Reservoir project standardization management method and system

Abstract

The invention provides a standardized management method and system for reservoir engineering, and belongs to the technical field of water conservancy project management, and the method comprises the steps: carrying out the processing of multi-dimensional data obtained by a sensor based on a first random forest model, and obtaining the target state data of a target reservoir dam body, the multi-dimensional data comprises structural data and monitoring data of the target reservoir dam body; performing feature extraction on the target state data to obtain target state feature data, obtaining a target similarity based on multiple similarities between the target state feature data and each piece of state feature data in a state library, and selecting a target state of the target reservoir dam body from the state library based on the target similarity; and determining a corresponding target management strategy based on the target state. According to the invention, the method and system can accurately recognize the state of the reservoir dam body, reflect the change trend of the structure of the reservoir dam body in real time, adjust the management strategy according to the state of the reservoir dam body, and achieve the risk prevention and control of the reservoir dam body.

Description

Technical Field

[0001] The present invention belongs to the technical field of water conservancy project management, and more specifically, relates to a reservoir project standardized management method and system. Background Art

[0002] As the core structure of a reservoir project, the state of a reservoir dam directly affects the performance of flood control, water supply and other functions. At present, empirical judgments based on historical data or simple threshold alarms cannot reflect the trend of dam structure changes in real time, which can easily lead to delayed discovery of safety hazards; the management strategy for reservoir dams relies on manual experience adjustment, which has a slow response speed and is difficult to cope with complex working conditions and dynamic environmental requirements; in the event of sudden abnormalities, there is a lack of automated decision support and it relies on manual intervention, which has a slow response speed and is prone to misjudgment. Summary of the invention

[0003] The purpose of the present invention is to provide a standardized management method and system for reservoir projects, so as to improve the timeliness of discovering potential safety hazards and the response speed of reservoir dam management under sudden abnormalities.

[0004] A first aspect of an embodiment of the present invention provides a reservoir engineering standardized management method, comprising: Processing the multidimensional data acquired by the sensor based on the first random forest model to determine target state data of the target reservoir dam body, wherein the multidimensional data includes structural data and monitoring data of the target reservoir dam body; Extracting features from the target state data to obtain target state feature data, obtaining target similarity based on multiple similarities between the target state feature data and each state feature data in a state library, and selecting the target state of the target reservoir dam body from the state library based on the target similarity; Based on the target status, a corresponding target management strategy is determined.

[0005] A second aspect of the embodiment of the present invention provides a reservoir engineering standardized management system, including: A data processing module, used to process the multidimensional data acquired by the sensor based on the first random forest model to determine the target state data of the target reservoir dam body, wherein the multidimensional data includes the structural data and monitoring data of the target reservoir dam body; A state determination module is used to extract features from the target state data to obtain target state feature data, obtain target similarity based on multiple similarities between the target state feature data and each state feature data in the state library, and select the target state of the target reservoir dam body from the state library based on the target similarity; The management strategy module is used to determine the corresponding target management strategy based on the target state.

[0006] The beneficial effects of a standardized management method and system for reservoir projects provided by an embodiment of the present invention are as follows: the present invention can accurately identify the state of a reservoir dam body, reflect the structural change trend of the reservoir dam body in real time, and improve the timeliness of discovering potential safety hazards; the management strategy is adjusted according to the state of the reservoir dam body, thereby improving the response speed of reservoir dam body management; and the present invention provides automated decision support under complex working conditions and dynamic environments to achieve risk prevention and control of the reservoir dam body. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0008] Figure 1 A schematic diagram of a process flow of a reservoir engineering standardization management method provided by an embodiment of the present invention; Figure 2 A structural diagram of a reservoir engineering standardization management system provided by an embodiment of the present invention; Figure 3 A schematic block diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0009] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0010] In order to make the purpose, technical solutions and advantages of the present invention more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0011] Please refer to Figure 1 , Figure 1 A schematic diagram of a process flow of a reservoir engineering standardization management method provided by an embodiment of the present invention, the method comprising: S101: Processing the multidimensional data acquired by the sensor based on the first random forest model to determine the target state data of the target reservoir dam body, where the multidimensional data includes the structural data and monitoring data of the target reservoir dam body.

