Water affair Internet of Things platform based on credential information

Abstract

The invention discloses a water affair internet-of-things platform based on credential information, and relates to a water affair internet-of-things cloud platform, the water affair internet-of-things platform comprises an information acquisition unit, an information analysis unit and an early warning and prediction unit, the information acquisition unit is used for acquiring historical data, real-time data, real-time images and historical images, and the information analysis unit comprises a model establishment module; the method is used for establishing a normal reservoir level model, calculating normal standard flow, calculating normal standard water level, further calculating a flow influence coefficient and a water level influence coefficient, obtaining flow prediction data and water level prediction data, calculating comprehensive water volume data based on the flow prediction data and the water level prediction data, presetting a comprehensive water volume interval, and calculating the normal reservoir level model according to the preset comprehensive water volume interval. And judging the comprehensive water volume data according to the comprehensive water volume interval to generate a flood early warning signal and a drought early warning signal. According to the method, flood and drought early warning is carried out by calculating the comprehensive water volume data, the accuracy and effectiveness of early warning are improved, water level change early warning can be carried out, and the safety of reservoir management is improved.

Description

Technical Field

[0001] The present invention relates to a water affairs Internet of Things cloud platform, and in particular to a water affairs Internet of Things platform based on trusted information. Background Art

[0002] With the development of society and the progress of the times, people's demand for water resources is increasing, and water management is facing greater challenges. Water resources are the basic resources for economic development. Scientific and effective water management can effectively ensure the security of water resources, improve the sustainable utilization rate of water resources, and help society better adapt to and respond to the challenges brought about by climate change.

[0003] However, in the traditional water management field, people usually rely on manual inspections and simple monitoring equipment to obtain key data such as reservoir water level and flow. Although these traditional methods can meet basic data needs to a certain extent, they increase personnel costs and have obvious deficiencies in the comprehensiveness of data collection, processing speed, and accuracy of early warnings. Incomplete data collection and omission of key information will lead to reduced accuracy of early warnings, and water level change warnings cannot be issued in a timely manner, increasing the risk of safety accidents caused by abnormal water level changes.

[0004] In view of the above technical defects, a solution is now proposed. Summary of the invention

[0005] The purpose of the present invention is to propose a water Internet of Things platform based on trusted information. The present invention calculates comprehensive water volume data to provide flood and drought warnings, thereby improving the accuracy and effectiveness of the warnings. It can also provide water level change warnings, thereby improving the safety of reservoir management.

[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical solutions: a water affairs Internet of Things platform based on Xinchuang Information, including an information collection unit, an information analysis unit and an early warning and prediction unit;

[0007] The information acquisition unit includes a historical data acquisition module, a real-time data acquisition module and an image information acquisition module. The historical data acquisition module is used to acquire historical data A and send the historical data A to the information analysis unit;

[0008] The real-time data acquisition module is used to obtain real-time data B and send the real-time data B to the information analysis unit;

[0009] The image information acquisition module is used to obtain the real-time image C and the historical image D of the reservoir through the camera, and send the real-time image C and the historical image D to the information analysis unit;

[0010] The information analysis unit includes a model building module, a data analysis module, an information judgment module and an image analysis module;

[0011] The model building module is used to build and analyze the reservoir water level model under normal conditions. Based on the environmental conditions of sunny and windless days, the reservoir water level model under normal conditions is built to obtain real-time data B under normal conditions, wherein the real-time data B under normal conditions include real-time flow data Qsc under normal conditions and real-time water level data Wsc under normal conditions. By substituting the real-time flow data Qsc under normal conditions into the objective function, the standard flow Qb under normal conditions is obtained, and the physical parameters of the river to be predicted are obtained. The standard water level Wb under normal conditions is calculated based on the standard flow Qb under normal conditions and the physical parameters of the reservoir to be predicted.

