Dam monitoring abnormity early warning method and system

Abstract

The invention discloses a dam monitoring abnormity early warning method and system, and relates to the technical field of dam early warning processing. The parameter data of the dam are collected in real time through the deployed sensors, if a certain group of parameter data results are higher than the corresponding preset early warning threshold value, the group of parameter data results are evaluated, and therefore corresponding types of grade early warning including blue early warning, yellow early warning and red early warning are triggered; and according to the triggered grade early warning, the candidate person with the maximum optimal position value is selected from the selectable person range corresponding to the grade early warning, and meanwhile, the area position of the corresponding parameter is sent to the mobile terminal of the solving person, so that the safety of the solving person is improved. The problem that in the prior art, only triggered early warning signals are responded through an alarm when early warning is triggered, and an effective early warning response mechanism is lacked is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of dam early warning processing, and in particular to a dam monitoring abnormality early warning method and system. Background Art

[0002] As an important water conservancy project facility, dams undertake key functions such as flood control, power generation, irrigation and water resource allocation. However, the safe operation of dams faces many potential risks, such as natural disasters, structural aging, design defects, etc. These risks may cause damage to the dam structure or even collapse, bringing catastrophic consequences. Therefore, effective monitoring and abnormal early warning of dams are crucial.

[0003] However, the existing technology for monitoring and early warning of dams still has the following deficiencies: With the development of science and technology, most of them use some modern sensor networks to monitor dam data and set corresponding warning thresholds. Although they can play the role of early warning, most of them only respond to the triggered warning signal through the alarm. There is a lack of effective early warning response mechanism. It is impossible to quickly determine the appropriate and optimal solution personnel based on the evaluation results of the relevant parameters of the triggering warning, resulting in the early warning emergency treatment not being timely and effective; At the same time, it is not possible to analyze the parameter changes before the warning is triggered, so as to determine the set of reasons that lead to the triggering of the warning, thereby helping problem solvers to quickly locate the problem that triggered the warning, and the degree of intelligence is low.

[0004] To this end, a dam monitoring abnormal early warning method and system is introduced. Summary of the invention

[0005] In view of this, the present invention provides a dam monitoring abnormality early warning method and system to solve the problems raised by the above background technology.

[0006] The purpose of the present invention can be achieved through the following technical solutions: A dam monitoring abnormality early warning method, comprising: S1: Deploy sensors at key locations of the dam and use the deployed sensors to collect parameter data of the dam in real time. The parameter data are numbered based on their types. The number is represented by i, where i=1,2...k, and k represents the total number of monitoring data required for the dam; pre-process the collected parameter data; S2: Mark each parameter data result after preprocessing as Gi, preset the warning threshold corresponding to each parameter data result Gi, and compare each parameter data result Gi with the corresponding preset warning threshold; S3: If a set of parameter data results Gi is higher than the corresponding preset warning threshold, the set of parameter data results Gi is evaluated to trigger the corresponding type of level warning, and the corresponding steps are executed to select the candidate with the largest advantage value Yc as the solver, and the historical number of solvers is increased by one; the level warning types include blue warning, yellow warning and red warning; S4: If there are multiple sets of parameter data results Gi that are all higher than the corresponding preset warning threshold, then extract the sets of parameter data that are higher than the corresponding preset warning threshold and record them as abnormal data. Similarly, step S3 evaluates each abnormal data to trigger the corresponding type of level warning; S5: After receiving the triggered warning of the corresponding level, the problem solver can selectively obtain the overall evaluation result of the parameter data of the triggered level warning. The problem solver can quickly locate the triggering cause of the warning based on the overall evaluation result of the parameter data and send it to the database for storage.

