Hydropower station equipment operation state safety early warning method

Abstract

The invention discloses a hydropower station equipment operation state safety early warning method comprising the steps that a three-dimensional model is established, the actual shape of a dam body is scaled down and converted into a three-dimensional model of a dynamic deformation module, the surface of the dynamic deformation module is covered with grid points, and an environment parameter sensor is arranged in the dynamic deformation module; environment data of the hydropower station dam are collected, a first work consumption random number and a second work consumption random number are calculated, the value of the first work consumption random number is mapped to a color space to be converted into a thermal loop, and the value of the second work consumption random number is mapped to a strip to be converted into a water level pressure band; and when the displacement of the grid points is greater than a preset displacement threshold value, the grid points are highlighted and abnormal early warning is carried out. By establishing a dynamic deformation module, complex displacement data becomes visual, and by introducing a thermal loop and a water level pressure band, operators can quickly find abnormal conditions, and the efficiency and accuracy of hydropower station dam safety management are improved.

Description

Technical Field

[0001] The invention relates to the technical field of data processing, and in particular to a safety early warning method for the operating status of hydropower station equipment. Background Art

[0002] Hydropower station equipment is used to monitor hydropower station dams. Hydropower station dams are important infrastructure of the national economy, important engineering measures for regulating the spatial and temporal distribution of water resources and optimizing water resource allocation, and important components of the national flood control, drought relief and disaster reduction system and river flood control engineering system. The safety of hydropower station dams is not only related to flood control safety, water supply safety, and food security, but also to economic security and ecological security.

[0003] For example, Chinese patent application No. 202311471302.2 discloses a method for warning abnormal data of a hydropower station dam, comprising the following steps: S1. Collecting a real-time data set of a hydropower station dam, wherein the real-time data set includes an environmental data subset and a working data subset; S2. Determining a first working consumption random number and a second working consumption random number; S3. Traversing the working data subset to generate a standard working data subset; S4. Filtering abnormal working data in the standard working data subset and issuing a warning. However, the above scheme does not predict the status of the hydropower station equipment, and cannot detect abnormal situations in time.

[0004] During the dam safety monitoring process, some abnormal data will be generated. The timely warning of abnormal data is related to the early prediction of dam danger. However, the existing abnormal data warning technology of hydropower station dams usually ignores the influence of the dam body's own environment (such as dam body water level and dam body temperature, etc.), resulting in inaccurate warning. In addition, the existing technology for monitoring abnormal data of hydropower station dams does not set a warning lead time, and the operating personnel cannot respond to abnormal situations in a timely manner, affecting the timeliness of the warning. Summary of the invention

[0005] The present application provides a safety early warning method for the operating status of hydropower station equipment. By analyzing the displacement changes of the hydropower station dam and its relationship with temperature and water level, the dam body is simulated into a three-dimensional model called a dynamic deformation module, which can accurately monitor and predict abnormal conditions of the dam body.

[0006] The present application provides a method for early warning of the operating status of hydropower station equipment, including:

[0007] S101, establishing a three-dimensional model, scaling down the actual shape of the dam body and converting it into a three-dimensional model of a dynamic deformation module, wherein the surface of the dynamic deformation module is covered with grid points, and the displacement of the dam body is converted into the displacement of the grid points. An environmental parameter sensor is provided in the dynamic deformation module, and the environmental parameter sensor can receive data in real time;

[0008] S102, collecting environmental data of the hydropower station dam, and calculating a first work consumption random number and a second work consumption random number according to the environmental data;

[0009] S103, storing the first work consumption random number and the second work consumption random number in the dynamic deformation module, the environmental parameter sensor in the dynamic deformation module receives the first work consumption random number and the second work consumption random number, maps the value of the first work consumption random number to the color space to convert it into a thermal ring, and maps the value of the second work consumption random number to the strip to convert it into a water level pressure strip;

[0010] S104, when the displacement size of the grid point is greater than the preset displacement threshold, the grid point is highlighted and an abnormal warning is issued. At the same time, the system automatically records the highlighted grid point as an abnormal point, wherein the first work consumption random number and the second work consumption random number can both affect the displacement of the grid point.

[0011] Preferably, the first operation consumes a random number The second job consumes random numbers Where σ0 represents the standard deviation of the dam body temperature at all times, h max Indicates the maximum working temperature of the dam body, h min Indicates the minimum working temperature of the dam body, h t represents the dam working temperature at time t, floor represents the rounding down operation, T represents all times; σ1 represents the standard deviation of the dam water level at all times, s max Indicates the maximum working water level of the dam, s min Indicates the minimum working water level of the dam, s t Represents the working water level of the dam at time t.