[0012] The data analysis module is used to obtain real-time data B, which includes real-time flow data Qs and real-time water level data Ws, and calculate the flow influence coefficient Qk based on the real-time flow data Qs and the normal standard flow Qb, and calculate the water level influence coefficient Wk based on the real-time water level data Ws, the normal standard water level Wb and the flow influence coefficient Qk;

[0013] The information judgment module is used to calculate the flow prediction data Qy through the real-time flow data Qs and the flow influence coefficient Qk, calculate the water level prediction data Wy based on the flow prediction data Qy, the real-time water level data Ws and the water level influence coefficient Wk, calculate the comprehensive water volume data Li based on the flow prediction data Qy and the water level prediction data Wy, preset the comprehensive water volume interval (Lmin, Lmax), judge the comprehensive water volume data according to the comprehensive water volume interval to generate flood warning signals and drought warning signals, and send them to the warning and prediction unit;

[0014] The image analysis module is used to receive the real-time image C and the historical image D, and perform image processing and feature extraction on the real-time image C and the historical image D respectively, establish a spatial three-dimensional coordinate system, and obtain the three-dimensional outline of the reservoir in the real-time image C. Figure 1 and the three-dimensional contour of the reservoir in the historical image D. Figure 1 It is superimposed with the three-dimensional contour map 2 to calculate the water level deviation index Fi, preset the water level deviation index threshold Pmax, judge the water level deviation index Pi according to the preset threshold to generate a water level deviation signal, and send the water level deviation warning signal to the warning and prediction unit.

[0015] Further, the warning and prediction unit includes a water volume warning module, a water level deviation warning module and a water level prediction module;

[0016] The water volume warning module receives a flood warning signal and emits a flood warning prompt sound through the flood warning indicator to give an alarm reminder. The water volume warning module receives a drought warning signal and emits a drought warning prompt sound through the drought warning indicator to give an alarm reminder.

[0017] The water level deviation warning module is used to receive the water level deviation signal and send out a water level deviation prompt sound through the water level deviation prompter to give an alarm reminder;

[0018] The water level prediction module is used to predict the water level through reservoir related data and environmental data.

[0019] Furthermore, the specific working process of calculating the standard flow rate under normal conditions and the standard water level under normal conditions is:

[0020] S101, based on normal real-time data B and historical data A, the normal real-time data B includes normal real-time flow data Qsc and normal real-time water level data Wsc, and the historical data A includes historical flow data Qu and historical water level data Wu;

[0021] S102. Based on the environmental condition of sunny and windless day, a reservoir water level model under normal conditions is established, and its objective function can be expressed as:

[0022] Where f(x) represents the objective function, Qsc represents the real-time flow data under normal conditions, m = 1, 2, 3, ..., M, M represents the number of test simulations, and Qu represents the historical flow data;

[0023] S103, obtaining real-time flow data under normal conditions by using a flow sensor for multiple times, and substituting the data into the objective function to obtain the standard flow Qb under normal conditions;

[0024] S104, obtaining physical parameters of the reservoir, wherein the physical parameters include a reservoir length Lc, a reservoir width dc, and a reservoir depth hc;

[0025] S105, through the formula: Among them, Wb is the standard water level under normal conditions.

[0026] Furthermore, the specific working process of calculating the flow influence coefficient and the water level influence coefficient is as follows:

[0027] S201, obtaining real-time flow data Qs and real-time water level data Ws;

[0028] S202, through the formula: Among them, Qk is the flow influence coefficient, and E is a constant;

[0029] S203, through the formula: Among them, Wk is the water level influence coefficient and F is a constant.

[0030] Furthermore, the specific working process of calculating the comprehensive water volume data is as follows:

[0031] S301, through the formula: Among them, Qy is the traffic prediction data;

[0032] S302, through the formula: Among them, Wy is the water level prediction data, and G is a constant;

[0033] S303, through the formula: Among them, Li is the comprehensive water volume data, and J is a constant;

[0034] S304, preset comprehensive water volume interval (Lmin, Lmax);

[0035] If Li is greater than and equal to Lmax, a flood warning signal is generated and sent to the warning and prediction unit;

[0036] If Li is less than Lmin, a drought warning signal is generated and sent to the warning and prediction unit.

[0037] Furthermore, the specific working process of image processing is:

[0038] S401, preprocessing: preprocessing the received real-time image C and historical image D by performing operations such as denoising, enhancement, and transformation respectively;

[0039] S402, feature extraction: extract features from the preprocessed real-time image C to obtain the target contour Figure 1 , extract the features of the preprocessed historical image D to obtain the target contour image 2;

[0040] S403, contour map positioning: The target contour is located by using the projection statistics method based on gradient information. Figure 1 Scan the target contour image 2 in rows and columns to determine the target contour Figure 1 And the starting row coordinates, height, column coordinates and width of the target contour image 2, so as to Figure 1 and positioning with target contour map 2;

[0041] S404, determine the reservoir location: along the target contour Figure 1 The contour edge points of the target contour image 2 are drawn to obtain a first edge contour point set and a second edge contour point set. The midpoint position of the reservoir is determined based on the first edge contour point set and the second edge contour point set.

