CN115880101B - A water conservancy data management system based on big data - Google Patents

Abstract

The present invention relates to the field of hydrological monitoring, in particular to a water conservancy data management system based on big data, which obtains predicted data and actual data through a data acquisition module, and obtains dangerous water levels from the data provided by the data acquisition module, and stores them according to the big data The data provided by the module establishes the first image and the second image, the parameter fitting module performs linear fitting according to the scatter diagram to obtain the first parameter and the second parameter, the correction parameter setting module provides the correction parameters, and then the calculation module calculates the The parameters, the second parameter and the correction parameter calculate the data to obtain the second water level, and then the comparison module judges the degree of danger to realize the water level danger warning, and finally the data processing module completes the big data storage module through screening and sorting. The invention solves the problem that delaying the timeliness of water conservancy data leads to incomplete work and reduces work efficiency.

Description

A water conservancy data management system based on big data

technical field

The invention relates to the field of hydrological monitoring, in particular to a water conservancy data management system based on big data.

Background technique

With the rapid development of information technology, more and more water conservancy information infrastructure and application systems have been applied to the construction and management of water conservancy projects, water administrative business disposal, data monitoring of hydrological systems and other fields. Water conservancy IoT equipment The uploaded data is getting bigger and bigger. At the same time, with the explosive growth of the amount of information on the entire Internet, big data technology has emerged as the times require. Big data technology has been introduced into the water conservancy industry, and it is used as an important tool for water conservancy informatization and intelligent construction. The basic technology has become an inevitable trend.

The patent document with the publication number CN112969051A discloses a water conservancy engineering management system based on big data, which can adjust the angle of the camera according to the monitoring coefficient, and at the same time, reasonably select the corresponding management personnel for processing according to the allocation value.

However, the camera collects real-time information. When the water conservancy data is abnormal, the corresponding management personnel cannot handle it in time. Delaying the timeliness of the water conservancy data will lead to incomplete work and reduce work efficiency.

Contents of the invention

Therefore, the present invention provides a water conservancy data management system based on big data, which can solve the problem that delaying the timeliness of water conservancy data will lead to incomplete work and reduce work efficiency.

In order to achieve the above object, the present invention provides a water conservancy data management system based on big data, including:

The data acquisition module is used to acquire the first predicted average temperature T3, the first predicted precipitation P3, the second actual average temperature T2, the second actual precipitation P2 and the second actual maximum water level Z2 of the target river section;

The big data storage module is used to store the historical actual average temperature T1 _i , the historical actual precipitation P1 _i , the historical actual maximum water level Z1 _i , and the historical forecast for each historical date of the target river section in the historical period and corresponding to that day. The maximum water level Z3 _i and the historical water level correction parameter n1 _i , where each historical date of the target river section includes the date of the accident in the target river section, where 1≤i≤N, N is a positive integer, and N is the date before the current day in the historical period The total number of days, n1 _N is set as the first water level correction parameter;

The dangerous water level setting module is connected with the big data storage module, and is used to extract the minimum value from the historical actual maximum water level Z1 _i corresponding to the accident date of all target river sections and set it as the dangerous water level Z0;

The data extraction module is connected with the data acquisition module and the big data storage module respectively, and each date is set as the first date group when the first predicted average temperature T3 and the historical actual average temperature T1 _i are equal, and the When the first predicted precipitation P3 and the historical actual precipitation P1 _i are equal, each date is set as the second date group to extract the historical actual precipitation P1 _i and the historical actual precipitation in the first date group. The data of the maximum water level Z1 _i , and the data used to extract the historical actual average temperature T1 _i and the historical actual maximum water level Z1 _i in the second date group;

An image creation module, connected to the data extraction module, to establish a first image according to the data relationship between the historical actual precipitation P1 _i and the historical actual maximum water level Z1 _i in the first date group, and, It is used to establish a second image according to the data relationship between the historical actual average temperature T1 _i and the historical actual maximum water level Z1 _i in the second date group;

A parameter fitting module, connected to the image creation module, for performing linear fitting according to the first image to obtain the first parameter k1, and for performing linear fitting according to the second image to obtain the second parameter k2 ;

The calculation module is connected with the data acquisition module, the big data storage module and the parameter fitting module respectively, and is used to calculate the temperature according to the first predicted average temperature T3, the first predicted precipitation P3, the first predicted precipitation A water level correction parameter n1 _N , the first parameter k1 and the second parameter k2 are calculated to obtain the first predicted maximum water level Z3;

A comparison module, connected to the dangerous water level setting module and the calculation module respectively, for comparing the size relationship between the first predicted maximum water level Z3 and the dangerous water level Z0, and judging the first predicted maximum water level Z3 according to the size relationship degree of danger;

A correction parameter setting module, connected to the big data storage module, used to calculate the second water level correction parameter according to the historical actual maximum water level Z1 _i , the historical predicted maximum water level Z3 _i , and the second actual maximum water level Z2 n1 _N+1 ;

The data processing module is respectively connected with the comparison module, the data acquisition module, the calculation module, the correction parameter setting module and the big data storage module, so as to reduce the risk according to the first predicted maximum water level Z3 The first predicted average temperature T3, the first predicted precipitation P3, the first predicted maximum water level Z3, the second water level correction parameter n1 _N+1 , the second actual average temperature T2, the second The actual precipitation P2 and the second actual maximum water level Z2 are stored or deleted.