[0007] In some embodiments, the group of parameter data results Gi is evaluated to trigger a corresponding type of level warning, specifically: Preset each type of parameter data to correspond to a basic value; extract the parameter type that is higher than the corresponding preset warning threshold, and obtain the basic value corresponding to the parameter type and record it as Ti, and at the same time calculate the difference between the parameter type result Gi and the corresponding warning threshold, and use the calculated difference as the warning difference, and mark it as Ri; Preset the weight coefficients of the basic value Ti and the warning difference Ri, multiply the basic value Ti and the warning difference Ri of the corresponding parameter type by the corresponding preset weight coefficients, and then sum them up to obtain the warning evaluation index Ei of the corresponding parameter type; preset three groups of index value ranges of the warning evaluation index Ei, and set the three groups of index value ranges to correspond to blue warning, yellow warning and red warning respectively; The early warning evaluation index Ei of the corresponding parameter type is matched with the preset three groups of index value ranges to obtain the level of early warning corresponding to the corresponding parameter type and trigger it.

[0008] In some embodiments, a level warning of a corresponding type is triggered, and corresponding steps are performed to select a candidate with the largest advantage value Yc, specifically: Obtain the corresponding type of the trigger level warning, that is, determine whether the trigger level warning is a blue warning, a yellow warning, or a red warning, and set the selectable personnel range corresponding to the blue warning, the yellow warning, and the red warning respectively; Based on the corresponding type of the current trigger level warning, the candidate with the largest advantage value Yc is selected as the solution person from the range of optional personnel corresponding to the level warning, and the regional location of the corresponding parameters is sent to the mobile terminal of the solution person.

[0009] In some embodiments, the specific process of obtaining the merit value Yc of each candidate is as follows: After determining the corresponding type of triggering level warning, send a position feedback instruction to the mobile terminal of each person within the corresponding optional personnel range, set the time range for personnel to confirm the position feedback instruction, mark the personnel who confirm the position feedback instruction within the set time range as candidate personnel, obtain the current location of each candidate personnel after confirmation, and calculate the distance with the regional location of the corresponding parameter to obtain the route distance j1 of each candidate personnel; Obtain the historical number of solutions for each candidate and record it as j2; count the time taken for each candidate to solve each time. The time taken is calculated from the time when the candidate is selected until the triggering cause of the positioning warning is found. This time period is taken as the time taken for the current solution process. Extract the time taken by each group corresponding to each candidate, calculate the mean value respectively, and use the mean value of each group as the average time taken by each candidate j3; The working years of each candidate are marked as j4, and the route distance j1, the number of historical solutions j2, the average time j3 and the working years j4 of each candidate are normalized and calculated to obtain the advantage value Yc of each candidate.

[0010] In some embodiments, the overall evaluation result of the parameter data that triggers the level warning is selectively obtained, specifically: When the problem solver selectively learns the overall evaluation result of a certain parameter data through the mobile terminal, the parameter data is marked as evaluation data, and the retrieval signaling is triggered with one click; When the retrieval signal is triggered, the specific values ​​of the evaluation data within the set time period before the corresponding level warning time point is triggered are extracted; Obtain the specific values ​​of the evaluation data at each time point within the set time period, and calculate the specific values ​​of the evaluation data at each time point using the standard deviation formula, thereby obtaining the coefficient of variation of the evaluation data within the set time period; A reference threshold range of the variation coefficient is set. If the variation coefficient is higher than the set reference threshold range, the variation trend of the evaluation data within the set time period is determined to be gradually increasing; if the variation coefficient is lower than the set reference threshold range, the variation trend of the evaluation data within the set time period is determined to be flat; If the evaluation data changes gradually within the set time period, it means that the process of triggering the level warning is trend triggering; if the evaluation data changes gradually within the set time period, it means that the process of triggering the level warning is sudden triggering; If the coefficient of variation is within the set reference threshold range, the specific values ​​of the evaluation data at each time point within the set time period are extracted, and the mean is calculated. The calculated mean is used as the warning mean of the evaluation data within the set time period, and the difference between the warning mean and the warning threshold corresponding to the evaluation data is calculated; A reference threshold of the difference is set. If the difference is less than the set reference threshold, the change trend is determined to be gradually increasing. If the difference is greater than the set reference threshold, the change trend is determined to be tending to be flat.