[0042] Furthermore, the specific working process of establishing a three-dimensional spatial coordinate system is as follows:

[0043] S501, establishing a spatial three-dimensional coordinate system: selecting the midpoint of the reservoir as the origin, defining the directions perpendicular to each other in the horizontal plane of the reservoir as the X-axis direction and the Y-axis direction, and defining the Z-axis perpendicular to the surface of the reservoir and pointing upward;

[0044] S502: Obtain target contour Figure 1 The midpoint coordinates of the reservoir (X1, Y1, Z1), the edge contour point U1 (X 11 , Y 11 , Z 11 )、U2(X 12 , Y 12 , Z 12 )、…、Uu(X 1u , Y 1u , Z 1u ), U is the total number of first edge contour points;

[0045] S503, obtain the midpoint coordinates (X2, Y2, Z2) of the reservoir in the target contour map 2, the edge contour point V1 (X 21 , Y 21 , Z 21 )、V2(X 22 , Y 22 , Z 22 ),…,Vv(X 2v , Y 2v , Z 2v ), V is the total number of the second edge contour points.

[0046] Furthermore, the specific working process of calculating the water level deviation index is as follows:

[0047] S601, according to the target profile Figure 1 The midpoint coordinates of the reservoir (X1, Y1, Z1), the edge contour point U1 (X 11 , Y 11 , Z 11 )、U2(X 12 , Y 12 , Z 12 )、…、Uu(X 1u , Y 1u , Z 1u ), and obtain the three-dimensional contour Figure 1 ;

[0048] S602, based on the midpoint coordinates (X2, Y2, Z2) of the reservoir in the target contour map 2, the edge contour point V1 (X 21 , Y 21 , Z 21 )、V2(X 22 , Y 22 , Z 22 ),…,Vv(X2v , Y 2v , Z 2v ), and obtain the three-dimensional contour diagram 2;

[0049] S603, the three-dimensional contour Figure 1 It is overlapped with the 3D contour map 2, and then its horizontal and vertical screenshots are obtained and compared to generate the total overlapping area dlm and the total non-overlapping area elm, where the total non-overlapping area elm is the offset of the reservoir water level.

[0050] S604, through the formula: Where Pi is the water level deviation index, q is a constant, and Ψ is the deviation factor.

[0051] Furthermore, the specific working process of generating the water level deviation signal is as follows:

[0052] S701, preset a water level deviation index threshold Fmax, and obtain a water level deviation index Pi of the reservoir;

[0053] S702: If Pi is greater than and equal to Pmax, a water level deviation signal is generated and sent to the early warning and prediction unit;

[0054] If Pi is less than Pmax, no signal is generated.

[0055] Furthermore, the specific working process of water level prediction is as follows:

[0056] S801, obtaining reservoir-related data and environmental data, wherein the environmental data includes the temperature, relative humidity and pressure of the surrounding environment of the reservoir, and performing feature extraction on the reservoir-related data, wherein the reservoir-related data includes the historical flow of the reservoir in the same period, the historical water level in the same period, the real-time flow of the reservoir, the real-time water level of the reservoir and the physical parameters of the reservoir;

[0057] S802, normalization processing: enhancing the reservoir-related data by rotation, scaling, and cropping, and normalizing the reservoir-related data by using the mean-to-standard deviation method so that its value is between 0 and 1, and integrating it into a reservoir-related database;

[0058] S803, training the reservoir-related database through a radial basis function-back propagation neural network, and dividing the input features of the reservoir-related database into a training set, a verification set, and a test set;

[0059] S804, using the trained and verified radial basis function-back propagation neural network to predict future water level changes, and reflecting the water level changes in real time through images.