Further, the data acquisition module includes a prediction unit and a detection unit, and the prediction unit and the detection unit are independent of each other;

The prediction unit is used to obtain the first predicted average temperature T3 and the first predicted precipitation P3 of the target river section;

The detection unit is used to acquire the second actual average temperature T2, the second actual precipitation P2 and the second actual maximum water level Z2.

Further, the big data storage module includes a first storage unit and a second storage unit, the first storage unit and the second storage unit are independent of each other, and are used to map each historical date in the historical period to the historical data of the current day The actual average temperature T1 _i , the historical actual precipitation P1 _i , the historical actual maximum water level Z1 _i , the historical predicted maximum water level Z3 _i and the historical water level correction parameter n1 _i are set as several independent data groups, One-to-one correspondence with each data group with the date as the index;

The first storage unit is used to store each historical date and the corresponding data sets when no accident occurred in the target river section within the historical period;

The second storage unit is used to store each historical date of an accident in the target river section within the historical period and the corresponding data groups.

Further, the data extraction module includes a first data extraction unit and a second data extraction unit, the first data extraction unit and the second data extraction unit are independent of each other, the first data extraction unit is connected with the prediction unit, the The first storage unit is connected to the second storage unit, and the second data extraction unit is respectively connected to the prediction unit, the first storage unit and the second storage unit;

The first data extraction unit is used to extract all the data groups of the first date group from the first storage unit and the second storage unit according to the value of the first predicted average temperature T3 , and set all the data groups of the extracted first date group as the first database, and extract the historical actual precipitation P1 _i and the historical actual maximum water level Z1 _i from the first database data, and the data of the extracted historical actual precipitation P1 _i and the historical actual maximum water level Z1 _i are set as the first data group to be mapped;

The second data extraction unit is used to extract all the data groups of the second date group from the first storage unit and the second storage unit according to the value of the first predicted precipitation P3 , and set all the data groups of the extracted second date group as the second database, and extract the historical actual average temperature T1 _i and the historical actual maximum water level Z1 _i from the second database data, and the extracted data of the historical actual average temperature T1 _i and the historical actual maximum water level Z1 _i are set as the second data group to be mapped.

Further, the image creation module includes a first image creation unit and a second image creation unit, the first image creation unit and the second image creation unit are independent of each other, the first image creation unit and the first data extraction unit connected, the second image creation unit is connected to the second data extraction unit;

The first image creation unit is used to arrange the historical actual precipitation P1 _i from low to high according to the first data set to be mapped, and establish a precipitation-water level scatter diagram as the first image;

The second image creation unit is used to arrange the historical actual average temperature T1 _i from low to high according to the second data set to be mapped, and create a scatter diagram of average temperature-water level as the second image.

Further, the parameter fitting module includes a first parameter fitting unit and a second parameter fitting unit, the first parameter fitting unit and the second parameter fitting unit are independent of each other, and the first parameter fitting unit and the The first image creation unit is connected, and the second parameter fitting unit is connected to the second image creation unit;

The first parameter fitting unit is used to perform linear fitting according to the first image, obtain the slope of the linear image after fitting with the first image as the first slope, and set the value of the first slope as the first slope. a parameter k1;

The second parameter fitting unit is used to perform linear fitting according to the second image, obtain the slope of the linear image after fitting with the second image as the second slope, and set the value of the second slope as the first Two parameters k2.

Further, the calculation module is respectively connected with the prediction unit, the first parameter fitting unit, the second parameter fitting unit, the first storage unit and the second storage unit, for The first predicted average temperature T3, the first predicted precipitation P3, the first parameter k1, the second parameter k2 and the first water level correction parameter n1 _N are calculated according to the formula (P3×k1)+ (T3×k2)+n1 _N =Z3 is calculated to obtain the first predicted maximum water level Z3.

Further, the comparison module is respectively connected with the dangerous water level setting module and the calculation module to compare the magnitude relationship between the dangerous water level Z0 and the first predicted maximum water level Z3, and judge the first predicted maximum water level Z3 according to the magnitude relationship. the degree of danger of a water level;

When the comparison module determines that Z3≥Z0, the first water level has the risk of causing an accident, and the comparison module issues a danger warning;

When the comparison module determines that Z3<Z0, the first water level does not have the risk of causing an accident.

Further, the correction parameter setting module is connected with the first storage unit and the second storage unit, and is used to set the historical actual maximum water level Z1 _i , the historical predicted maximum water level Z3 _i , The second actual maximum water level Z2 and the second predicted maximum water level Z3 _N+1 are according to the formula

The second water level correction parameter n1 _N+1 is calculated to obtain, wherein 1≤i≤N, N is a positive integer, and N is the total number of days before the current day in the historical period.