[0012] In this embodiment, the multidimensional data of the target reservoir dam body includes temperature data, displacement data, stress strain data, seepage data, crack data, etc. As the core component of water conservancy projects, reservoir dam bodies are key construction facilities for intercepting water flow, forming reservoirs and regulating water volume, and play a vital role in water resource regulation, flood control, irrigation and other fields.

[0013] The present invention performs data cleaning, format conversion, and normalization on the multidimensional data before the first random forest model processes the multidimensional data; the first random forest model performs multiple random samplings according to the importance of feature data in the processed data to construct multiple decision trees; by integrating the output results of multiple decision trees, noise data and abnormal fluctuation data are filtered out, and the state that can reflect the current actual operating status of the target reservoir dam body is accurately screened out.

[0014] In this embodiment, the multidimensional data acquired by the sensor is processed based on the first random forest model to determine the target state data of the target reservoir dam body, including: The multidimensional data acquired by the sensor is processed based on the first random forest model to obtain the difference of the recognition result; When the difference of the recognition result is greater than the first difference, the multidimensional data is verified based on the second random forest model to obtain a verification difference; When the verification difference is greater than the first difference, the environmental data around the target reservoir dam is collected; Target state data is determined based on the environmental data and the multidimensional data.

[0015] Specifically, the first random forest model is trained with a large amount of historical state data, and can accurately identify and classify current multi-dimensional data and output corresponding identification results.

[0016] After obtaining the recognition results, the difference between multiple recognition results is calculated to determine the difference between the recognition results. When the difference between the recognition results is greater than the preset first difference, it indicates that there is an error between the current recognition results and there may be potential abnormalities. The multidimensional data is verified again based on the second random forest model. The second random forest model uses different training data and parameter settings, which can analyze and judge the multidimensional data from another perspective; after being processed by the second random forest model, the verification difference is obtained. When the verification difference is greater than the first difference, there is a high probability that the state of the reservoir dam body is abnormal. In order to have a more comprehensive understanding of the condition of the dam body, the environmental data around the target reservoir dam body is collected. The environmental data includes: meteorological data (such as temperature, humidity, wind speed, rainfall, etc.), geological data (such as soil moisture, stratum displacement, etc.) and hydrological data (such as water level changes, water flow velocity, etc.). After obtaining the environmental data and the original multidimensional data, the two types of data are fused. The multidimensional data is corrected and supplemented in combination with the environmental data to determine more accurate and reliable target state data. For example, when environmental data shows a sudden increase in rainfall, it may affect the state of the reservoir dam. According to the relationship between rainfall and the state of the reservoir dam, the multidimensional data is adjusted accordingly to obtain target state data that can better reflect the true state of the dam.

[0017] S102: extracting features from the target state data to obtain target state feature data, obtaining target similarity based on multiple similarities between the target state feature data and each state feature data in the state library, and selecting a target state of the target reservoir dam body from the state library based on the target similarity.

[0018] In this embodiment, feature extraction is performed on the target state data to obtain target state feature data including: According to the target state data, feature extraction algorithms are used to extract the features of the target state data to obtain target state feature data. For example, through dimensionality reduction algorithms such as principal component analysis (PCA) and linear discriminant analysis (LDA), high-dimensional and complex target state data are converted into low-dimensional and more representative target state feature data while retaining key information. The target state feature data includes key operating indicators such as the displacement change trend of the dam body, the fluctuation characteristics of the seepage flow, and the concentrated area of ​​stress and strain.