[0060] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0061] The present invention realizes multi-dimensional and all-round monitoring of the reservoir operation status through the historical data acquisition module, the real-time data acquisition module and the image information acquisition module in the information acquisition unit, effectively improves the efficiency and quality of water affairs information collection, and calculates the standard flow and standard water level under normal conditions by establishing a reservoir water level model under normal conditions, and then calculates the comprehensive water volume data, and performs flood and drought warnings according to the preset comprehensive water volume interval, thereby improving the accuracy and effectiveness of the warnings. In addition, the water level deviation index is calculated through image analysis, and water level change warnings are performed, which can effectively reduce safety accidents caused by abnormal water level changes and improve the efficiency and safety of reservoir management. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 A flow chart of the water conservancy Internet of Things platform based on trusted information disclosed in the present invention is shown. DETAILED DESCRIPTION

[0063] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0064] Example:

[0065] like Figure 1 As shown, the water Internet of Things platform based on Xinchuang Information is characterized by including an information collection unit, an information analysis unit, and an early warning and prediction unit;

[0066] The information acquisition unit includes a historical data acquisition module, a real-time data acquisition module and an image information acquisition module. The historical data acquisition module is used to acquire historical data A and send the historical data A to the information analysis unit. The historical data A is historical data of the same period.

[0067] The real-time data acquisition module is used to obtain real-time data B and send the real-time data B to the information analysis unit;

[0068] The image information acquisition module is used to obtain the real-time image C and the historical image D of the reservoir through the camera, and send the real-time image C and the historical image D to the information analysis unit;

[0069] The information analysis unit includes a model building module, a data analysis module, an information judgment module and an image analysis module;

[0070] The model building module is used to build and analyze the reservoir water level model under normal conditions. Based on the environmental conditions of sunny and windless days, the reservoir water level model under normal conditions is built to obtain the real-time data B under normal conditions. The real-time data B under normal conditions include the real-time flow data Qsc under normal conditions and the real-time water level data Wsc under normal conditions. By substituting the real-time flow data Qsc under normal conditions into the objective function, the standard flow Qb under normal conditions is obtained, and the physical parameters of the river to be predicted are obtained. The standard water level Wb under normal conditions is calculated based on the standard flow Qb under normal conditions and the physical parameters of the reservoir to be predicted.

[0071] The specific working process of calculating the standard flow rate under normal conditions and the standard water level under normal conditions is:

[0072] S101, based on normal real-time data B and historical data A, the normal real-time data B includes normal real-time flow data Qsc and normal real-time water level data Wsc, and the historical data A includes historical flow data Qu and historical water level data Wu;

[0073] S102. Based on the environmental condition of sunny and windless day, a reservoir water level model under normal conditions is established, and its objective function can be expressed as:

[0074] Where f(x) represents the objective function, Qsc represents the real-time flow data under normal conditions, m = 1, 2, 3, ..., M, M represents the number of test simulations, and Qu represents the historical flow data;

[0075] S103, obtaining real-time flow data under normal conditions by using a flow sensor for multiple times, and substituting the data into the objective function to obtain the standard flow Qb under normal conditions;

[0076] S104, obtaining physical parameters of the reservoir, the physical parameters including reservoir length Lc, reservoir width dc and reservoir depth hc;

[0077] S105, through the formula: Among them, Wb is the standard water level under normal conditions;

[0078] The data analysis module is used to obtain real-time data B, which includes real-time flow data Qs and real-time water level data Ws. Based on the real-time flow data Qs and the normal standard flow Qb, the flow influence coefficient Qk is calculated. Based on the real-time water level data Ws, the normal standard water level Wb and the flow influence coefficient Qk, the water level influence coefficient Wk is calculated.

[0079] The specific working process of calculating the flow influence coefficient and the water level influence coefficient is as follows:

[0080] S201, obtaining real-time flow data Qs and real-time water level data Ws;

[0081] S202, through the formula: Among them, Qk is the flow impact coefficient, E is a constant, and the flow impact coefficient is used to reflect the impact of real-time flow data and standard flow under normal conditions on flow prediction data. The flow impact coefficient is negatively correlated with the flow prediction data;

[0082] S203, through the formula: Among them, Wk is the water level influence coefficient, F is a constant, and the water level influence coefficient is used to reflect the influence of real-time water level data, standard water level under normal conditions and flow influence coefficient on water level prediction data. The water level influence coefficient is negatively correlated with the water level prediction data.