Further, the data processing module is respectively connected with the prediction unit, the detection unit, the first storage unit, the second storage unit, the calculation module and the correction parameter setting module;

Delete the first predicted average temperature T3 and the first predicted precipitation P3;

When Z3≥Z0, set the first predicted maximum water level Z3 as the historical predicted maximum water level Z3 _N+1 , set the second actual average temperature T2 as the historical actual average temperature T1 _{N+1 , and set the second actual average temperature T1 N+1} 2. The actual precipitation P2 is set as the historical actual precipitation P1 _N+1 , the second actual maximum water level Z2 is set as the historical actual maximum water level Z1 _N+1 , and the historical predicted maximum water level Z3 _N+1 , historical actual average Air temperature T1 _N+1 , historical actual precipitation P1 _N+1 , historical actual maximum water level Z1 _N+1 and the first water level correction parameter n1 _N are stored in the first storage unit;

When Z3<Z0, set the first predicted maximum water level Z3 as the historical predicted maximum water level Z3 _N+1 , set the second actual average temperature T2 as the historical actual average temperature T1 _{N+1 , set the second actual average temperature T1 N+1} 2. The actual precipitation P2 is set as the historical actual precipitation P1 _N+1 , the second actual maximum water level Z2 is set as the historical actual maximum water level Z1 _N+1 , and the historical predicted maximum water level Z3 _N+1 , historical actual average Air temperature T1 _N+1 , historical actual precipitation P1 _N+1 , historical actual maximum water level Z1 _N+1 and the second water level correction parameter n1 _N+1 are stored in the second storage unit.

Compared with the prior art, the beneficial effect of the present invention is that the data information managed by the present invention is divided into predicted data and actual data in time, wherein the predicted data includes the first predicted average temperature T3, the The first predicted precipitation P3, the first predicted maximum water level Z3 and the historical predicted maximum water level Z3 _i , the actual data include the second actual average temperature T2, the second actual precipitation P2, the second actual The maximum water level Z2, the historical actual average temperature T1 _i , the historical actual precipitation P1 _i , the historical actual maximum water level Z1 _i and the historical water level correction parameter n1 _i , where the predicted data are mostly used to speculate the first predicted maximum The water level Z3 is used to obtain early warning of danger and deal with it, and most of the actual data is classified and stored by the data processing module for extraction and utilization. With the increase of the data base in the big data storage module, the calculated value based on these The results will also become more and more accurate with time. The whole system forms a closed loop from data storage to calculation to feedback adjustment to re-storage. With the accumulation of data, the accuracy and reliability will increase, which can solve the delay. The timeliness of water conservancy data leads to incomplete work, which reduces work efficiency.

In particular, the historical actual average temperature T1 _i , the historical actual precipitation P1 _i , the historical actual maximum water level Z1 _i , the historical predicted maximum water level Z3 _i and the historical water level correction parameters generated on the same day n1 _i are unified and integrated, and indexed by date to facilitate information screening and search, further increasing work efficiency, dividing the big data storage module into two independent storage units, the first storage unit and the second storage unit The unit is to isolate important data and speed up the extraction.

In particular, some scattered data sets obtained through multiple observations or experiments on relevant quantities are not only inconvenient to handle, but also usually cannot accurately and fully reflect their inherent laws. In order to obtain the inherent laws between the data or use the current data to To predict the expected data, linear fitting is generally used. Linear fitting is a form of curve fitting. Let x and y be observed quantities, and y is a function of x, that is, y=f(x; b), curve fitting is to seek the best estimated value of parameter b through the observed values of x and y, that is, to seek the best theoretical curve y=f(x; b), when the function y=f(x; b) When it is a linear function about the parameter b, this curve fitting is called linear fitting, the linear function image obtained by linear fitting, the slope in the image is numerically equal to the rate of change between the influencing factors, the present invention adopts In the way of big data, linear fitting is performed in the scatter diagram generated by the massive data sets provided by the first storage unit and the second storage unit, and the degree of fitting will increase with the increase of the amount of data, and then The obtained first parameter k1 and the second parameter k2 will also become more accurate as the amount of data increases, which improves the accuracy of subsequent calculation results.

Description of drawings

Fig. 1 is a schematic structural diagram of a water conservancy data management system based on big data provided by an embodiment of the present invention;

Fig. 2 is a schematic structural diagram of a big data storage module of a water conservancy data management system based on big data provided by an embodiment of the present invention;

Fig. 3 is a schematic structural diagram of a data extraction module of a water conservancy data management system based on big data provided by an embodiment of the present invention;

4 is a schematic structural diagram of an image building module of a water conservancy data management system based on big data provided by an embodiment of the present invention;

Fig. 5 is a schematic structural diagram of a parameter fitting module of a water conservancy data management system based on big data provided by an embodiment of the present invention.

Detailed ways

In order to make the objects and advantages of the present invention clearer, the present invention will be further described below in conjunction with the examples; it should be understood that the specific examples described here are only for explaining the present invention, and are not intended to limit the present invention.

Preferred embodiments of the present invention are described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principle of the present invention, and are not intended to limit the protection scope of the present invention.

It should be noted that, in the description of the present invention, terms such as "upper", "lower", "left", "right", "inner", "outer" and other indicated directions or positional relationships are based on the terms shown in the accompanying drawings. The direction or positional relationship shown is only for convenience of description, and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention.

In addition, it should be noted that, in the description of the present invention, unless otherwise clearly stipulated and limited, the terms "installation", "connection" and "connection" should be understood in a broad sense, for example, it can be a fixed connection or a It is a detachable connection or an integral connection; it may be a mechanical connection or an electrical connection; it may be a direct connection or an indirect connection through an intermediary, and it may be the internal communication of two components. Those skilled in the art can understand the specific meanings of the above terms in the present invention according to specific situations.