[0011] In some embodiments, selectively obtaining the overall evaluation result of the parameter data that triggers the level warning also includes: Construct databases corresponding to trend trigger and sudden trigger respectively, recorded as trend trigger database and sudden trigger database, extract the warning difference Ri corresponding to the evaluation data, and judge the result of the evaluation data process based on the trigger level warning. If the judgment result is trend trigger, the warning difference Ri is input into the trend trigger database; if the judgment result is sudden trigger, the warning difference Ri is input into the sudden trigger database; The trend trigger database and the sudden trigger database are both set with groups of difference value ranges corresponding to the warning difference Ri, and each group of difference value ranges corresponds to a set of reasons for triggering a warning for the evaluation data; Based on the judgment result of the evaluation data process, the warning difference Ri extracted from the evaluation data is matched with the range of each group of difference values ​​in the corresponding constructed database, so as to obtain the set of reasons for the evaluation data to trigger the corresponding level of warning; The process judgment results of the evaluation data and the set of reasons for triggering the warning are extracted and integrated as the overall evaluation results of the parameter data for triggering the level warning.

[0012] In some embodiments, each abnormal data is evaluated to trigger a corresponding type of level warning, specifically: The sum of each abnormal data warning evaluation index Ei is calculated and matched with the preset three groups of index value ranges corresponding to the preset warning evaluation index Ei, thereby triggering the corresponding type of level warning.

[0013] In some embodiments, a dam monitoring abnormality early warning system includes: The deployment and collection module is used to deploy sensors at key areas of the dam, and use the deployed sensors to collect parameter data of the dam in real time; the parameter data are numbered based on their types, and the number is represented by i, where i=1,2...k, k represents the total number of monitoring data required for the dam, and the collected parameter data of the dam are sent to the data processing module; The data processing module is used to pre-process the collected parameter data and send it to the early warning comparison module; The early warning comparison module is used to mark each parameter data result after preprocessing as Gi, preset the early warning threshold corresponding to each parameter data result Gi, and compare each parameter data result Gi with the corresponding preset early warning threshold, and send the comparison result to the early warning evaluation module; The warning evaluation module is used to receive the comparison results of each parameter data. If a group of parameter data results Gi is higher than the corresponding preset warning threshold, the group of parameter data results Gi is evaluated, thereby triggering the corresponding type of level warning and sending it to the personnel screening module. The level warning types include blue warning, yellow warning and red warning; The personnel screening module is used to receive the triggered level warning and execute the corresponding steps to select the candidate with the largest advantage value Yc as the solution personnel, and at the same time increase the historical solution times of the solution personnel by one; The trigger positioning module is used to solve the problem that after receiving the corresponding level warning triggered, personnel can selectively obtain the overall evaluation results of the parameter data of the trigger level warning, so as to solve the problem that personnel can quickly locate the triggering cause of the warning based on the overall evaluation results of the parameter data.

[0014] Compared with the prior art, the present invention has the following beneficial effects: The present invention uses deployed sensors to collect parameter data of the dam in real time. If a group of parameter data results is higher than the corresponding preset warning threshold, the group of parameter data results is evaluated to trigger the corresponding type of graded warning, including blue warning, yellow warning and red warning, so as to distinguish the degree of dangerous hidden dangers of the warning. According to the triggered graded warning, the candidate with the largest advantage value is selected from the range of optional personnel corresponding to the graded warning, and the regional position of the corresponding parameter is sent to the mobile terminal of the problem solver, which solves the problem that in the prior art, when the warning is triggered, the triggered warning signal is mostly responded to through an alarm, and there is a lack of an effective warning response mechanism. The present invention enables the problem solver to selectively obtain the overall evaluation result of the parameter data of the triggering level warning after receiving the corresponding level warning triggered, determine the change trend of the parameter data within a set time period before the warning is triggered, and match the corresponding cause set from the corresponding constructed database according to the result of the determination, thereby helping the problem solver to quickly locate the cause of the triggering warning and improving the degree of intelligence and processing efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Further details, features and advantages of the present application are disclosed in the following description of exemplary embodiments in conjunction with the accompanying drawings, in which: Figure 1 is a flow chart of the present invention; Figure 2 It is a schematic diagram of the present invention. DETAILED DESCRIPTION

[0016] Several embodiments of the present application will be described in more detail below with reference to the accompanying drawings so that those skilled in the art can implement the present application. The present application can be embodied in many different forms and purposes and should not be limited to the embodiments described herein. These embodiments are provided to make the present application comprehensive and complete, and to fully convey the scope of the present application to those skilled in the art. The embodiments do not limit the present application.