[0019] In this embodiment, the target similarity is obtained based on multiple similarities between the target state feature data and each state feature data in the state library, and the target state of the target reservoir dam body is selected from the state library based on the target similarity, including: Compare the target state characteristic data with each state characteristic data in the pre-built state library. The state library stores a large number of various dam state characteristics summarized based on historical data and professional experience, such as normal operating state, slightly abnormal state, and seriously abnormal state. Using similarity calculation methods such as cosine similarity and Euclidean distance, calculate the similarity between the target state characteristic data and each state characteristic data in the state library one by one to obtain multiple similarity values. After comprehensive evaluation and analysis of these similarity results, select the most representative value with the highest degree of matching with the target state characteristic data as the target similarity. According to the calculated target similarity, perform precise matching in the state library to screen out the target state that is closest to the current target reservoir dam operation state.

[0020] S103: Determine a corresponding target management strategy based on the target state.

[0021] In this embodiment, based on the target state, a target management policy corresponding to the target state is selected from a preset policy rule library.

[0022] As described above, the present invention can accurately identify the state of the reservoir dam body, reflect the structural change trend of the reservoir dam body in real time, and improve the timeliness of the discovery of safety hazards; adjust the management strategy according to the state of the reservoir dam body, improve the response speed of the reservoir dam body management, and the present invention provides automated decision support under complex working conditions and dynamic environments to achieve risk prevention and control of the reservoir dam body.

[0023] In one embodiment of the present invention, the health index of the target reservoir dam is determined based on the target state; based on the health index, the safety level of the target reservoir dam is determined; based on the safety level, the corresponding target management strategy in the strategy rule library is selected; and a variety of management strategies are stored in the strategy rule library.

[0024] In this embodiment, the health index of the reservoir dam is calculated by the entropy weight method; The calculation formula is:

[0025]

[0026] in, For the j The entropy value of an indicator, For the j The entropy weight of an indicator, m is the number of indicators corresponding to the target state, For the j Standardized data of indicators, For the health index.

[0027] In this embodiment, referring to Table 1, the safety level table, the safety level is divided into four levels, wherein the threshold of the health index is set by combining the statistical quantile with the engineering specification; Table 1 Safety level table

[0028] Specifically, the policy rule base includes detailed management measures for safety levels. For example, for safety level I, the target management strategy is regular inspection (drone aerial photography + sensor calibration). For safety level II, the target management strategy is to increase the number of monitoring times, for example, real-time seepage monitoring + weekly manual inspections. For safety level III, the management strategy is to inform management personnel to repair parts of the dam body. For safety level IV, the management strategy is to activate the emergency plan, notify management personnel to support and reinforce the dam body, and report to the superior department.

[0029] The present invention can obtain a target management strategy according to the safety level, improve the response speed and accuracy of reservoir dam management, and achieve accurate prevention and control of reservoir dam risks.

[0030] In one embodiment of the present invention, based on the security level, a corresponding target management strategy in a policy rule library is selected, and the method also includes: processing environmental data to obtain seasonal characteristics; selecting a corresponding management policy template in the policy rule library based on seasonal characteristics and the security level; and adjusting the management policy template based on seasonal characteristics and a first amplitude value to obtain a corresponding target management strategy.

[0031] In this embodiment, environmental data including temperature, humidity, light intensity, air pressure, geographic location (latitude and longitude) and historical meteorological data are collected in real time through a multi-source sensor network. The raw data is cleaned (such as removing outliers) and normalized, and the seasonal characteristics of the processed environmental data are extracted using a time series decomposition algorithm. Management policy templates corresponding to different seasonal characteristics and security levels are pre-stored in the policy rule library, and each management policy template contains management policy parameters and rules formulated for the corresponding security level and seasonal characteristics.

[0032] The first amplitude value is calculated by the amplitude value calculation formula. The first amplitude value reflects the degree of deviation between the target state and the preset threshold value in the management policy template.

[0033] The amplitude calculation formula is:

[0034] in, is the first amplitude value, x is the characteristic value of the target state, δ base It is the baseline threshold of the corresponding parameter in the management policy template.