[0083] The information judgment module is used to calculate the flow prediction data Qy through the real-time flow data Qs and the flow influence coefficient Qk, calculate the water level prediction data Wy based on the flow prediction data Qy, the real-time water level data Ws and the water level influence coefficient Wk, calculate the comprehensive water volume data Li based on the flow prediction data Qy and the water level prediction data Wy, preset the comprehensive water volume interval (Lmin, Lmax), judge the comprehensive water volume data according to the comprehensive water volume interval to generate flood warning signals and drought warning signals, and send them to the warning and prediction unit;

[0084] The specific working process of image calculation of comprehensive water volume data is as follows:

[0085] S301, through the formula: Among them, Qy is the traffic prediction data;

[0086] S302, through the formula: Among them, Wy is the water level prediction data, and G is a constant;

[0087] S303, through the formula: Among them, Li is the comprehensive water volume data, and J is a constant;

[0088] S304, preset comprehensive water volume interval (Lmin, Lmax);

[0089] If Li is greater than and equal to Lmax, a flood warning signal is generated and sent to the warning and prediction unit; if Li is less than Lmin, a drought warning signal is generated and sent to the warning and prediction unit. ;

[0090] The analysis module is used to receive the real-time image C and the historical image D, and perform image processing and feature extraction on the real-time image C and the historical image D respectively, and the historical image D is a historical image of the same period;

[0091] The specific working process of image processing is:

[0092] S401, preprocessing: preprocessing the received real-time image C and historical image D by performing operations such as denoising, enhancement, and transformation respectively;

[0093] S402, feature extraction: extract features from the preprocessed real-time image C to obtain the target contour Figure 1 , extract the features of the preprocessed historical image D to obtain the target contour image 2;

[0094] S403, contour map positioning: The target contour is located by using the projection statistics method based on gradient information. Figure 1 Scan the target contour image 2 in rows and columns to determine the target contour Figure 1 And the starting row coordinates, height, column coordinates and width of the target contour image 2, so as to Figure 1 and positioning with target contour map 2;

[0095] S404, determine the reservoir location: along the target contour Figure 1 The contour edge points of the target contour image 2 are drawn to obtain the first edge contour point set and the second edge contour point set. Based on the first edge contour point set and the second edge contour point set, the midpoint position of the reservoir is determined, and a spatial three-dimensional coordinate system is established to obtain the three-dimensional contour of the reservoir in the real-time image C. Figure 1 and the three-dimensional contour of the reservoir in the historical image D. Figure 1 Superimpose with the three-dimensional contour map 2, calculate the water level deviation index Fi, preset the water level deviation index threshold Pmax, judge the water level deviation index Pi according to the preset threshold to generate a water level deviation signal, and send the water level deviation warning signal to the warning and prediction unit;

[0096] The specific working process of image processing is:

[0097] S401, preprocessing: preprocessing the received real-time image C and historical image D by performing operations such as denoising, enhancement, and transformation respectively;

[0098] S402, feature extraction: extract features from the preprocessed real-time image C to obtain the target contour Figure 1 , extract the features of the preprocessed historical image D to obtain the target contour image 2;

[0099] S403, contour map positioning: The target contour is located by using the projection statistics method based on gradient information. Figure 1 Scan the target contour image 2 in rows and columns to determine the target contour Figure 1 And the starting row coordinates, height, column coordinates and width of the target contour image 2, so as to Figure 1 and positioning with target contour map 2;

[0100] S404, determine the reservoir location: along the target contour Figure 1and the contour edge points of the target contour image 2 to obtain a first edge contour point set and a second edge contour point set, and determine the midpoint position of the reservoir based on the first edge contour point set and the second edge contour point set;

[0101] The specific working process of establishing a three-dimensional spatial coordinate system is:

[0102] S501, establishing a spatial three-dimensional coordinate system: selecting the midpoint of the reservoir as the origin, defining the directions perpendicular to each other in the horizontal plane of the reservoir as the X-axis direction and the Y-axis direction, and defining the Z-axis perpendicular to the surface of the reservoir and pointing upward;

[0103] S502: Obtain target contour Figure 1 The midpoint coordinates of the reservoir (X1, Y1, Z1), the edge contour point U1 (X 11 , Y 11 , Z 11 )、U2(X 12 , Y 12 , Z 12 )、…、Uu(X 1u , Y 1u , Z 1u ), U is the total number of first edge contour points;