Referring to Fig. 1, the water conservancy data management system based on big data provided by the embodiment of the present invention includes:

The data acquisition module 101 is used to acquire the first predicted average temperature T3, the first predicted precipitation P3, the second actual average temperature T2, the second actual precipitation P2 and the second actual maximum water level Z2 of the target river section;

The big data storage module 102 is used to store the historical actual average temperature T1 _i , historical actual precipitation P1 _i , historical actual maximum water level Z1 _i , and historical Predict the maximum water level Z3 _i and historical water level correction parameters n1 _i , where each historical date of the target river section includes the accident date of the target river section, where 1≤i≤N, N is a positive integer, and N is the second in the historical period For the total number of days before, n1 _N is set as the first water level correction parameter;

The dangerous water level setting module 103 is connected with the big data storage module, and is used to extract the minimum value from the historical actual maximum water level Z1 _i corresponding to the accident date of all target river sections and set it as the dangerous water level Z0;

The data extraction module 104 is connected with the data acquisition module and the big data storage module respectively, and when the first predicted average temperature T3 and the historical actual average temperature T1 _i are equal, each date is set as the first date group, When the first predicted precipitation P3 and the historical actual precipitation P1 _i are equal, each date is set as a second date group to extract the historical actual precipitation P1 i and the historical actual precipitation P1 _i in the first date group. The data of the actual maximum water level Z1 _i , and the data used to extract the historical actual average temperature T1 _i and the historical actual maximum water level Z1 _i in the second date group;

An image creation module 105, connected to the data extraction module, for establishing a first image according to the data relationship between the historical actual precipitation P1 _i and the historical actual maximum water level Z1 _i in the first date group, and , for establishing a second image according to the data relationship between the historical actual average temperature T1 _i and the historical actual maximum water level Z1 _i in the second date group;

A parameter fitting module 106, connected to the image creation module, for performing linear fitting according to the first image to obtain the first parameter k1, and for performing linear fitting according to the second image to obtain the second parameter k2;

The computing module 107 is connected to the data acquisition module, the big data storage module and the parameter fitting module respectively, and is used to calculate the temperature according to the first predicted average temperature T3, the first predicted precipitation P3, the The first water level correction parameter n1 _N , the first parameter k1 and the second parameter k2 are calculated to obtain the first predicted maximum water level Z3;

The comparison module 108 is connected with the dangerous water level setting module and the calculation module respectively, to compare the size relationship between the first predicted maximum water level Z3 and the dangerous water level Z0, and judge the first predicted maximum water level according to the size relationship The degree of danger of Z3;

The correction parameter setting module 109 is connected with the big data storage module, and is used to calculate and obtain the second water level correction according to the historical actual maximum water level Z1 _i , the historical predicted maximum water level Z3 _i , and the second actual maximum water level Z2 parameter n1 _N+1 ;

The data processing module 110 is respectively connected with the comparison module, the data acquisition module, the calculation module, the correction parameter setting module and the big data storage module, and is used to predict the degree of danger of the maximum water level Z3 according to the first The first predicted average temperature T3, the first predicted precipitation P3, the first predicted maximum water level Z3, the second water level correction parameter n1 _N+1 , the second actual average temperature T2, the first predicted The second actual precipitation P2 and the second actual maximum water level Z2 are stored or deleted.

Specifically, the first predicted average temperature T3, the first predicted precipitation P3 and the first predicted maximum water level Z3 represent the predicted average temperature, precipitation and maximum water level data for tomorrow, and the second actual average The air temperature T2, the second actual precipitation P2 and the second actual maximum water level Z2 represent actually measured tomorrow's average temperature, precipitation and maximum water level data.

Specifically, the data information managed by the present invention is divided into predicted data and actual data in time, wherein the predicted data includes the first predicted average temperature T3, the first predicted precipitation P3, the first predicted precipitation A predicted maximum water level Z3 and the historical predicted maximum water level Z3 _i , the actual data includes the second actual average temperature T2, the second actual precipitation P2, the second actual maximum water level Z2, and the historical actual average temperature T1 _i , historical actual precipitation P1 _i , historical actual maximum water level Z1 _i , and historical water level correction parameters n1 _i , where the predicted data are mostly used to speculate the first predicted maximum water level Z3 based on parameters and formulas to obtain early warning of danger and In response, most of the actual data is categorized and stored by the data processing module to be extracted and utilized. With the increase of the data base in the big data storage module, the results calculated based on these values will also increase with time. Accurate, the entire system data forms a closed loop from storage to calculation to feedback adjustment to re-storage. With the accumulation of data, the accuracy and reliability will increase, which can solve the problem of incomplete work caused by delays in the timeliness of water conservancy data thereby reducing work efficiency.

Specifically, the data acquisition module includes a prediction unit and a detection unit, and the prediction unit and the detection unit are independent of each other;

The prediction unit is used to obtain the first predicted average temperature T3 and the first predicted precipitation P3 of the target river section;

The detection unit is used to acquire the second actual average temperature T2, the second actual precipitation P2 and the second actual maximum water level Z2.

Specifically, the first predicted average temperature T3 and the first predicted precipitation P3 obtained by the prediction unit are used to calculate the predicted water level Z, and the second actual average temperature T2 obtained by the detection unit , the second actual precipitation P2 and the second actual maximum water level Z2 are used to enrich the storage content of the big data storage module.