[0035] In this embodiment, the management policy template is adjusted based on the first amplitude value to obtain the corresponding target management policy, including: when the seasonal characteristics are the first season characteristics, the seepage monitoring level and the inspection frequency in the management policy template are adjusted based on the first amplitude value to obtain the target management policy; when the seasonal characteristics are the second season characteristics, the seepage monitoring level and the inspection frequency in the management policy template are adjusted based on the first amplitude value to obtain the target management policy; the precipitation of the first season characteristics is greater than the second threshold; the precipitation of the second season characteristics is less than the first threshold, and the second threshold is greater than the first threshold.

[0036] When the seasonal characteristics are determined to be the first season characteristics, the precipitation is large at this time, and the reservoir faces a high seepage risk and safety hazards. Based on the first amplitude value, the seepage monitoring level and patrol frequency in the management strategy template are adjusted accordingly. The larger the first amplitude value, the farther the current seepage situation deviates from the normal threshold, and the seepage monitoring level needs to be increased. For example, if the first amplitude value exceeds a certain proportion, the seepage monitoring level is increased from level one to level two, the accuracy of the monitoring equipment and the frequency of data acquisition are increased, and the changes in the seepage situation can be grasped in a timely and accurate manner. At the same time, the patrol frequency is increased. The inspectors need to conduct more frequent inspections of various key parts of the reservoir dam. The larger the first amplitude value, the greater the increase in the patrol frequency, so as to timely discover possible safety problems such as cracks and leakage in the reservoir dam, and take corresponding measures to deal with them. When the seasonal characteristics are determined to be the second season characteristics, the precipitation is small, and the seepage risk of the reservoir is relatively low, but a certain monitoring and patrol intensity still needs to be maintained. Also based on the first amplitude value, the seepage monitoring level and patrol frequency in the management strategy template are adjusted. If the first amplitude value is small, the monitoring accuracy and frequency of seepage monitoring remain unchanged; the inspection frequency is adjusted accordingly according to the first amplitude value to reduce the inspection frequency.

[0037] The present invention can determine the target management strategy according to the safety level and seasonal changes, and manage the target reservoir dam based on the target management strategy, which greatly improves the scientific nature of management decisions in different seasons, avoids management errors of the dam due to management strategies obtained without collecting environmental factors, and effectively ensures the safe and efficient operation of the reservoir dam; and realizes precise prevention and control of the reservoir dam.

[0038] In one embodiment of the present invention, determining a corresponding target management strategy based on the target state further includes: determining a corresponding risk level identifier based on the feature data; Determine the policy triggering conditions based on the risk level identification; The policy triggering conditions are matched with the management policies in the policy rule base to obtain the target management policy.

[0039] In this embodiment, based on the characteristic data, the corresponding risk level identification is determined, including: Perform weighted calculation on environmental data and characteristic data to obtain a comprehensive risk value; based on the comprehensive risk value, determine the corresponding risk level identification.

[0040] Specifically, in order to obtain a comprehensive risk value that accurately reflects the risk status, it is necessary to perform weighted calculations on the environmental data and the characteristic data corresponding to the target state. The weights are processed using methods such as expert evaluation and hierarchical analysis to assign reasonable weights to each data indicator.

[0041] The formula for calculating the comprehensive risk value is:

[0042] in, It is the risk level indicator. The environmental data indicators, For environmental data The weight of the indicator, The characteristic data k indicators, The feature data k The weight of an indicator.

[0043] The comprehensive risk value range corresponding to different risk level indicators, for example: low risk indicator ( R 1) The comprehensive risk value range is: R ≤ R low ; Medium risk indicator ( R 2) The comprehensive risk value range is: R low < R ≤ R medium ; High risk ( R 3) The comprehensive risk value range is: R > R medium .