[0017] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those of ordinary skill in the art to which this application belongs. It will be further understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the relevant art and / or the context of this specification, and will not be interpreted in an idealized or overly formal sense unless explicitly defined as such herein. Example 1

[0018] See also Figure 1 As shown, a dam monitoring abnormality early warning method includes: S1: Deploy sensors at key locations of the dam and use the deployed sensors to collect parameter data of the dam in real time. The parameter data are numbered based on their types. The number is represented by i, where i=1,2...k, and k represents the total number of monitoring data required for the dam. The parameter data include displacement, stress, and water level. Preprocess the collected parameter data. The preprocessing includes but is not limited to cleaning, denoising, and standardization. The location of key areas is selected based on the structural characteristics, setting characteristics and safety monitoring needs of the current monitored dam, such as the dam top and the inside of the dam body, and is arranged by technical personnel; S2: Mark each parameter data result after preprocessing as Gi, preset the warning threshold corresponding to each parameter data result Gi, and compare each parameter data result Gi with the corresponding preset warning threshold; The warning threshold is set based on historical data, statistical analysis and expert experience, and can be dynamically adjusted according to actual conditions; S3: If a set of parameter data results Gi is higher than the corresponding preset warning threshold, the set of parameter data results Gi is evaluated to trigger the corresponding type of level warning, and the corresponding steps are executed to select the candidate with the largest advantage value Yc as the solver, and the historical number of solvers is increased by one; the level warning types include blue warning, yellow warning and red warning; The degree of danger and hidden danger corresponding to the red warning is greater than that corresponding to the yellow warning, and the degree of danger and hidden danger corresponding to the blue warning. The group of parameter data results Gi is evaluated to trigger the corresponding type of level warning, specifically: Each type of parameter data is preset to correspond to a basic value; the greater the hidden danger caused by the parameter triggering the warning, the higher the corresponding basic value. For example, the basic value corresponding to the displacement parameter is higher than the basic value corresponding to the water level. Extract the parameter type that is higher than the corresponding preset warning threshold, obtain the basic value corresponding to the parameter type and record it as Ti, and calculate the difference between the parameter type result Gi and the corresponding warning threshold, use the calculated difference as the warning difference, and mark it as Ri; Preset the weight coefficients of the basic value Ti and the warning difference Ri, multiply the basic value Ti and the warning difference Ri of the corresponding parameter type by the corresponding preset weight coefficients, and then sum them up to obtain the warning evaluation index Ei of the corresponding parameter type; Three groups of index value ranges of the preset warning evaluation index Ei are set to correspond to blue warning, yellow warning and red warning respectively; Match the early warning evaluation index Ei of the corresponding parameter type with the preset three groups of index value ranges, so as to obtain the level of early warning corresponding to the corresponding parameter type and trigger it; Trigger the corresponding type of level warning, and execute the corresponding steps to select the candidate with the largest advantage value Yc, specifically: Obtain the corresponding type of the trigger level warning, that is, determine whether the trigger level warning is a blue warning, a yellow warning, or a red warning, and set the selectable personnel range corresponding to the blue warning, the yellow warning, and the red warning respectively; It should be noted that different levels of warnings have different requirements for the experience and ability of the problem solvers. Different problem solvers are assigned to corresponding levels of warnings to facilitate targeted screening when the corresponding types of level warnings are triggered later.

