storage medium 600 includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0120] To sum up, the advantages of the present invention are: it realizes the comprehensive analysis of dam body detection data, can reasonably plan the detection accuracy of each detection, and makes personalized detection planning for the dam body. On the basis of ensuring the detection accuracy, it greatly reduces the waste of detection resources and improves the detection efficiency.

[0121] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. A dam body detection and control method for a smart hydropower station, characterized in that: include: Obtain at least one possible damage type of the dam body, and set a corresponding detection method based on each damage type; Based on the historical operation and maintenance management data of the dam, determine all possible dam operation and maintenance events; Analyze the correlation between each dam operation and maintenance event and the damage type, and build a damage type risk assessment model; Based on the historical operation and maintenance management data of the dam, determine the detection time closest to the current time for each damage type and record it as the initial detection time; All dam operation and maintenance events between the initial detection time and the current time are counted and recorded as analysis operation and maintenance events; Substitute the analyzed operation and maintenance events into the damage type risk assessment index to obtain the transition assessment index of each damage type; Based on the damage type transition evaluation index, the detection accuracy of the detection method corresponding to the damage type is set; The analysis of the correlation between each dam operation and maintenance event and the damage type and the construction of the damage type risk assessment model specifically includes: Based on each test data in the historical test data, analyze the risk probability of the damage type at each test; Calculate the difference between the risk probability of the damage type at the time of detection and the risk probability of the damage type at the previous detection; Collect statistics on all dam operation and maintenance events that occurred between the time of the inspection and the time of the previous inspection; The difference between the risk probability of the damage type at the time of detection and the risk probability of the damage type at the previous detection and all the dam operation and maintenance events that occurred between the time of detection and the time of the previous detection form a sample data; Get all sample data to form a sample data set; Based on the sample data set, all dam operation and maintenance events that occurred between the detection time and the previous detection time were used as input, and the difference between the risk probability of the damage type at the time of detection and the risk probability of the damage type at the previous detection time was used as output. The damage type risk assessment model was trained using a neural network. The damage type-based transition evaluation index and the detection accuracy of the detection method corresponding to the damage type are specifically set as follows: Based on the detection data corresponding to the initial detection time, the occurrence risk probability of the damage type at the initial detection is analyzed as the basic risk indicator of the damage type; The basic risk index of the damage type plus the change assessment index of the damage type are used as the actual risk assessment value corresponding to the damage type; Determine several precision adjustment gears corresponding to the detection method corresponding to the damage type; Determine the accuracy adjustment gear based on the actual risk assessment value corresponding to the damage type; The dam body is inspected by adjusting the gear according to the set accuracy.

2. The dam body detection and control method of a smart hydropower station according to claim 1 is characterized in that: The use of a neural network to train the damage type risk assessment model specifically includes: Divide all the data in the sample data set into a training set and a validation set in a ratio of 8:2; Constructing a loss function, wherein the loss function is a mean square error function; Set the regularization coefficient, and introduce the regularization term into the loss function based on the regularization coefficient to obtain the regularized loss function; Based on the regularized loss function, several candidate models are trained through the neural network using the training set; Use the loss function to evaluate the loss values ​​of several candidate models on the validation set; Screen out the candidate model corresponding to the minimum loss value as the training damage type risk assessment model; The regularization loss function is specifically: L'(θ)=L(θ)+L1 ∑ |θ j | Among them, L'(θ) is the regularization loss function, L(θ) is the loss function, L1 is the regularization coefficient, θ j is the jth parameter of the neural network.

3. The dam body detection and control method of a smart hydropower station according to claim 2 is characterized in that: The determining of the accuracy adjustment gear position based on the actual risk assessment value corresponding to the damage type specifically includes: Set the actual risk assessment value corresponding to the highest precision adjustment gear, which is recorded as the upper risk assessment threshold; Within 0-risk assessment upper threshold, set a number of gradient thresholds corresponding to the number of precision adjustment gears; Establish corresponding relationships between all gradient thresholds and precision adjustment gears in order from small to large; The actual risk assessment value corresponding to the damage type is compared with the gradient threshold, and the first gradient threshold that is greater than the actual risk assessment value from small to large is determined, and the precision adjustment gear corresponding to the gradient threshold is used as the determined precision adjustment gear.

4. A dam detection and control system for a smart hydropower station, characterized in that: A dam body detection and control method for implementing a smart hydropower station as claimed in any one of claims 1 to 3, comprising: A model training model, wherein the model training model is used to construct a damage type risk assessment model; An event analysis module, which is used to statistically analyze operation and maintenance events based on historical operation and maintenance management data of the dam body; A detection module, wherein the detection module is electrically connected to the model training model and the event analysis module, and is used to determine a transition evaluation index for each damage type, and based on the transition evaluation index for the damage type, set the detection accuracy of the detection method corresponding to the damage type.

5. The dam body detection and control system of a smart hydropower station according to claim 4 is characterized in that: The model training model includes: A data processing unit, the data processing unit is used to analyze and process the historical detection data, extract the risk probability of the damage type at each detection, calculate the difference between the risk probability of the damage type at the detection and the risk probability of the damage type at the previous detection, and count all dam operation and maintenance events that occurred between the detection and the previous detection; A sample statistics unit, which is used to form a sample data set by combining the difference between the risk probability of the damage type at the time of detection and the risk probability of the damage type at the previous detection and all dam operation and maintenance events occurring between the time of detection and the time of the previous detection based on the processing result of the data processing unit, and obtaining all the sample data to form a sample data set; A neural network training unit is used to train a damage type risk assessment model using a neural network based on a sample data set.

6. The dam body detection and control system of a smart hydropower station according to claim 5 is characterized in that: The detection module comprises: A reference state analysis unit, the reference state analysis unit is used to analyze the basic risk index of the damage type based on the detection data corresponding to the initial detection time; A transition analysis unit, the transition analysis unit is used to analyze the transition evaluation index of each damage type; A comprehensive assessment unit, wherein the comprehensive assessment unit calculates an actual risk assessment value corresponding to the damage type; The precision setting unit is used to determine the precision adjustment gear based on the actual risk assessment value corresponding to the damage type, and detect the dam body according to the set precision adjustment gear.

7. An electronic device, characterized in that: include: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the dam body detection and control method of the smart hydropower station as described in any one of claims 1-3.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the dam body detection and control method of the smart hydropower station described in any one of claims 1-3 is implemented.

Images