[0044] The calculated comprehensive risk value R , determine the interval to which it belongs and determine the corresponding risk level identification. R 1, the triggering conditions of the strategy may be: the seepage volume is less than the threshold Q1, the displacement of the dam body is within the allowable range ΔD1, and the precipitation is less than P1. R 2, the trigger conditions may become: the seepage volume is between Q1 and Q2, the dam displacement exceeds ΔD1 but is less than ΔD2, or the precipitation is between P1 and P2. R3, the triggering conditions are more stringent, the seepage is greater than Q2, the dam displacement exceeds ΔD2, or the precipitation is greater than P2. Among them, ΔD1<ΔD2, Q1<Q2, P1<P2.

[0045] In this embodiment, the policy triggering condition is matched with the management policy in the policy rule base to obtain the target management policy, including: When multiple management policies match the policy triggering condition, the multiple management policies are sorted according to the priority sorting rule preset in the policy rule library to obtain a first sorting list, and the target management policy is determined based on the first sorting list.

[0046] Specifically, when multiple management strategies match the triggering conditions, it is necessary to sort the multiple management strategies according to the priority sorting rules preset in the strategy rule library to obtain a first sorting list, and determine the target management strategy based on the first sorting list. The priority sorting rules comprehensively consider multiple factors, such as the urgency of the risk, the impact on reservoir safety, and the implementation cost. For example, in high-risk situations, the emergency evacuation strategy to ensure the safety of personnel has the highest priority, followed by the flood discharge strategy to control the reservoir water level, and finally the maintenance strategy to reinforce the dam body.

[0047] The present invention can improve the accuracy of risk assessment, and obtain a comprehensive risk value by weighted calculation of environmental data and characteristic data, thereby improving the accuracy and scientificity of management strategies. The policy triggering conditions are determined based on accurate risk level identification, and then matched with the management strategies in the policy rule base, which greatly improves the pertinence of management strategy selection. It can quickly and accurately screen out target management strategies that match the current risk status from the policy rule base, effectively avoiding the problem of over-management or under-management, and ensuring that reservoirs can be properly and timely managed and controlled under various risk conditions.

[0048] In one embodiment of the present invention, determining target state data based on environmental data and multidimensional data includes: Based on the preset weight distribution rules, multidimensional data and environmental data are fused to obtain target state data.

[0049] In this embodiment, based on the preset weight distribution rule, data fusion is performed on the multidimensional data and the environmental data to obtain the target state data including: Determining a first weight adjustment step size based on the importance level of the environmental data; Adjusting the first weight reference value based on the first weight adjustment step length to obtain a first weight; adjusting the second weight reference value based on the first weight adjustment step length to obtain a second weight; Perform weighted calculation based on the first weight, the second weight, the environmental data and the multi-dimensional data to obtain target state data; The first weight is the weight corresponding to the multidimensional data, the second weight is the weight corresponding to the environmental data, and the first weight reference value and the second weight reference value have different adjustment directions.

[0050] Specifically, in this embodiment, the first weight reference value is adjusted based on the first weight adjustment step to obtain the first weight; the second weight reference value is adjusted based on the first weight adjustment step to obtain the second weight. It should be noted here that the adjustment directions of the first weight reference value and the second weight reference value are different. For example, assuming that the first weight reference value is w1, the second weight reference value is w2, and w1+w2=1. When the first weight adjustment step Δw is a positive number, the first weight w r1 =w1+Δw, the second weight w r2 =w2−Δw; when the first weight adjustment step Δw is negative, the first weight w r1 =w1+Δw, the second weight w r2 =w2−Δw. Through such adjustment, it is ensured that the sum of the first weight and the second weight is always 1, and it also reflects the reasonable adjustment of the weights of the two data according to different conditions.