[0012] Preferably, the specific steps of converting the first work consumption random number into a thermal ring and the second work consumption random number into a water level pressure zone are as follows:

[0013] A1. Determine the maximum and minimum values ​​of the random numbers consumed by the first work according to the formula of the random numbers consumed by the first work; determine the maximum and minimum values ​​of the random numbers consumed by the second work according to the formula of the random numbers consumed by the second work;

[0014] A2, using a hue, saturation, and brightness model to map the maximum and minimum values ​​of the random numbers consumed by the first task and the maximum and minimum values ​​of the random numbers consumed by the second task;

[0015] A3, selecting a hue range to represent the maximum and minimum values ​​of the random numbers consumed by the first job and the maximum and minimum values ​​of the random numbers consumed by the second job;

[0016] A4. Normalize each value of the first work consumption random number and the second work consumption random number;

[0017] A5. Map the normalized values ​​to the selected hue range, and use the graphics library to draw the thermal ring and water level pressure belt based on the mapped data.

[0018] Preferably, the specific steps of adding a time dimension to the dynamic deformation module are:

[0019] S201, recording the current time information of the random number consumed by the first work and the random number consumed by the second work, forming a timestamp of the time information and storing it in the dynamic deformation module, arranging the thermal loop data in the dynamic deformation module in time sequence to form a time series thermal loop, and similarly arranging the water level pressure zone data in time sequence to form a time pressure zone;

[0020] S202, updating the first work consumption random number and the second work consumption random number stored in the dynamic deformation module through the collected real-time environmental data, the time series thermal loop is updated in real time according to the changes of the temperature data and the first work consumption random number, and the time pressure band is updated in real time according to the water level data and the second work consumption random number;

[0021] S203, according to historical data, preset temperature thresholds and water level thresholds, and store the preset temperature thresholds and water level thresholds in the dynamic deformation module, when the monitored temperature exceeds the temperature threshold or the water level exceeds the water level threshold, the early warning mechanism in the dynamic deformation module is triggered;

[0022] S204, according to step S201, the timestamp is stored in the dynamic deformation module, so that the device is equipped with an early warning lead time, and the number of actual abnormalities and warnings and the number of actual normals and false alarms are counted according to the early warning situation, and the proportion of warnings and the proportion of false alarms are calculated according to the statistical number of times, and the comprehensive accuracy of the proportion of warnings and the proportion of false alarms is calculated through F1 score statistics.

[0023] Preferably, the early warning precursor loop is the temperature variation characteristics of the dam body in the period before the abnormal situation is about to occur, which is the historical data in the time series thermal loop;

[0024] The critical pressure trajectory is the rising trajectory and pressure change of the water level change in the historical data in the time pressure zone before the abnormal situation occurs.

[0025] Preferably, the step of generating a directional early warning precursor ring is:

[0026] B1. Collect the dam body temperature data at each time point, compare the temperature values ​​at consecutive time points, and determine the direction of the temperature change trend;

[0027] B2. Based on the continuous temperature values, calculate the difference between adjacent temperature values, and determine the direction of temperature change according to the positive or negative value of the difference;

[0028] B3. Sum the differences in the same direction to represent the cumulative value in this direction, and sum the differences in different directions to obtain the cumulative values ​​in different directions;

[0029] B4. Based on the accumulated value, with time as the horizontal axis and the accumulated value as the vertical axis, the chart making software in the dynamic deformation module generates a chart of the directional early warning precursor ring using the accumulated value and time.

[0030] Preferably, a positive difference indicates that the temperature rises within the time interval, and the positive temperature difference is quantified as the micro-motion in the direction of temperature rise; a negative difference indicates that the temperature drops within the time interval, and the absolute value of the negative temperature difference is quantified as the micro-motion in the direction of temperature drop.

[0031] Preferably, the step of generating the micro-momentum critical pressure trajectory is:

[0032] C1. Collect dam water level data at each time point, compare the water level values ​​at consecutive time points, and determine the direction of water level change trend;

[0033] C2. Based on the continuous water level values, calculate the difference between adjacent water level values, and determine the direction of water level change according to the positive or negative value of the difference;

[0034] C3. Sum the differences in the same direction to represent the cumulative value in this direction, and sum the differences in different directions to obtain the cumulative values ​​in different directions;

[0035] C4. Based on the accumulated value, draw the critical pressure trajectory of the micro-motion volume with time as the horizontal axis and the accumulated value as the vertical axis.

[0036] Preferably, a positive difference indicates that the water level rises during the time interval, and the positive water level difference is quantified as the micro-motion in the rising direction; a negative difference indicates that the water level drops during the time interval, and the absolute value of the negative water level difference is quantified as the micro-motion in the dropping direction.