Specifically, the data acquired by the predicting unit and the data acquired by the detecting unit respectively implement different functions, and acquiring separately can improve the efficiency of data sorting.

Specifically, as shown in FIG. 2, the big data storage module includes a first storage unit and a second storage unit, and the first storage unit and the second storage unit are independent of each other, so as to store each The historical date corresponds to the historical actual average temperature T1 _i , the historical actual precipitation P1 _i , the historical actual maximum water level Z1 _i , the historical predicted maximum water level Z3 _i and the historical water level correction parameter n1 _i set It is a number of independent data groups, and the date is used as the index to correspond to each data group one by one;

The first storage unit is used to store each historical date and the corresponding data sets when no accident occurred in the target river section within the historical period;

The second storage unit is used to store each historical date of an accident in the target river section within the historical period and the corresponding data groups.

Specifically, the value range of i is that i is greater than or equal to 1 and less than or equal to N, and N is the number of days before the current day. The historical actual average temperature T1 _i and the historical actual precipitation P1 generated on the same day _i . The historical actual maximum water level Z1 _i , the historical predicted maximum water level Z3 _i and the historical water level correction parameter n1 _i are unified and integrated, and are indexed by date to facilitate information screening and searching, further increasing work efficiency.

Specifically, the purpose of dividing the big data storage module into two mutually independent units, the first storage unit and the second storage unit, is to separate important data and speed up extraction.

Specifically, referring to Fig. 3, the data extraction module includes a first data extraction unit and a second data extraction unit, the first data extraction unit and the second data extraction unit are independent of each other, and the first data extraction unit respectively connected to the prediction unit, the first storage unit and the second storage unit, and the second data extraction unit is respectively connected to the prediction unit, the first storage unit and the second storage unit;

The first data extraction unit is used to extract all the data groups of the first date group from the first storage unit and the second storage unit according to the value of the first predicted average temperature T3 , and set all the data groups of the extracted first date group as the first database, and extract the historical actual precipitation P1 _i and the historical actual maximum water level Z1 _i from the first database data, and the data of the extracted historical actual precipitation P1 _i and the historical actual maximum water level Z1 _i are set as the first data group to be mapped;

The second data extraction unit is used to extract all the data groups of the second date group from the first storage unit and the second storage unit according to the value of the first predicted precipitation P3 , and set all the data groups of the extracted second date group as the second database, and extract the historical actual average temperature T1 _i and the historical actual maximum water level Z1 _i from the second database data, and the extracted data of the historical actual average temperature T1 _i and the historical actual maximum water level Z1 _i are set as the second data group to be mapped.

Specifically, the first data extraction unit and the second data extraction unit adopt the idea of the control variable method. Based on the huge data information in big data, a certain parameter can be controlled to a fixed value, so that the parameter can be excluded. For the influence effect of the overall data, the influence relationship between the data groups can be reflected more accurately, and the accuracy of the system is improved.

Specifically, referring to Fig. 4, the image building module includes a first image building unit and a second image building unit, the first image building unit and the second image building unit are independent of each other, and the first image building unit connected to the first data extraction unit, and the second image creation unit is connected to the second data extraction unit;

The first image creation unit is used to arrange the historical actual precipitation P1 _i from low to high according to the first data set to be mapped, and establish a precipitation-water level scatter diagram as the first image;

The second image creation unit is used to arrange the historical actual average temperature T1 _i from low to high according to the second data set to be mapped, and create a scatter diagram of average temperature-water level as the second image.

Specifically, the purpose of establishing a scatter diagram according to the historical precipitation and the historical temperature from low to high, rather than according to time order, is to make the trend of the scatter distribution in the graph linear, which is convenient for the next parameter simulation. combined operation.

Specifically, the scatter diagram generated by the massive data sets provided by the first storage unit and the second storage unit will further reflect its linear characteristics as the cardinality increases, which is conducive to reducing errors and increasing data precision.

Specifically, as shown in FIG. 5, the parameter fitting module includes a first parameter fitting unit and a second parameter fitting unit. The first parameter fitting unit and the second parameter fitting unit are independent of each other. A parameter fitting unit is connected to the first image creation unit, and a second parameter fitting unit is connected to the second image creation unit;

The first parameter fitting unit is used to perform linear fitting according to the first image, obtain the slope of the linear image after fitting with the first image as the first slope, and set the value of the first slope as the first slope. a parameter k1;

The second parameter fitting unit is used to perform linear fitting according to the second image, obtain the slope of the linear image after fitting with the second image as the second slope, and set the value of the second slope as the first Two parameters k2.

Specifically, some scattered data sets obtained through multiple observations or experiments on related quantities are not only inconvenient to deal with, but also cannot accurately and fully reflect their inherent laws. In order to obtain the inherent laws between the data or use the current Data is used to predict the expected data. Generally, linear fitting is used. Linear fitting is a form of curve fitting. Let x and y be observed quantities, and y is a function of x, that is, y=f( x; b), curve fitting is to seek the best estimated value of parameter b through the observed values of x and y, that is, to seek the best theoretical curve y=f(x; b), when the function y=f(x; When b) is a linear function about parameter b, this kind of curve fitting is called linear fitting.