[0051] In this embodiment, based on a preset weight allocation rule, data fusion is performed on multidimensional data and environmental data to obtain target state data, and the method also includes: extracting time series features from environmental data to obtain feature data containing seasonal periodicity; inputting the seasonal feature data into a preset seasonal impact factor calculation model to output a seasonal adjustment coefficient; and correcting the second weight reference value according to the seasonal adjustment coefficient, wherein: when the seasonal adjustment coefficient represents the first seasonal feature (rainy season), the second weight reference value of the environmental data is corrected based on the first correction amplitude to obtain a second weight; when the seasonal adjustment coefficient represents the second seasonal feature (dry season), the second weight reference value of the environmental data is corrected based on the second correction amplitude to obtain a second weight.

[0052] Specifically, the first correction amplitude and the second correction amplitude are determined based on the actual situation of the reservoir project and historical data. For example, by analyzing the impact of historical rainy and dry season environmental data on the operation status of the reservoir, combined with expert experience, it is determined that in the rainy season, the importance of environmental data increases relatively, and the first correction amplitude can be set to a value greater than 1; in the dry season, the importance of environmental data decreases relatively, and the second correction amplitude can be set to a value less than 1. When the seasonal adjustment coefficient is characterized by the first season characteristics (rainy season), the second weight reference value of the environmental data is multiplied by the first correction amplitude to obtain the second weight. Assume that the second weight reference value of the environmental data is w ref Then the second weight w f1 =w ref×1.2. When the seasonal adjustment coefficient is characterized by the second season characteristics (dry season), the second weight reference value of the environmental data is multiplied by the second correction amplitude to obtain the second weight, that is, w f2 =w ref ×0.8. Through such correction, the weight of environmental data in different seasons can be made more consistent with the actual situation, thus improving the accuracy of reservoir project management decisions.

[0053] The present invention increases the weight of environmental data in the rainy season and reduces the weight of environmental data in the dry season, which greatly improves the scientific nature of management decisions in different seasons and avoids the impact of management strategies output due to failure to collect environmental factors on the management of the reservoir dam.

[0054] Corresponding to the standardized management method of reservoir engineering in the above embodiment, Figure 2 This is a structural block diagram of a reservoir engineering standardization management system provided by an embodiment of the present invention. For ease of explanation, only the parts related to the embodiment of the present invention are shown. Figure 2 The reservoir engineering standardized management system 20 includes: a data processing module 21, a state determination module 22 and a management strategy module 23.

[0055] The data processing module 21 is used to process the multidimensional data acquired by the sensor based on the first random forest model to obtain the target state data of the target reservoir dam body, and the multidimensional data includes the structural data and monitoring data of the target reservoir dam body; The state determination module 22 is used to extract features from the target state data to obtain target state feature data, obtain target similarity based on multiple similarities between the target state feature data and each state feature data in the state library, and select the target state of the target reservoir dam body from the state library based on the target similarity; The management strategy module 23 is used to determine the corresponding target management strategy based on the target state.

[0056] In one embodiment of the present invention, the management policy module 23 is specifically used to: Determine the health index of the target reservoir dam body based on the target state; Determine the safety level of the target reservoir dam based on the health index; Based on the security level, select the corresponding target management strategy in the policy rule base; the policy rule base stores a variety of management strategies.

[0057] In one embodiment of the present invention, the management policy module 23 is specifically used to: Process environmental data to obtain seasonal characteristics; Select the corresponding management policy template in the policy rule base based on seasonal characteristics and security levels; The management strategy template is adjusted based on the seasonal characteristics and the first amplitude value to obtain a corresponding target management strategy.

[0058] In one embodiment of the present invention, the management policy module 23 is specifically used to: When the seasonal characteristic is the first seasonal characteristic, the seepage monitoring level and inspection frequency in the management strategy template are adjusted based on the first amplitude value to obtain a target management strategy; When the seasonal characteristics are the second seasonal characteristics, the seepage monitoring level and inspection frequency in the management strategy template are adjusted based on the first amplitude value to obtain a target management strategy; The precipitation characteristic of the first season is greater than the second threshold; the precipitation characteristic of the second season is less than the first threshold, and the second threshold is greater than the first threshold.