[0037] Preferably, the specific steps for dividing the warning sensitive areas are:

[0038] S301, dividing the hydropower station dam into multiple monitoring areas, and marking different monitoring areas as early warning sensitive areas of different degrees according to the structural characteristics and historical data of each monitoring area;

[0039] S302, adjusting the data collection frequency according to different levels of early warning sensitivity areas. For areas with high early warning sensitivity and frequent historical problems, the data collection frequency is increased to capture more subtle changes; for relatively stable areas or areas with fewer problems, the collection frequency is reduced;

[0040] S303, establish a collaborative early warning model, use algorithms to build models based on historical data on dam temperature and water level, and design a collaborative early warning mechanism.

[0041] One or more technical solutions provided in this application have at least the following technical effects or advantages: by establishing a three-dimensional model of the dynamic deformation module, complex displacement data becomes intuitive, and the introduction of the thermal ring and the water level pressure zone can intuitively show the influence of temperature and water level on the displacement of the dam body, so that operators can quickly discover abnormal conditions, thereby improving the efficiency and accuracy of the safety management of the hydropower station dam;

[0042] By introducing the time dimension, the dynamic deformation module can identify safety hazards earlier. Abnormal changes are not significant in the early stage, but will gradually accumulate over time and lead to serious consequences. The time-series thermal ring and time pressure zone enable the dynamic deformation module to warn the safety status of the dam in advance, so that operators can pay more attention to it; the early warning precursor ring and critical pressure trajectory enable the dynamic deformation module to issue an early warning before the abnormal situation occurs, providing operators with sufficient response time, so that the accuracy of the early warning is improved;

[0043] At the same time, the time-series thermal ring and time-pressure belt can display the trend of temperature and water level changes, so that the dynamic deformation module can predict the state of the dam here according to the trend. The trend prediction capability enables operators to understand the state of the dam in time and deal with it. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a flow chart of a method for early warning safety of equipment operation status in a hydropower station according to the present invention;

[0045] Figure 2 A schematic diagram of a process of adding a time dimension to a dynamic deformation module according to an embodiment of the present invention;

[0046] Figure 3 The figure is a schematic diagram of a process of dividing warning sensitive areas according to an embodiment of the present invention. DETAILED DESCRIPTION

[0047] To facilitate the understanding of the present invention, the present application will be described more comprehensively below with reference to the relevant drawings; the drawings show preferred embodiments of the present invention, but the present invention can be implemented in many different forms and is not limited to the embodiments described herein; on the contrary, the purpose of providing these embodiments is to enable a more thorough and comprehensive understanding of the disclosed content of the present invention.

[0048] It should be noted that the terms “vertical”, “horizontal”, “up”, “down”, “left”, “right” and similar expressions used in this document are only for illustrative purposes and do not represent the only implementation method.

[0049] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which the present invention belongs; the terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention; the term "and / or" used herein includes any and all combinations of one or more related listed items.

[0050] Embodiment 1: Figure 1 The present invention is a schematic flow chart of a method for early warning of the operation status of hydropower station equipment according to an embodiment of the present invention, comprising the following steps:

[0051] S101, establishing a three-dimensional model, scaling down the actual shape of the dam body and converting it into a three-dimensional model of a dynamic deformation module, the surface of the dynamic deformation module is covered with grid points, and an environmental parameter sensor is arranged in the dynamic deformation module.

[0052] Specifically, SolidWorks is used to model the dam body, and the three-dimensional model of the dam body is reduced at a ratio of 1:500, so that the dam body is more refined and the displacement of the grid is clearer. The dynamic deformation module refers to a digital model constructed by scaling down the actual three-dimensional shape of the hydropower station dam. The model can reflect the deformation of the dam body under various environmental conditions in real time; the environmental parameter sensor uses a temperature sensor and a liquid level sensor. The temperature sensor has an accuracy of ±0.1°C and is used to monitor the dam body temperature in real time; the liquid level sensor has an accuracy of ±1cm and is used to monitor the dam body water level in real time; the environmental parameter sensor can receive temperature and water level data in real time, and the grid points move according to the received temperature and water level data. The distance moved by the grid points represents the size of the dam body displacement, and the direction of the displacement is indicated by an arrow. The three-dimensional modeling technology is used to establish the three-dimensional model. The three-dimensional modeling technology is an existing technical means and will not be elaborated here.

[0053] S102, collecting environmental data of the hydropower station dam, and calculating a first work consumption random number (H) and a second work consumption random number (S) according to the environmental data.