[0104] S503, obtain the midpoint coordinates (X2, Y2, Z2) of the reservoir in the target contour map 2, the edge contour point V1 (X 21 , Y 21 , Z 21 )、V2(X 22 , Y 22 , Z 22 ),…,Vv(X 2v , Y 2v , Z 2v ), V is the total number of the second edge contour points;

[0105] The specific working process of calculating the water level deviation index is as follows:

[0106] S601, according to the target profile Figure 1 The midpoint coordinates of the reservoir (X1, Y1, Z1), the edge contour point U1 (X 11 , Y 11 , Z 11 )、U2(X 12 , Y 12 , Z 12 )、…、Uu(X 1u , Y 1u , Z 1u ), and obtain the three-dimensional contour Figure 1 ;

[0107] S602, based on the midpoint coordinates (X2, Y2, Z2) of the reservoir in the target contour map 2, the edge contour point V1 (X 21 , Y 21 , Z 21 )、V2(X 22 , Y 22 , Z 22 ),…,Vv(X 2v , Y 2v , Z 2v ), and obtain the three-dimensional contour diagram 2;

[0108] S603, the three-dimensional contour Figure 1 It is overlapped with the 3D contour map 2, and then its horizontal and vertical screenshots are obtained and compared to generate the total overlapping area dlm and the total non-overlapping area elm, where the total non-overlapping area elm is the offset of the reservoir water level.

[0109] S604, through the formula: Where Pi is the water level deviation index, q is a constant, and Ψ is the deviation factor;

[0110] The specific working process of generating water level deviation signal is as follows:

[0111] S701, preset a water level deviation index threshold Fmax, and obtain a water level deviation index Pi of the reservoir;

[0112] S702: If Pi is greater than and equal to Pmax, a water level deviation signal is generated and sent to the early warning and prediction unit;

[0113] If Pi is less than Pmax, no signal is generated;

[0114] The warning and prediction unit includes a water volume warning module, a water level deviation warning module and a water level prediction module;

[0115] The water volume warning module receives a flood warning signal and sends a flood warning tone through the flood warning indicator to give an alarm reminder. The water volume warning module receives a drought warning signal and sends a drought warning tone through the drought warning indicator to give an alarm reminder.

[0116] The water level deviation warning module is used to receive the water level deviation signal and send out a water level deviation prompt sound through the water level deviation prompter to give an alarm reminder;

[0117] The water level prediction module is used to predict water levels through reservoir-related data and environmental data;

[0118] The specific working process of water level prediction is as follows:

[0119] S801, obtaining reservoir-related data and environmental data, the environmental data including the temperature, relative humidity and pressure of the surrounding environment of the reservoir, and extracting features from the reservoir-related data, the reservoir-related data including the historical flow of the reservoir in the same period, the historical water level in the same period, the real-time flow of the reservoir, the real-time water level of the reservoir and the physical parameters of the reservoir;

[0120] S802, normalization processing: enhancing the reservoir-related data by rotation, scaling, and cropping, and normalizing the reservoir-related data by using the mean-to-standard deviation method so that its value is between 0 and 1, and integrating it into a reservoir-related database;

[0121] S803, training the reservoir-related database through a radial basis function-back propagation neural network, and dividing the input features of the reservoir-related database into a training set, a verification set, and a test set;

[0122] S804, using the trained and verified radial basis function-back propagation neural network to predict future water level changes, and reflecting the water level changes in real time through images.

[0123] In summary of the above technical solutions: The present invention realizes multi-dimensional and all-round monitoring of the reservoir operation status through the historical data acquisition module, the real-time data acquisition module and the image information acquisition module in the information acquisition unit, effectively improves the efficiency and quality of water information collection, and calculates the standard flow and standard water level under normal conditions by establishing a reservoir water level model under normal conditions, and then calculates the comprehensive water volume data, and performs flood and drought warnings according to the preset comprehensive water volume interval, thereby improving the accuracy and effectiveness of the warnings. In addition, by calculating the water level deviation index through image analysis and performing water level change warnings, it can effectively reduce safety accidents caused by abnormal water level changes and improve the efficiency and safety of reservoir management.