[0059] In one embodiment of the present invention, the management policy module 23 is specifically used to: Based on the target status, determine the corresponding risk level identification; Determine the policy triggering conditions based on the risk level identification; The policy triggering conditions are matched with the management policies in the policy rule base to obtain the target management policy.

[0060] In one embodiment of the present invention, the management policy module 23 is specifically used to: Perform weighted calculation on the environmental data and characteristic data corresponding to the target state to obtain a comprehensive risk value; Based on the comprehensive risk value, determine the corresponding risk level identification.

[0061] In one embodiment of the present invention, the management policy module 23 is specifically used to: When multiple management policies match the policy triggering condition, the multiple management policies are sorted according to the priority sorting rule preset in the policy rule library to obtain a first sorting list, and the target management policy is determined based on the first sorting list.

[0062] In one embodiment of the present invention, the data processing module 21 is specifically used for: The multidimensional data acquired by the sensor is processed based on the first random forest model to obtain the difference of the recognition result; When the difference of the recognition result is greater than the first difference, the multidimensional data is verified based on the second random forest model to obtain a verification difference; When the verification difference is greater than the first difference, the environmental data around the target reservoir dam is collected; Target state data is determined based on the environmental data and the multidimensional data.

[0063] In one embodiment of the present invention, the data processing module 21 is specifically used for: Based on the preset weight distribution rules, multidimensional data and environmental data are fused to obtain target state data.

[0064] See also Figure 3 , Figure 3 FIG. 1 is a schematic block diagram of an electronic device provided by an embodiment of the present invention. Figure 3 The electronic device 300 in the embodiment shown may include: one or more processors 301, one or more input devices 302, one or more output devices 303 and one or more memories 304. The processors 301, input devices 302, output devices 303 and memories 304 communicate with each other via a communication bus 305. The memory 304 is used to store computer programs, which include program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. The processor 301 is configured to call the program instructions to execute the functions of the modules in the above-mentioned device embodiments, such as Figure 2 The functions of modules 21 to 23 are shown.

[0065] It should be understood that in the embodiment of the present invention, the processor 301 may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0066] The input device 302 may include a touch panel, a fingerprint collection sensor (for collecting the user's fingerprint information and fingerprint direction information), a microphone, etc., and the output device 303 may include a display (LCD, etc.), a speaker, etc.

[0067] The memory 304 may include a read-only memory and a random access memory, and provide instructions and data to the processor 301. A portion of the memory 304 may also include a non-volatile random access memory. For example, the memory 304 may also store information about the device type.

[0068] In a specific implementation, the processor 301, input device 302, and output device 303 described in the embodiment of the present invention can execute the implementation methods described in the first and second embodiments of the standardized management method for reservoir projects provided in the embodiment of the present invention, and can also execute the implementation methods of the electronic device described in the embodiment of the present invention, which will not be repeated here.

[0069] In another embodiment of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by the processor, all or part of the processes in the above-mentioned embodiment method are implemented, and the computer program can also be completed by instructing the relevant hardware through the computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0070] The computer-readable storage medium may be an internal storage unit of the electronic device of any of the aforementioned embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Furthermore, the computer-readable storage medium may also include both an internal storage unit of the electronic device and an external storage device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

[0071] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0072] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the electronic devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0073] In the several embodiments provided in the present application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces or units, or it can be an electrical, mechanical or other form of connection.

[0074] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present invention.

[0075] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0076] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A reservoir engineering standardized management method, characterized in that: include: Processing the multidimensional data acquired by the sensor based on the first random forest model to obtain target state data of the target reservoir dam body, wherein the multidimensional data includes structural data and monitoring data of the target reservoir dam body; Extracting features from the target state data to obtain target state feature data, obtaining target similarity based on multiple similarities between the target state feature data and each state feature data in a state library, and selecting the target state of the target reservoir dam body from the state library based on the target similarity; Based on the target status, a corresponding target management strategy is determined.