[0054] Among them, the collected data is collected through environmental parameter sensors, and the collected data includes temperature data and water level data. The first working consumption random number (H) represents the change of the real-time temperature of the dam body. The specific calculation method of the first working consumption random number (H) is to obtain the temperature range (maximum value, minimum value and standard deviation) of the dam body under different working conditions through experimental measurement or historical data statistics, and then calculate the H value based on the real-time temperature. The setting of this parameter is based on the thermal expansion coefficient of the material and engineering experience to ensure that it can accurately reflect the impact of temperature on the displacement of the dam body. Where σ0 represents the standard deviation of the dam body temperature at all times, hmax Indicates the maximum working temperature of the dam body, h min Indicates the minimum working temperature of the dam body, h t It represents the working temperature of the dam at time t, floor represents rounding down, and T represents all times; the second work consumption random number (S) represents the change of the real-time water level of the dam. The calculation basis of the second work consumption random number (S) is the ratio of the change amplitude of the dam water level to the working water level range of the dam. The maximum, minimum and standard deviation of the dam working water level are obtained through experimental measurement or historical data statistics, and then the S value is calculated in combination with the real-time water level. The setting of this parameter takes into account the influence of water pressure on the dam structure and is determined based on the principles of fluid mechanics and engineering safety specifications. σ1 represents the standard deviation of the dam water level at all times, s max Indicates the maximum working water level of the dam, s min Indicates the minimum working water level of the dam, s t It represents the working water level of the dam at time t, floor represents rounding down, and T represents all times.

[0055] S103, storing the first work consumption random number (H) and the second work consumption random number (S) in the dynamic deformation module. In the dynamic deformation module, mapping the value of the first work consumption random number (H) to the color space and converting it into a thermal ring, and mapping the value of the second work consumption random number (S) to the strip and converting it into a water level pressure band.

[0056] Specifically, the maximum value and minimum value of the first work consumption random number (H) are determined according to the formula of the first work consumption random number (H); the maximum value and minimum value of the second work consumption random number (S) are determined according to the formula of the second work consumption random number (S), and the hue, saturation, and brightness model (HSV) are used to map the maximum value and minimum value of the first work consumption random number (H) and the maximum value and minimum value of the second work consumption random number (S), and a hue range is selected to represent the maximum value and minimum value of the first work consumption random number (H) and the maximum value and minimum value of the second work consumption random number (S), and each value of the first work consumption random number (H) and the second work consumption random number (S) is normalized to a range of 0 to 1, and the normalized value is mapped to the selected hue range through a mapping function, and a thermal ring and a water level pressure belt are drawn using a graphics library according to the mapped data, and the mapping function and the graphics library are both existing technical solutions.

[0057] The color mapping rule of the thermal ring is that the lowest temperature value corresponds to blue, the highest temperature value corresponds to red, and the intermediate temperature value is mapped to a color between blue and red by linear interpolation. The depth and distribution of the color of the thermal ring indicate the current temperature of the dam body. The high density and dark color of the thermal ring indicate that this is a high temperature area. The color of the thermal ring can remind the operator that this is a high temperature area, and the dam body in the high temperature area is more likely to deform. The mapping rule of the water level pressure belt is that the lowest water level corresponds to a light-colored strip, the highest water level corresponds to a dark-colored strip, and the intermediate water level value is mapped to color strips of different depths by linear interpolation. The depth and range of the water level pressure belt reflect the pressure distribution of the water level on the bottom of the dam body. The deepening of the color of the water level pressure belt and the expansion of the range indicate that the pressure at the bottom of the dam body has increased. The color of the water level pressure belt can remind the operator to pay attention to the water level in the area and reduce the instability of the dam body caused by the rising water level. The color changes of the thermal ring and the water level pressure belt can intuitively show the changes in the dam body, so that the operator can intervene in the abnormal situation of the dam body in time.

[0058] S104, when the displacement of a grid point is greater than a preset displacement threshold, the grid point is highlighted and an abnormal warning is issued. At the same time, the system automatically records the highlighted grid point as an abnormal point to remind the operator to handle it in time.

[0059] The technical solutions in the above embodiments of the present application have at least the following technical effects or advantages:

[0060] By establishing a three-dimensional model of the dynamic deformation module, complex displacement data becomes intuitive and easy to understand; the introduction of thermal rings and water level pressure zones makes it possible to intuitively display the effects of temperature and water level on dam displacement; the method of highlighting abnormal grid points can quickly attract the attention of operators and trigger an early warning mechanism, ensuring that potential abnormal situations are discovered and handled in a timely manner, thereby improving the efficiency and accuracy of hydropower station dam safety management.