Specifically, for the linear function image obtained by linear fitting, the slope in the image is numerically equal to the rate of change between the influencing factors. Linear fitting is performed in the scatter diagram generated by the massive data set provided by the second storage unit, and the fitting degree will increase with the increase of the data volume, and the first parameter k1 and the second parameter k2 obtained thereupon are also It will become more accurate as the amount of data increases, improving the accuracy of subsequent calculation results.

Specifically, the calculation module is respectively connected to the prediction unit, the first parameter fitting unit, the second parameter fitting unit, the first storage unit, and the second storage unit, and is used to The first predicted average temperature T3, the first predicted precipitation P3, the first parameter k1, the second parameter k2 and the first water level correction parameter n1 _N are calculated according to the formula (P3×k1) +(T3×k2)+n1 _N =Z3 is calculated to obtain the first predicted maximum water level Z3.

Specifically, the acquisition of the correction parameters is obtained by calculating the historical actual maximum water level Z1 _i and the historical predicted maximum water level Z3 _i , so as to adjust the first parameter k1 and the second parameter k2 to the first On the basis of the influence of the predicted maximum water level Z3, the value of the first predicted maximum water level Z3 is further refined to increase the reliability of the system.

Specifically, the comparison module is respectively connected with the dangerous water level setting module and the calculation module, and is used to compare the size relationship between the dangerous water level Z0 and the first predicted maximum water level Z3, and judge according to the size relationship the degree of danger of the first water level;

When the comparison module determines that Z3≥Z0, the first water level has the risk of causing an accident, and the comparison module issues a danger warning;

When the comparison module determines that Z3<Z0, the first water level does not have the risk of causing an accident.

Specifically, the dangerous water level Z0 is in a state of real-time update rather than a fixed value, and the minimum value is extracted from the historical actual maximum water level Z1 _i corresponding to the accident date of all target river sections and set as the dangerous water level The purpose of Z0 is to minimize the possibility of accidents in the target river section and increase the real-time reliability of the system.

Specifically, the degree of danger of the first water level can be judged according to the comparison result of the comparison module, which saves calculation steps, is simple and fast, and optimizes the implementation of the system.

Specifically, the correction parameter setting module is connected with the first storage unit and the second storage unit to set the historical actual maximum water level Z1 _i , the historical predicted maximum water level Z3 _i , the second actual maximum water level Z2, the second predicted maximum water level Z3 _N+1 according to the formula

The second water level correction parameter n1 _N+1 is calculated to obtain, wherein 1≤i≤N, N is a positive integer, and N is the total number of days before the current day in the historical period.

Specifically, the newly generated first water level correction parameter n1 _N is the sum of all historical actual maximum water levels Z1 _i minus the sum of all historical predicted maximum water levels Z3 _i N days ago Find the total difference between the historical actual maximum water level Z1 _i and the historical predicted maximum water level Z3 _i before N days, set the total difference as the first difference, and the first difference includes the calculation data of N days , the difference obtained by subtracting the second predicted maximum water level Z3 _N+1 in the historical predicted maximum water level Z3 _i from the second actual maximum water level Z2 is set as the second difference, and only one day is included in the second difference The calculation data of the first difference and the second difference are divided by the total number of days N+1 days, and the obtained result is the newly generated first water level correction parameter n1 _N .

Specifically, the first water level correction parameter n1 _N will change with the continuous expansion of data in the first storage unit and the second storage unit, so that the first water level correction parameter n1 _N can be changed with Accurate with the increase of the data base, improve the correction accuracy.

Specifically, the data processing module is respectively connected to the prediction unit, the detection unit, the first storage unit, the second storage unit, the calculation module and the correction parameter setting module;

Delete the first predicted average temperature T3 and the first predicted precipitation P3;

When Z3≥Z0, set the first predicted maximum water level Z3 as the historical predicted maximum water level Z3 _N+1 , set the second actual average temperature T2 as the historical actual average temperature T1 _{N+1 , and set the second actual average temperature T1 N+1} 2. The actual precipitation P2 is set as the historical actual precipitation P1 _N+1 , the second actual maximum water level Z2 is set as the historical actual maximum water level Z1 _N+1 , and the historical predicted maximum water level Z3 _N+1 , historical actual average Air temperature T1 _N+1 , historical actual precipitation P1 _N+1 , historical actual maximum water level Z1 _N+1 and the first water level correction parameter n1 _N are stored in the first storage unit;

When Z3<Z0, set the first predicted maximum water level Z3 as the historical predicted maximum water level Z3 _N+1 , set the second actual average temperature T2 as the historical actual average temperature T1 _{N+1 , set the second actual average temperature T1 N+1} 2. The actual precipitation P2 is set as the historical actual precipitation P1 _N+1 , the second actual maximum water level Z2 is set as the historical actual maximum water level Z1 _N+1 , and the historical predicted maximum water level Z3 _N+1 , historical actual average Air temperature T1 _N+1 , historical actual precipitation P1 _N+1 , historical actual maximum water level Z1 _N+1 and the second water level correction parameter n1 _N+1 are stored in the second storage unit.

Specifically, the purpose of deleting the first predicted average temperature T3 and the first predicted precipitation P3 is to simplify the data management space, clean up the data that has no application value in time, save space, and speed up the operation of the system. According to the The size relationship between the dangerous water level Z0 and the first predicted maximum water level Z3 classifies data to facilitate faster extraction of target data and improve the accuracy of data management.