[0019] After determining the corresponding type of triggering level warning, send a position feedback instruction to the mobile terminal of each person within the corresponding optional personnel range, set the time range for personnel to confirm the position feedback instruction, mark the personnel who confirm the position feedback instruction within the set time range as candidate personnel, obtain the current location of each candidate personnel after confirmation, and calculate the distance with the regional location of the corresponding parameter to obtain the route distance j1 of each candidate personnel; Obtain the historical number of solutions for each candidate and record it as j2; count the time taken for each candidate to solve each time. The time taken is calculated from the time when the candidate is selected until the triggering cause of the positioning warning is found. This time period is taken as the time taken for the current solution process. Extract the time taken by each group corresponding to each candidate, calculate the mean value respectively, and use the mean value of each group as the average time taken by each candidate j3; Mark the working years of each candidate as j4, according to the formula , weighted calculation is performed on the route distance j1, historical solution times j2, average time j3 and working years j4 of each candidate to obtain the advantage value Yc of each candidate; where a1, a2, a3 and a4 are the influence weight factors of route distance j1, historical solution times j2, average time j3 and working years j4 respectively; The candidate with the largest advantage value Yc is selected as the solver, and the regional location of the corresponding parameters is sent to the solver's mobile terminal; It should be noted that through intelligent analysis and scheduling, the efficiency and effectiveness of the dam monitoring abnormality early warning system have been improved, ensuring the timeliness and effectiveness of dam safety monitoring.

[0020] S4: If there are multiple sets of parameter data results Gi that are all higher than the corresponding preset warning threshold, then extract the sets of parameter data that are higher than the corresponding preset warning threshold and record them as abnormal data. Similarly, step S3 evaluates each abnormal data to trigger the corresponding type of level warning; Specifically: Calculate the sum of each abnormal data warning evaluation index Ei, and match it with the preset three groups of index value ranges corresponding to the preset warning evaluation index Ei, so as to trigger the corresponding type of level warning; S5: After receiving the triggered warning of the corresponding level, the problem solver can selectively obtain the overall evaluation result of the parameter data of the triggering level warning. The problem solver can quickly locate the triggering cause of the warning based on the overall evaluation result of the parameter data and send it to the database for storage; Selectively obtain the overall evaluation results of the parameter data that triggers the level warning, specifically: When the problem solver selectively learns the overall evaluation result of a certain parameter data through the mobile terminal, the parameter data is marked as evaluation data, and the retrieval signaling is triggered with one click; When the retrieval signal is triggered, the specific values ​​of the evaluation data within the set time period before the corresponding level warning time point is triggered are extracted; Obtain the specific values ​​of the evaluation data at each time point within the set time period, and calculate the specific values ​​of the evaluation data at each time point using the standard deviation formula, thereby obtaining the coefficient of variation of the evaluation data within the set time period; A reference threshold range of the variation coefficient is set. If the variation coefficient is higher than the set reference threshold range, the variation trend of the evaluation data within the set time period is determined to be gradually increasing; if the variation coefficient is lower than the set reference threshold range, the variation trend of the evaluation data within the set time period is determined to be flat; If the evaluation data changes gradually within the set time period, it means that the process of triggering the level warning is trend triggering; if the evaluation data changes gradually within the set time period, it means that the process of triggering the level warning is sudden triggering; If the coefficient of variation is within the set reference threshold range, the specific values ​​of the evaluation data at each time point within the set time period are extracted, and the mean is calculated. The calculated mean is used as the warning mean of the evaluation data within the set time period, and the difference between the warning mean and the warning threshold corresponding to the evaluation data is calculated; Set a reference threshold of the difference. If the difference is less than the set reference threshold, the change trend is determined to be gradually increasing. If the difference is greater than the set reference threshold, the change trend is determined to be flat. Construct databases corresponding to trend trigger and sudden trigger respectively, recorded as trend trigger database and sudden trigger database, extract the warning difference Ri corresponding to the evaluation data, and judge the result of the evaluation data process based on the trigger level warning. If the judgment result is trend trigger, the warning difference Ri is input into the trend trigger database; if the judgment result is sudden trigger, the warning difference Ri is input into the sudden trigger database; The trend trigger database and the sudden trigger database are both set with groups of difference value ranges corresponding to the warning difference value Ri, and each group of difference value ranges corresponds to a set of reasons for triggering a warning for the evaluation data; Based on the judgment result of the evaluation data process, the warning difference Ri extracted from the evaluation data is matched with the range of each group of difference values ​​in the corresponding constructed database, so as to obtain the set of reasons for the evaluation data to trigger the corresponding level of warning; Extract the process judgment results of the evaluation data and the set of reasons for triggering the warning, and integrate them as the overall evaluation results of the parameter data for triggering the level warning; The database construction process is based on historical data and expert advice, and the content of the database is dynamically adjusted in real time according to subsequent actual conditions; For example, The problem solver selects the dam displacement parameters through the mobile terminal, and the system marks them as evaluation data and triggers the retrieval signal; The system extracts the data of the dam displacement parameters within 1 hour before the warning, for example, recording once every 5 minutes, for a total of 12 data points.