[0061] Embodiment 2: In embodiment 1, a safety warning system based on a three-dimensional model was established. However, the system mainly focused on real-time data and lacked the ability to analyze and predict historical data. On the basis of embodiment 1, a time dimension was added to the dynamic deformation module, and the changes in temperature and water level were analyzed according to historical data. This enabled the dynamic deformation module to issue early warnings for abnormal situations, and operators had sufficient response time.

[0062] like Figure 2 As shown in the figure, the steps to add a time module to the dynamic deformation module are:

[0063] S201, record the current time information of the first work consumption random number (H) and the second work consumption random number (S), the time information forms a timestamp and is stored in the dynamic deformation module, the thermal ring data in the dynamic deformation module is arranged in chronological order to form a time-series thermal ring, and similarly, the water level pressure zone data is arranged in chronological order to form a time pressure zone.

[0064] Among them, the time stamp is set based on the time synchronization function of the real-time data acquisition system to ensure that all collected data can be accurate to a specific time point, which is convenient for subsequent time series analysis and early warning processing. The time series thermal ring records the temperature change trends and patterns of various parts of the dam body over a period of time, and the time pressure belt shows the water level changes in the same period.

[0065] S202, collect real-time environmental data, and store the first work consumption random number (H) and the second work consumption random number (S) in the dynamic deformation module through periodic updates of real-time data. The time series thermal loop is updated in real time according to the changes of temperature data and the first work consumption random number (H), and the time pressure band is updated in real time according to the water level data and the second work consumption random number (S).

[0066] S203, based on historical data, preset temperature thresholds and water level thresholds, store the predicted temperature thresholds and water level thresholds in the dynamic deformation module, and when the monitored temperature exceeds the temperature threshold or the water level exceeds the water level threshold, the early warning mechanism in the dynamic deformation module is triggered.

[0067] Specifically, the warning information issued by the early warning mechanism includes the type, location, duration and response measures of the abnormality, and the information is quickly transmitted to the operating personnel through sound and light alarms and SMS notifications;

[0068] S204, according to step S201, the timestamp is stored in the dynamic deformation module, so that the device is equipped with an early warning lead time, and the number of actual abnormalities and warnings and the number of actual normals and false alarms are counted according to the early warning situation, and the proportion of warnings and the proportion of false alarms are calculated according to the statistical number of times, and the comprehensive accuracy is calculated by combining the proportion of warnings and the proportion of false alarms with the F1 score statistics.

[0069] Specifically, if the warning lead time is measured in hours, different lead time thresholds are set, for example: 24 hours, 48 ​​hours and 72 hours, and are set according to actual conditions.

[0070] The technical solutions in the above embodiments of the present application have at least the following technical effects or advantages:

[0071] By introducing the time dimension, the dynamic deformation module can identify abnormal situations earlier. Abnormal changes are not significant in the early stage, but will gradually accumulate over time and lead to serious consequences. The time-series thermal ring and time-pressure belt enable the dynamic deformation module to warn the safety status of the dam in advance, so that operators can pay more attention to it; at the same time, the time-series thermal ring and time-pressure belt can display the trend of temperature and water level changes, so that the dynamic deformation module can predict the status of the dam here according to the trend. The trend prediction capability enables operators to understand the status of the dam in time and deal with it.

[0072] Example 3: In Example 2, the time dimension is introduced and the visualization of time series data is realized. However, how to extract useful information from the time series data to predict abnormal situations? Based on the time series thermal ring and time pressure band in Example 2, a warning precursor ring and a critical pressure trajectory are proposed. By analyzing the abnormal precursors in the historical data, the accuracy and timeliness of the warning are improved.

[0073] Collect historical data, traverse the historical data in the time-series thermal loop, find out the temperature change characteristics of the dam body in the period before the abnormal situation is about to occur in the historical data, and the graphical representation formed by the temperature change characteristics of the dam body in the period before the abnormal situation is about to occur is called an early warning precursor loop; traverse the historical data in the time pressure zone, identify the rising trajectory and pressure changes presented by the water level changes in the period before the abnormal situation occurs, and the graphical representation formed by the rising trajectory and pressure changes is called a critical pressure trajectory; a period of time is the early warning lead time, by setting different levels of advance time thresholds, based on Example 2, the early warning lead time in this embodiment is greater than the early warning lead time in Example 2.