So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings, but those skilled in the art will easily understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to related technical features, and the technical solutions after these changes or substitutions will all fall within the protection scope of the present invention.

The above descriptions are only preferred embodiments of the present invention, and are not intended to limit the present invention; for those skilled in the art, the present invention may have various modifications and changes. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims (10)

1. A big data based water conservancy data management system, comprising:

the data acquisition module is used for acquiring a first predicted average air temperature T3, a first predicted precipitation amount P3, a second actual average air temperature T2, a second actual precipitation amount P2 and a second actual maximum water level Z2 of the target river reach;

the big data storage module is used for storing each historical date of the target river reach in the historical period and the actual average temperature T1 of the current day corresponding to each historical date _i Historical actual precipitation P1 _i Historical actual maximum water level Z1 _i Historical predicted maximum water level Z3 _i And a historical water level correction parameter n1 _i Wherein each historical date of the target river reach comprises the accident date of the target river reach, i is more than or equal to 1 and less than or equal to N, N is a positive integer, N is the total number of days before the current day in the historical period, and N1 is calculated _N Setting the first water level correction parameter;

the dangerous water level setting module is connected with the big data storage module and is used for setting the historical actual maximum water level Z1 corresponding to the accident date of all the target river reach _i The minimum value is extracted and set as a dangerous water level Z0;

the data extraction module is respectively connected with the data acquisition module and the big data storage module and used for obtaining the first predicted average air temperature T3 and the historical actual average air temperature T1 _i Setting each date as a first date group when the first predicted precipitation amount P3 and the historical actual precipitation amount P1 are equal to each other _i Each date is set as a second date group when the actual precipitation amount P1 is equal to the first date group _i And the historic actual maximum water level Z1 _i And to extract said historical actual average air temperature T1 in the second date group _i And the historic actual maximum water level Z1 _i Data of (2);

the image establishing module is connected with the data extracting module and is used for carrying out the data extraction according to the history in the first date groupActual precipitation P1 _i And the historic actual maximum water level Z1 _i A first image is established according to the data relation of the historical actual average temperature T1 in the second date group _i And the historic actual maximum water level Z1 _i Establishing a second image;

the parameter fitting module is connected with the image building module and used for performing linear fitting according to the first image to obtain a first parameter k1 and performing linear fitting according to the second image to obtain a second parameter k2;

the calculation module is respectively connected with the data acquisition module, the big data storage module and the parameter fitting module and is used for correcting the parameter n1 according to the first predicted average air temperature T3, the first predicted precipitation P3 and the first water level _N Calculating the first parameter k1 and the second parameter k2 to obtain a first predicted maximum water level Z3;

the comparison module is respectively connected with the dangerous water level setting module and the calculation module, and is used for comparing the magnitude relation between the first predicted maximum water level Z3 and the dangerous water level Z0 and judging the dangerous degree of the first predicted maximum water level Z3 according to the magnitude relation;

the correction parameter setting module is connected with the big data storage module and is used for setting the historical actual maximum water level Z1 according to the historical actual maximum water level _i Said historic predicted maximum water level Z3 _i Calculating the second actual maximum water level Z2 to obtain a second water level correction parameter n1 _N+1 ；

The data processing module is respectively connected with the comparison module, the data acquisition module, the calculation module, the correction parameter setting module and the big data storage module and is used for correcting the first predicted average air temperature T3, the first predicted precipitation P3, the first predicted maximum water level Z3 and the second water level correction parameter n1 according to the risk degree of the first predicted maximum water level Z3 _N+1 And the second actual average air temperature T2, the second actual precipitation amount P2 and the second actual maximum water level Z2 are stored or deleted.

2. The big data-based water conservancy data management system according to claim 1, wherein the data acquisition module comprises a prediction unit and a detection unit, and the prediction unit and the detection unit are mutually independent;

the prediction unit is used for obtaining the first predicted average air temperature T3 and the first predicted precipitation P3 of the target river reach;

the detection unit is used for acquiring the second actual average air temperature T2, the second actual precipitation amount P2 and the second actual maximum water level Z2.

3. The big data based water conservancy data management system as set forth in claim 2, wherein the big data storage module comprises a first storage unit and a second storage unit, the first storage unit and the second storage unit being independent of each other, for mapping each historical date in a historical period to the historical actual average temperature T1 of the current day _i Said historical actual precipitation P1 _i Said historic actual maximum water level Z1 _i Said historic predicted maximum water level Z3 _i And the historical water level correction parameter n1 _i The method comprises the steps of setting a plurality of data sets which are independent respectively, and taking a date as an index to correspond to each data set one by one;

the first storage unit is used for storing each historical date and corresponding data sets of accidents not occurring in the target river reach in the historical period;

The second storage unit is used for storing each historical date of the accident of the target river reach in the historical period and corresponding data sets.