[0124] The setting of the threshold and interval size is for the convenience of comparison. The size of the threshold depends on the amount of sample data and the number of bases set by technicians in this field for each group of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value;

[0125] Those skilled in the art can appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented by a device or a combination of computer software and electronic hardware; whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution;

[0126] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. The water Internet of Things platform based on Xinchuang Information is characterized by: It includes information collection unit, information analysis unit and early warning and prediction unit; The information acquisition unit includes a historical data acquisition module, a real-time data acquisition module and an image information acquisition module. The historical data acquisition module is used to acquire historical data A and send the historical data A to the information analysis unit; The real-time data acquisition module is used to obtain real-time data B and send the real-time data B to the information analysis unit; The image information acquisition module is used to obtain the real-time image C and the historical image D of the reservoir through the camera, and send the real-time image C and the historical image D to the information analysis unit; The information analysis unit includes a model building module, a data analysis module, an information judgment module and an image analysis module; The model building module is used to build and analyze the reservoir water level model under normal conditions. Based on the environmental conditions of sunny and windless days, the reservoir water level model under normal conditions is built to obtain real-time data B under normal conditions, wherein the real-time data B under normal conditions include real-time flow data Qsc under normal conditions and real-time water level data Wsc under normal conditions. By substituting the real-time flow data Qsc under normal conditions into the objective function, the standard flow Qb under normal conditions is obtained, and the physical parameters of the river to be predicted are obtained. The standard water level Wb under normal conditions is calculated based on the standard flow Qb under normal conditions and the physical parameters of the reservoir to be predicted. The data analysis module is used to obtain real-time data B, which includes real-time flow data Qs and real-time water level data Ws, and calculate the flow influence coefficient Qk based on the real-time flow data Qs and the normal standard flow Qb, and calculate the water level influence coefficient Wk based on the real-time water level data Ws, the normal standard water level Wb and the flow influence coefficient Qk; The information judgment module is used to calculate the flow prediction data Qy through the real-time flow data Qs and the flow influence coefficient Qk, calculate the water level prediction data Wy based on the flow prediction data Qy, the real-time water level data Ws and the water level influence coefficient Wk, calculate the comprehensive water volume data Li based on the flow prediction data Qy and the water level prediction data Wy, preset the comprehensive water volume interval (Lmin, Lmax), judge the comprehensive water volume data according to the comprehensive water volume interval to generate flood warning signals and drought warning signals, and send them to the warning and prediction unit; The image analysis module is used to receive the real-time image C and the historical image D, and perform image processing and feature extraction on the real-time image C and the historical image D respectively, establish a spatial three-dimensional coordinate system, obtain a three-dimensional contour map 1 of the reservoir in the real-time image C and a three-dimensional contour map 2 of the reservoir in the historical image D, superimpose the three-dimensional contour map 1 with the three-dimensional contour map 2, calculate the water level deviation index Fi, preset the water level deviation index threshold Pmax, judge the water level deviation index Pi according to the preset threshold to generate a water level deviation signal, and send the water level deviation warning signal to the warning and prediction unit.

2. The water affairs Internet of Things platform based on Xinchuang information according to claim 1 is characterized in that: The warning and prediction unit includes a water volume warning module, a water level deviation warning module and a water level prediction module; The water volume warning module receives a flood warning signal and emits a flood warning prompt sound through the flood warning indicator to give an alarm reminder. The water volume warning module receives a drought warning signal and emits a drought warning prompt sound through the drought warning indicator to give an alarm reminder. The water level deviation warning module is used to receive the water level deviation signal and send out a water level deviation prompt sound through the water level deviation prompter to give an alarm reminder; The water level prediction module is used to predict the water level through reservoir related data and environmental data.

3. The water conservancy Internet of Things platform based on Xinchuang information according to claim 1 is characterized in that: The specific working process of calculating the standard flow rate under normal conditions and the standard water level under normal conditions is: S101, based on normal real-time data B and historical data A, the normal real-time data B includes normal real-time flow data Qsc and normal real-time water level data Wsc, and the historical data A includes historical flow data Qu and historical water level data Wu; S102. Based on the environmental condition of sunny and windless day, a reservoir water level model under normal conditions is established, and its objective function can be expressed as: Where f(x) represents the objective function, Qsc represents the real-time flow data under normal conditions, m = 1, 2, 3, ..., M, M represents the number of test simulations, and Qu represents the historical flow data; S103, obtaining real-time flow data under normal conditions by using a flow sensor for multiple times, and substituting the data into the objective function to obtain the standard flow Qb under normal conditions; S104, obtaining physical parameters of the reservoir, wherein the physical parameters include a reservoir length Lc, a reservoir width dc, and a reservoir depth hc; S105, through the formula: Among them, Wb is the standard water level under normal conditions.