[0074] Through the pattern recognition algorithm in the dynamic deformation module, the collected real-time data is compared and matched with the predefined early warning precursor ring and critical pressure trajectory. In the process of comparing and matching the real-time data with the predefined early warning precursor ring and critical pressure trajectory, a recognition accuracy threshold is preset, that is, not less than 90%. The matching comparison result and the accuracy threshold are optimized by the confusion matrix method for the pattern recognition algorithm. Specifically, the pattern recognition algorithm and the confusion matrix method are clustering algorithms in the prior art and will not be repeated in this application.

[0075] When a warning precursor ring or critical pressure trajectory is identified, the dynamic deformation module sends out a warning signal and provides a warning analysis report at the same time. The warning analysis report includes the expected time, location, possible impact range and recommended response measures of the abnormality.

[0076] The technical solutions in the above embodiments of the present application have at least the following technical effects or advantages:

[0077] The addition of early warning precursor rings and critical pressure trajectories enables the dynamic deformation module to issue early warnings before abnormal situations occur, providing operators with sufficient response time, thereby improving the accuracy of early warnings and reducing false alarms and missed alarms.

[0078] Embodiment 4: Based on embodiment 3, the early warning precursor ring is further optimized by incorporating temperature change directional analysis and critical pressure trajectory.

[0079] According to the real-time data of the dam body temperature collected at the time point, the temperature values ​​at consecutive time points are compared to determine the direction of the temperature change trend. After determining the direction of the temperature change trend, for the consecutive temperature values, the difference between adjacent temperature values ​​is calculated, and the direction of the temperature change is judged according to the positive or negative difference. If the difference is positive, it means that the temperature rises within the time interval, and the positive temperature difference is quantified as the micro-motion in the direction of heating; if the difference is negative, it means that the temperature drops within the time interval, and the absolute value of the negative temperature difference is quantified as the micro-motion in the direction of cooling. The micro-motions in the same direction are summed to represent the cumulative change in this direction, and the micro-motions in different directions are summed to obtain the cumulative values ​​of the micro-motions in different directions.

[0080] Specifically, according to the accumulated value, the chart making software in the dynamic deformation module generates a chart of the directional early warning precursor ring with time as the horizontal axis and the accumulated value as the vertical axis.

[0081] Similarly, by collecting water level data of the dam body, the water level values ​​at consecutive time points are compared to determine the direction of the water level change trend. After determining the direction of the water level change trend, for consecutive water level values, the difference between adjacent water level values ​​is calculated, and the direction of the water level change is judged according to the positive or negative difference. A positive difference indicates that the water level rises within the time interval, and the positive water level difference is quantified as the micro-motion in the rising direction; a negative difference indicates that the water level drops within the time interval, and the absolute value of the negative water level difference is quantified as the micro-motion in the falling direction. The micro-motions in the same direction are summed to represent the cumulative change in this direction. The micro-motions in different directions are summed to obtain the cumulative values ​​of the micro-motions in different directions, and the critical pressure trajectory of the micro-motions is plotted with time as the horizontal axis and the cumulative value as the vertical axis.

[0082] When the directional warning precursor ring or the critical pressure trajectory of micro-momentum reaches the preset threshold, the dynamic deformation module automatically triggers the multi-dimensional warning mechanism through the preset threshold of historical data, including sound, light signal, and SMS notification.

[0083] The technical solutions in the above embodiments of the present application have at least the following technical effects or advantages:

[0084] By introducing directional warning precursors and micro-momentum critical pressure trajectories, the system can more accurately identify signs of impending abnormal situations and issue warning signals in advance. The accuracy and timeliness of the warnings are significantly improved, and false alarms and missed alarms are further reduced.

[0085] Embodiment 5: Based on Embodiment 4, a zoned warning sensitive area and a collaborative warning network are introduced to improve the accuracy and timeliness of the warning.

[0086] like Figure 3 As shown in the figure, the specific steps for dividing the warning sensitive areas are:

[0087] S301, dividing the hydropower station dam into multiple monitoring areas, and marking different monitoring areas as early warning sensitive areas of different degrees according to the structural characteristics and historical data of each monitoring area.

[0088] Specifically, the structural characteristics include dam type and foundation conditions, and the historical data include crack development and seepage records.

[0089] S302, adjust the data collection frequency according to the different levels of early warning sensitivity areas. For areas with high early warning sensitivity and frequent historical problems, increase the data collection frequency to capture more subtle changes; for relatively stable areas or areas with fewer problems, reduce the collection frequency.

[0090] Specifically, for areas with high warning sensitivity and frequent historical problems, the data collection frequency shall not be less than once an hour; for relatively stable areas or areas with fewer problems, the data collection frequency shall be reduced to once every 6 hours.