4. The big data based hydraulic data management system according to claim 3, wherein the data extraction module comprises a first data extraction unit and a second data extraction unit, the first data extraction unit and the second data extraction unit are independent from each other, the first data extraction unit is respectively connected with the prediction unit, the first storage unit and the second storage unit, and the second data extraction unit is respectively connected with the prediction unit, the first storage unit and the second storage unit;

the first data extraction unit is configured to extract all the data sets of the first date group from the first storage unit and the second storage unit according to the magnitude of the first predicted average air temperature T3, set all the data sets of the first date group extracted as a first database, and extract the historical actual precipitation amount P1 from the first database _i And the historic actual maximum water level Z1 _i And to extract said historical actual precipitation P1 _i And the historic actual maximum water level Z1 _i Setting the data of the first data set to be plotted;

the second data extraction unit is configured to extract all the data sets of the second date group from the first storage unit and the second storage unit according to the magnitude of the first predicted precipitation amount P3, set all the data sets of the second date group extracted as a second database, and extract the historical actual average air temperature T1 from the second database _i And the historic actual maximum water level Z1 _i And the extracted historical actual average air temperature T1 _i And the historic actual maximum water level Z1 _i Is set as the second data set to be plotted.

5. The big data based hydraulic data management system of claim 4, wherein,

the image establishing module comprises a first image establishing unit and a second image establishing unit, the first image establishing unit and the second image establishing unit are mutually independent, the first image establishing unit is connected with the first data extracting unit, and the second image establishing unit is connected with the second data extracting unit;

the first image creating unit is used for creating the historical actual precipitation amount P1 according to the first to-be-mapped data set _i Setting a precipitation amount-water level scatter diagram as a first image by arranging from low to high;

the second image is builtA standing unit for setting the historical actual average air temperature T1 according to the second to-be-mapped data set _i And arranging from low to high, and establishing an average air temperature-water level scatter diagram as a second image.

6. The big data based hydraulic data management system of claim 5, wherein the parameter fitting module comprises a first parameter fitting unit and a second parameter fitting unit, the first parameter fitting unit and the second parameter fitting unit are independent from each other, the first parameter fitting unit is connected with the first image building unit, and the second parameter fitting unit is connected with the second image building unit;

the first parameter fitting unit is configured to perform linear fitting according to the first image, obtain a slope of the linear image after fitting with the first image as a first slope, and set a value of the first slope as a first parameter k1;

the second parameter fitting unit is configured to perform linear fitting according to the second image, obtain a slope of the linear image after fitting with the second image as a second slope, and set a value of the second slope as a second parameter k2.

7. The big data based hydraulic data management system of claim 6, wherein the calculation module is connected to the prediction unit, the first parameter fitting unit, the second parameter fitting unit, the first storage unit, and the second storage unit, respectively, for calculating the first predicted average air temperature T3, the first predicted precipitation amount P3, the first parameter k1, the second parameter k2, and the first water level correction parameter n1 _N According to the formula (P3.times.k1) + (T3.times.k2) +n1 _N The first predicted maximum water level Z3 is calculated by =z3.

8. The big data-based hydraulic data management system according to claim 7, wherein the comparison module is connected to the dangerous water level setting module and the calculation module, respectively, and is configured to compare the magnitude relation between the dangerous water level Z0 and the first predicted maximum water level Z3, and determine the dangerous degree of the first water level according to the magnitude relation;

when the comparison module determines that Z3 is more than or equal to Z0, the first water level has the danger of causing accidents, and the comparison module sends out danger early warning;

when the comparison module determines that Z3 is less than Z0, the first water level does not have the danger of causing accidents.

9. The big data based water conservancy data management system according to claim 8, wherein the correction parameter setting module is connected with the first storage unit and the second storage unit for setting the historical actual maximum water level Z1 in a historical period _i Said historic predicted maximum water level Z3 _i The second actual maximum water level Z2 and the second predicted maximum water level Z3 _N+1 According to the formula

Calculating the second water level correction parameter n1 _N+1 Wherein i is 1.ltoreq.N, N is a positive integer, N is the total number of days before the day in the history period.

10. The big data based hydraulic data management system according to claim 9, wherein the data processing module is connected to the prediction unit, the detection unit, the first storage unit, the second storage unit, the calculation module, and the correction parameter setting module, respectively;

deleting the first predicted average air temperature T3 and the first predicted precipitation amount P3;

when Z3 is more than or equal to Z0, setting the first predicted maximum water level Z3 as the historical predicted maximum water level Z3 _N+1 The second actual average air temperature T2 is set as the historical actual average air temperature T1 _N+1 Setting the second actual precipitation amount P2 as the historical actual precipitation amount P1 _N+1 Setting the second actual maximum water level Z2 as a history actualMaximum water level Z1 _N+1 And predicts the history to the maximum water level Z3 _N+1 Historical actual average temperature T1 _N+1 Historical actual precipitation P1 _N+1 Historical actual maximum water level Z1 _N+1 And the first water level correction parameter n1 _N Stored in the first storage unit;

when Z3 < Z0, setting the first predicted maximum water level Z3 as a historical predicted maximum water level Z3 _N+1 The second actual average air temperature T2 is set as the historical actual average air temperature T1 _N+1 Setting the second actual precipitation amount P2 as the historical actual precipitation amount P1 _N+1 Setting the second actual maximum water level Z2 as a historical actual maximum water level Z1 _N+1 And predicts the history to the maximum water level Z3 _N+1 Historical actual average temperature T1 _N+1 Historical actual precipitation P1 _N+1 Historical actual maximum water level Z1 _N+1 And the second water level correction parameter n1 _N+1 Stored in the second storage unit.

Images