[0021] Calculate the standard deviation of these data points to get the coefficient of variation.

[0022] The reference threshold range of the variation coefficient is set to ±0.5mm. If the calculated variation coefficient is 0.7mm, which is higher than the threshold range, it means that the process of triggering the level warning is trend triggering, and lower than the threshold range, it means that the process of triggering the level warning is sudden triggering; If it is a trend trigger, then in the trend trigger database, according to the value of Ri, a set of possible warning reasons is matched, such as "increased rainfall upstream causes water levels to rise, which in turn leads to increased displacement."

[0023] Integrate the change trend of displacement parameters, warning difference Ri, and cause set to form an overall evaluation result, which is sent to the mobile terminal of the problem solver; It should be noted that By analyzing the changing trends and calculating the changing coefficients, problem solvers can quickly locate the triggering cause of the warning and provide a basis for taking countermeasures; automated data processing and trend analysis reduce the time of manual analysis and improve the response speed to warning situations. Example 2

[0024] See also Figure 2 As shown, based on a dam monitoring abnormality early warning method provided in Example 1 of the present application, Example 2 of the present application proposes a dam monitoring abnormality early warning system. Example 2 is only a preferred method of Example 1, and the implementation of Example 2 will not affect the independent implementation of Example 1.

[0025] Specifically, the difference of a dam monitoring abnormality early warning system provided in Example 2 of the present application is that it includes a deployment collection module, a data processing module, an early warning comparison module, an early warning assessment module, a personnel screening module and a trigger positioning module; The deployment and collection module is used to deploy sensors at key areas of the dam, and use the deployed sensors to collect parameter data of the dam in real time; the parameter data are numbered based on their types, and the number is represented by i, where i=1,2...k, k represents the total number of monitoring data required for the dam, and the collected parameter data of the dam are sent to the data processing module; The data processing module is used to pre-process the collected parameter data and send it to the early warning comparison module; pre-processing includes but is not limited to cleaning, denoising and standardization processing The early warning comparison module is used to mark each parameter data result after preprocessing as Gi, preset the early warning threshold corresponding to each parameter data result Gi, and compare each parameter data result Gi with the corresponding preset early warning threshold, and send the comparison result to the early warning evaluation module; The warning evaluation module is used to receive the comparison results of each parameter data. If a group of parameter data results Gi is higher than the corresponding preset warning threshold, the group of parameter data results Gi is evaluated, thereby triggering the corresponding type of level warning and sending it to the personnel screening module. The level warning types include blue warning, yellow warning and red warning; The personnel screening module is used to receive the triggered level warning and execute the corresponding steps to select the candidate with the largest advantage value Yc as the solution personnel, and at the same time increase the historical solution times of the solution personnel by one; The trigger positioning module is used to solve the problem that after receiving the corresponding level warning triggered, the personnel can selectively obtain the overall evaluation results of the parameter data of the trigger level warning, so as to solve the problem that the personnel can quickly locate the triggering cause of the warning based on the overall evaluation results of the parameter data; The above formulas are obtained by collecting a large amount of data and performing software simulation, and a formula close to the actual value is selected. The influencing weight factor and specific coefficient value in the formula are set by technical personnel in this field according to actual conditions, and can be adjusted and modified later.