[0091] S303, establish a collaborative early warning model. Based on the historical data of dam body temperature and water level, use algorithms to build models and design collaborative early warning mechanisms. Specifically, the collaborative early warning mechanism refers to the establishment of an information sharing platform so that information from each monitoring area can be transmitted in real time. When the real-time monitoring data exceeds the preset threshold, the early warning mechanism is triggered. The early warning mechanism sends the early warning signal to the relevant areas and operators at the same time. When early warning signs appear in one or more areas, the various departments monitoring each area can communicate quickly and respond in a timely manner.

[0092] In some embodiments, in the safety monitoring center of the hydropower station dam, different monitoring areas of the dam body are displayed in real time on a large screen, and the timing thermal ring and time pressure belt of the dynamic deformation module are displayed in different monitoring areas. The staff can observe the conditions of different parts of the dam body in real time through the large screen. At the same time, the early warning precursor ring and the critical pressure trajectory can predict the potential safety hazards of the dam body in advance. The directional early warning precursor ring can combine the spatial position information to point out the direction of the spread of potential risks. The micro-momentum critical pressure trajectory can focus on tiny deformations and pressures, so that the staff can accurately detect abnormal situations and have sufficient response time. The establishment of a coordinated early warning model enables the dam body to integrate data from various areas, so that operators can accurately identify the specific location and trend of abnormal situations that are about to occur in the dam.

[0093] The technical solutions in the above embodiments of the present application have at least the following technical effects or advantages:

[0094] By zoning the early warning sensitive areas, the dam body is divided into different monitoring areas, so that the monitoring areas can independently reflect the condition of the dam body, and the operators can accurately find the specific location where the abnormal situation occurs. At the same time, the establishment of a collaborative early warning network enables the various monitoring areas to be linked, and the dynamic deformation module can comprehensively analyze the situation in each area and send detailed early warning reports to the operators, which improves the accuracy and timeliness of the early warning and reduces false alarms and missed alarms.

[0095] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for early warning of the operating status of hydropower station equipment, characterized in that: include: S101, establishing a three-dimensional model, scaling down the actual shape of the dam body and converting it into a three-dimensional model of a dynamic deformation module, wherein the surface of the dynamic deformation module is covered with grid points, and the displacement of the dam body is converted into the displacement of the grid points. An environmental parameter sensor is provided in the dynamic deformation module, and the environmental parameter sensor can receive data in real time; S102, collecting environmental data of the hydropower station dam, and calculating a first work consumption random number and a second work consumption random number according to the environmental data; S103, storing the first work consumption random number and the second work consumption random number in the dynamic deformation module, the environmental parameter sensor in the dynamic deformation module receives the first work consumption random number and the second work consumption random number, maps the value of the first work consumption random number to the color space to convert it into a thermal ring, and maps the value of the second work consumption random number to the strip to convert it into a water level pressure strip; S104, when the displacement size of the grid point is greater than the preset displacement threshold, the grid point is highlighted and an abnormal warning is issued. At the same time, the system automatically records the highlighted grid point as an abnormal point, wherein the first work consumption random number and the second work consumption random number can both affect the displacement of the grid point.

2. A method for early warning of the operating status of hydropower station equipment according to claim 1, characterized in that: Said Where σ0 represents the standard deviation of the dam body temperature at all times, h max Indicates the maximum working temperature of the dam body, h min Indicates the minimum working temperature of the dam body, h t represents the dam working temperature at time t, floor represents the rounding down operation, T represents all times; σ1 represents the standard deviation of the dam water level at all times, s max Indicates the maximum working water level of the dam, s min Indicates the minimum working water level of the dam, s t Represents the working water level of the dam at time t.

3. A method for early warning of the operating status of hydropower station equipment according to claim 1, characterized in that: The specific steps of converting the first work consumption random number into a thermal ring and the second work consumption random number into a water level pressure zone are as follows: A1. Determine the maximum and minimum values ​​of the random numbers consumed by the first work according to the formula of the random numbers consumed by the first work; determine the maximum and minimum values ​​of the random numbers consumed by the second work according to the formula of the random numbers consumed by the second work; A2, using a hue, saturation, and brightness model to map the maximum and minimum values ​​of the random numbers consumed by the first work and the maximum and minimum values ​​of the random numbers consumed by the second work; A3, selecting a hue range to represent the maximum and minimum values ​​of the random numbers consumed by the first task and the maximum and minimum values ​​of the random numbers consumed by the second task; A4. Normalize each value of the first work consumption random number and the second work consumption random number; A5. Map the normalized values ​​to the selected hue range, and use the graphics library to draw the thermal ring and water level pressure belt based on the mapped data.