2. The reservoir engineering standardization management method according to claim 1, characterized in that: The determining a corresponding target management strategy based on the target state includes: Determining a health index of the target reservoir dam body based on the target state; Based on the health index, determining the safety level of the target reservoir dam body; Based on the security level, a corresponding target management policy in a policy rule base is selected; the policy rule base stores a variety of management policies.

3. The reservoir engineering standardization management method according to claim 2, characterized in that: The selecting, based on the security level, a corresponding target management policy in a policy rule base includes: Process environmental data to obtain seasonal characteristics; Selecting a corresponding management policy template in the policy rule base based on the seasonal characteristics and the security level; The management strategy template is adjusted based on the seasonal characteristics and the first amplitude value to obtain a corresponding target management strategy.

4. The reservoir engineering standardization management method according to claim 3, characterized in that: The step of adjusting the management strategy template based on the seasonal characteristics and the first amplitude value to obtain a corresponding target management strategy includes: When the seasonal characteristic is the first seasonal characteristic, the seepage monitoring level and the inspection frequency in the management strategy template are adjusted based on the first amplitude value to obtain a target management strategy; When the seasonal characteristic is the second seasonal characteristic, the seepage monitoring level and the inspection frequency in the management strategy template are adjusted based on the first amplitude value to obtain a target management strategy; The precipitation characteristic of the first season is greater than a second threshold; the precipitation characteristic of the second season is less than the first threshold, and the second threshold is greater than the first threshold.

5. The reservoir engineering standardization management method according to claim 2, characterized in that: The determining of the corresponding target management strategy based on the target state also includes: Based on the target state, determining a corresponding risk level identifier; Determining a policy triggering condition based on the risk level identifier; The policy triggering condition is matched with the management policy in the policy rule base to obtain a target management policy.

6. The reservoir engineering standardization management method according to claim 5, characterized in that: The determining a corresponding risk level identifier based on the target state includes: Performing weighted calculation on the environmental data and characteristic data corresponding to the target state to obtain a comprehensive risk value; Based on the comprehensive risk value, a corresponding risk level identifier is determined.

7. The reservoir engineering standardization management method according to claim 6, characterized in that: The matching of the policy triggering condition with the management policy in the policy rule base to obtain the target management policy includes: When multiple management policies match the policy triggering condition, the multiple management policies are sorted according to the priority sorting rule preset in the policy rule base to obtain a first sorting list, and the target management policy is determined based on the first sorting list.

8. The reservoir engineering standardization management method according to claim 1, characterized in that: The multidimensional data acquired by the sensor is processed based on the first random forest model to obtain target state data of the target reservoir dam body, including: Processing the multidimensional data based on a first random forest model to obtain a difference in recognition results; When the difference of the recognition result is greater than the first difference, verifying the multidimensional data based on the second random forest model to obtain a verification difference; When the verification difference is greater than the first difference, the environmental data around the target reservoir dam is collected; Based on the environmental data and the multi-dimensional data, target state data is determined.

9. The reservoir engineering standardization management method according to claim 8, characterized in that: The determining target state data based on the environmental data and the multi-dimensional data includes: Based on a preset weight distribution rule, the multidimensional data and the environmental data are fused to obtain target state data.

10. A standardized management system for reservoir engineering, characterized in that: include: A data processing module, used for processing the multidimensional data acquired by the sensor based on the first random forest model to obtain target state data of the target reservoir dam body, wherein the multidimensional data includes structural data and monitoring data of the target reservoir dam body; A state determination module is used to extract features from the target state data to obtain target state feature data, obtain target similarity based on multiple similarities between the target state feature data and each state feature data in the state library, and select the target state of the target reservoir dam body from the state library based on the target similarity; The management strategy module is used to determine the corresponding target management strategy based on the target state.

Images