[0026] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A dam monitoring abnormality early warning method, characterized in that: include: S1: Deploy sensors at key locations of the dam and use the deployed sensors to collect parameter data of the dam in real time. The parameter data are numbered based on their types. The number is represented by i, where i=1,2...k, and k represents the total number of monitoring data required for the dam; pre-process the collected parameter data; S2: Mark each parameter data result after preprocessing as Gi, preset the warning threshold corresponding to each parameter data result Gi, and compare each parameter data result Gi with the corresponding preset warning threshold; S3: If a set of parameter data results Gi is higher than the corresponding preset warning threshold, the set of parameter data results Gi is evaluated to trigger the corresponding type of level warning, and the corresponding steps are executed to select the candidate with the largest advantage value Yc as the solver, and the historical number of solvers is increased by one; The types of warning levels include blue warning, yellow warning and red warning; S4: If there are multiple sets of parameter data results Gi that are all higher than the corresponding preset warning threshold, then extract the sets of parameter data that are higher than the corresponding preset warning threshold and record them as abnormal data. Similarly, step S3 evaluates each abnormal data to trigger the corresponding type of level warning; S5: After receiving the triggered warning of the corresponding level, the problem solver can selectively obtain the overall evaluation result of the parameter data of the triggered level warning. The problem solver can quickly locate the triggering cause of the warning based on the overall evaluation result of the parameter data and send it to the database for storage.

2. A dam monitoring abnormality early warning method according to claim 1, characterized in that: The group of parameter data results Gi is evaluated to trigger the corresponding type of level warning, specifically: Preset each type of parameter data to correspond to a basic value; extract the parameter type that is higher than the corresponding preset warning threshold, and obtain the basic value corresponding to the parameter type and record it as Ti, and at the same time calculate the difference between the parameter type result Gi and the corresponding warning threshold, and use the calculated difference as the warning difference, and mark it as Ri; Preset the weight coefficients of the basic value Ti and the warning difference Ri, multiply the basic value Ti and the warning difference Ri of the corresponding parameter type by the corresponding preset weight coefficients, and then sum them up to obtain the warning evaluation index Ei of the corresponding parameter type; preset three groups of index value ranges of the warning evaluation index Ei, and set the three groups of index value ranges to correspond to blue warning, yellow warning and red warning respectively; The early warning evaluation index Ei of the corresponding parameter type is matched with the preset three groups of index value ranges to obtain the level of early warning corresponding to the corresponding parameter type and trigger it.

3. The dam monitoring abnormality early warning method according to claim 1 is characterized in that: Trigger the corresponding type of level warning, and execute the corresponding steps to select the candidate with the largest advantage value Yc, specifically: Obtain the corresponding type of the trigger level warning, that is, determine whether the trigger level warning is a blue warning, a yellow warning, or a red warning, and set the selectable personnel range corresponding to the blue warning, the yellow warning, and the red warning respectively; Based on the corresponding type of the current trigger level warning, the candidate with the largest advantage value Yc is selected as the solution person from the range of optional personnel corresponding to the level warning, and the regional location of the corresponding parameters is sent to the mobile terminal of the solution person.

4. The dam monitoring abnormality early warning method according to claim 1 is characterized in that: The specific process of obtaining the merit value Yc of each candidate is as follows: After determining the corresponding type of triggering level warning, send a position feedback instruction to the mobile terminal of each person within the corresponding optional personnel range, set the time range for personnel to confirm the position feedback instruction, mark the personnel who confirm the position feedback instruction within the set time range as candidate personnel, obtain the current location of each candidate personnel after confirmation, and calculate the distance with the regional location of the corresponding parameter to obtain the route distance j1 of each candidate personnel; Obtain the historical number of solutions for each candidate and record it as j2; count the time taken for each candidate to solve each time. The time taken is calculated from the time when the candidate is selected until the triggering cause of the positioning warning is found. This time period is taken as the time taken for the current solution process. Extract the time taken by each group corresponding to each candidate, calculate the mean value respectively, and use the mean value of each group as the average time taken by each candidate j3; The working years of each candidate are marked as j4, and the route distance j1, historical solution times j2, average time j3 and working years j4 of each candidate are normalized and calculated to obtain the advantage value Yc of each candidate.