4. A method for early warning of the operating status of hydropower station equipment according to claim 1, characterized in that: Specific steps to add a time module to the dynamic deformation module: S201, recording the current time information of the first work consumption random number and the second work consumption random number, the time information forms a timestamp and is stored in the dynamic deformation module, the thermal loop data in the dynamic deformation module is arranged in time sequence to form a time series thermal loop, and similarly, the water level pressure zone data is arranged in time sequence to form a time pressure zone; S202, updating the first work consumption random number and the second work consumption random number stored in the dynamic deformation module through the collected real-time environmental data, the time series thermal loop is updated in real time according to the changes of the temperature data and the first work consumption random number, and the time pressure band is updated in real time according to the water level data and the second work consumption random number; S203, according to historical data, preset temperature thresholds and water level thresholds, and store the preset temperature thresholds and water level thresholds in the dynamic deformation module, when the monitored temperature exceeds the temperature threshold or the water level exceeds the water level threshold, the early warning mechanism in the dynamic deformation module is triggered; S204, according to step S201, the timestamp is stored in the dynamic deformation module, so that the device is equipped with an early warning lead time, and the number of actual abnormalities and warnings and the number of actual normals and false alarms are counted according to the early warning situation, and the proportion of warnings and the proportion of false alarms are calculated according to the statistical number of times, and the comprehensive accuracy of the proportion of warnings and the proportion of false alarms is calculated through F1 score statistics.

5. A method for early warning of the operating status of hydropower station equipment according to claim 4, characterized in that: The early warning precursor loop is the historical data in the time series thermal loop, which shows the temperature variation characteristics of the dam body in the period before the abnormal situation is about to occur; The critical pressure trajectory is the rising trajectory and pressure change of the water level change in the historical data in the time pressure zone before the abnormal situation occurs.

6. A method for early warning of the operating status of hydropower station equipment according to claim 5, characterized in that: Steps to generate a directional warning precursor ring: B1. Collect the data of dam body temperature in the early warning precursor ring at the time point, compare the temperature values ​​at consecutive time points, and determine the direction of temperature change trend; B2. Based on the continuous temperature values, calculate the difference between adjacent temperature values, and determine the direction of temperature change according to the positive or negative value of the difference; B3. Sum the differences in the same direction to represent the cumulative value in this direction, and sum the differences in different directions to obtain the cumulative values ​​in different directions; B4. Based on the accumulated value, with time as the horizontal axis and the accumulated value as the vertical axis, the chart making software in the dynamic deformation module generates a chart of the directional early warning precursor ring using the accumulated value and time.

7. A method for early warning of the operating status of hydropower station equipment according to claim 6, characterized in that: If the difference is positive, it means that the temperature rises within the time interval, and the positive temperature difference is quantified as the micro-motion in the direction of temperature rise; if the difference is negative, it means that the temperature drops within the time interval, and the absolute value of the negative temperature difference is quantified as the micro-motion in the direction of temperature drop.

8. A method for early warning of the operating status of hydropower station equipment according to claim 5, characterized in that: Steps to generate micro-momentum critical pressure trajectory: C1. Collect the data of the dam body water level in the critical pressure trajectory at each time point, compare the water level values ​​at consecutive time points, and determine the direction of the water level change trend; C2. Based on the continuous water level values, calculate the difference between adjacent water level values, and determine the direction of water level change according to the positive or negative value of the difference; C3. Sum the differences in the same direction to represent the cumulative value in this direction, and sum the differences in different directions to obtain the cumulative values ​​in different directions; C4. Based on the accumulated value, draw the critical pressure trajectory of the micro-motion volume with time as the horizontal axis and the accumulated value as the vertical axis.

9. A method for early warning of the operating status of hydropower station equipment according to claim 8, characterized in that: If the difference is positive, it means that the water level rises within the time interval, and the positive water level difference is quantified as the micro-motion in the rising direction; if the difference is negative, it means that the water level drops within the time interval, and the absolute value of the negative water level difference is quantified as the micro-motion in the falling direction.

10. A method for early warning of the operating status of hydropower station equipment according to claim 1, characterized in that: Specific steps for dividing early warning sensitive areas: S301, dividing the hydropower station dam into multiple monitoring areas, and marking different monitoring areas as early warning sensitive areas of different degrees according to the structural characteristics and historical data of each monitoring area; S302, adjusting the data collection frequency according to different levels of early warning sensitivity areas. For areas with high early warning sensitivity and frequent historical problems, the data collection frequency is increased to capture more subtle changes; for relatively stable areas or areas with fewer problems, the collection frequency is reduced; S303, establish a collaborative early warning model, use algorithms to build models based on historical data on dam temperature and water level, and design a collaborative early warning mechanism.

Images