5. The dam monitoring abnormality early warning method according to claim 1 is characterized in that: Selectively obtain the overall evaluation results of the parameter data that triggers the level warning, specifically: When the problem solver selectively learns the overall evaluation result of a certain parameter data through the mobile terminal, the parameter data is marked as evaluation data, and the retrieval signaling is triggered with one click; When the retrieval signal is triggered, the specific values ​​of the evaluation data within the set time period before the corresponding level warning time point is triggered are extracted; Obtain the specific values ​​of the evaluation data at each time point within the set time period, and calculate the specific values ​​of the evaluation data at each time point using the standard deviation formula, thereby obtaining the coefficient of variation of the evaluation data within the set time period; A reference threshold range of the variation coefficient is set. If the variation coefficient is higher than the set reference threshold range, the variation trend of the evaluation data within the set time period is determined to be gradually increasing; if the variation coefficient is lower than the set reference threshold range, the variation trend of the evaluation data within the set time period is determined to be flat; If the evaluation data changes gradually within the set time period, it means that the process of triggering the level warning is trend triggering; if the evaluation data changes gradually within the set time period, it means that the process of triggering the level warning is sudden triggering; If the coefficient of variation is within the set reference threshold range, the specific values ​​of the evaluation data at each time point within the set time period are extracted, and the mean is calculated. The calculated mean is used as the warning mean of the evaluation data within the set time period, and the difference between the warning mean and the warning threshold corresponding to the evaluation data is calculated; A reference threshold of the difference is set. If the difference is less than the set reference threshold, the change trend is determined to be gradually increasing. If the difference is greater than the set reference threshold, the change trend is determined to be tending to be flat.

6. A dam monitoring abnormality early warning method according to claim 5, characterized in that: Selectively obtain the overall evaluation results of the parameter data that triggers the level warning, including: Construct databases corresponding to trend trigger and sudden trigger respectively, recorded as trend trigger database and sudden trigger database, extract the warning difference Ri corresponding to the evaluation data, and judge the result of the evaluation data process based on the trigger level warning. If the judgment result is trend trigger, the warning difference Ri is input into the trend trigger database; if the judgment result is sudden trigger, the warning difference Ri is input into the sudden trigger database; The trend trigger database and the sudden trigger database are both set with groups of difference value ranges corresponding to the warning difference Ri, and each group of difference value ranges corresponds to a set of reasons for triggering a warning for the evaluation data; Based on the judgment result of the evaluation data process, the warning difference Ri extracted from the evaluation data is matched with the range of each group of difference values ​​in the corresponding constructed database, so as to obtain the set of reasons for the evaluation data to trigger the corresponding level of warning; The process judgment results of the evaluation data and the set of reasons for triggering the warning are extracted and integrated as the overall evaluation results of the parameter data for triggering the level warning.

7. The dam monitoring abnormality early warning method according to claim 1 is characterized in that: Each abnormal data is evaluated to trigger the corresponding level warning, specifically: The sum of each abnormal data warning evaluation index Ei is calculated and matched with the preset three groups of index value ranges corresponding to the preset warning evaluation index Ei, thereby triggering the corresponding type of level warning.

8. The dam monitoring abnormality early warning system according to claim 1 is applied to the dam monitoring abnormality early warning system according to claims 1 to 7, characterized in that: include: The deployment and collection module is used to deploy sensors at key areas of the dam and use the deployed sensors to collect parameter data of the dam in real time; The parameter data are numbered based on their types, and the number is represented by i, where i=1,2...k, and k represents the total number of monitoring data required for the dam, and the collected parameter data of the dam are sent to the data processing module; The data processing module is used to pre-process the collected parameter data and send it to the early warning comparison module; The early warning comparison module is used to mark each parameter data result after preprocessing as Gi, preset the early warning threshold corresponding to each parameter data result Gi, and compare each parameter data result Gi with the corresponding preset early warning threshold, and send the comparison result to the early warning evaluation module; The warning evaluation module is used to receive the comparison results of each parameter data. If a group of parameter data results Gi is higher than the corresponding preset warning threshold, the group of parameter data results Gi is evaluated, thereby triggering the corresponding type of level warning and sending it to the personnel screening module. The level warning types include blue warning, yellow warning and red warning; The personnel screening module is used to receive the triggered level warning and execute the corresponding steps to select the candidate with the largest advantage value Yc as the solution personnel, and at the same time increase the historical solution times of the solution personnel by one; The trigger positioning module is used to solve the problem that after receiving the corresponding level warning triggered, personnel can selectively obtain the overall evaluation results of the parameter data of the trigger level warning, so as to solve the problem that personnel can quickly locate the triggering cause of the warning based on the overall evaluation results of the parameter data.

Images