4. The water Internet of Things platform based on Xinchuang information according to claim 1 is characterized in that: The specific working process of calculating the flow influence coefficient and the water level influence coefficient is as follows: S201, obtaining real-time flow data Qs and real-time water level data Ws; S202, through the formula: Among them, Qk is the flow influence coefficient, and E is a constant; S203, through the formula: Among them, Wk is the water level influence coefficient and F is a constant.

5. The water affairs Internet of Things platform based on Xinchuang information according to claim 1 is characterized in that: The specific working process of calculating comprehensive water volume data is as follows: S301, through the formula: Among them, Qy is the traffic prediction data; S302, through the formula: Among them, Wy is the water level prediction data, and G is a constant; S303, through the formula: Among them, Li is the comprehensive water volume data, and J is a constant; S304, preset comprehensive water volume interval (Lmin, Lmax); If Li is greater than and equal to Lmax, a flood warning signal is generated and sent to the warning and prediction unit; If Li is less than Lmin, a drought warning signal is generated and sent to the warning and prediction unit.

6. The water Internet of Things platform based on Xinchuang information according to claim 1 is characterized in that: The specific working process of image processing is: S401, preprocessing: preprocessing the received real-time image C and historical image D by performing operations such as denoising, enhancement, and transformation respectively; S402, feature extraction: extracting features from the preprocessed real-time image C to obtain a target contour image 1, and extracting features from the preprocessed historical image D to obtain a target contour image 2; S403, contour map positioning: Scan the target contour map 1 and the target contour map 2 in rows and columns by using a projection statistics method based on gradient information, determine the starting row coordinates, height, column coordinates and width of the target contour map 1 and the target contour map 2, and thus position the target contour map 1 and the target contour map 2; S404, determining the location of the reservoir: tracing points along the contour edges of the target contour map 1 and the target contour map 2 to obtain a first edge contour point set and a second edge contour point set, and determining the midpoint location of the reservoir based on the first edge contour point set and the second edge contour point set.

7. The water Internet of Things platform based on Xinchuang information according to claim 6 is characterized in that: The specific working process of establishing a three-dimensional spatial coordinate system is: S501, establishing a spatial three-dimensional coordinate system: selecting the midpoint of the reservoir as the origin, defining the directions perpendicular to each other in the horizontal plane of the reservoir as the X-axis direction and the Y-axis direction, and defining the Z-axis perpendicular to the surface of the reservoir and pointing upward; S502, obtain the midpoint coordinates (X1, Y1, Z1) of the reservoir in the target contour map 1, the edge contour point U1 (X 11 , Y 11 , Z 11 )、U2(X 12 , Y 12 , Z 12 )、…、Uu(X 1u , Y 1u , Z 1u ), U is the total number of first edge contour points; S503, obtain the midpoint coordinates (X2, Y2, Z2) of the reservoir in the target contour map 2, the edge contour point V1 (X 21 , Y 21 , Z 21 )、V2(X 22 , Y 22 , Z 22 ),…,Vv(X 2v , Y 2v , Z 2v ), V is the total number of the second edge contour points.

8. The water affairs Internet of Things platform based on Xinchuang information according to claim 7 is characterized in that: The specific working process of calculating the water level deviation index is as follows: S601, according to the midpoint coordinates (X1, Y1, Z1) of the reservoir in the target contour map 1, the edge contour point U1 (X 11 , Y 11 , Z 11 )、U2(X 12 , Y 12 , Z 12 )、…、Uu(X 1u , Y 1u , Z 1u ), and obtain a three-dimensional contour map 1; S602, based on the midpoint coordinates (X2, Y2, Z2) of the reservoir in the target contour map 2, the edge contour point V1 (X 21 , Y 21 , Z 21 )、V2(X 22 , Y 22 , Z 22 ),…,Vv(X 2v , Y 2v , Z 2v ), and obtain the three-dimensional contour diagram 2; S603, superimpose the 3D contour map 1 and the 3D contour map 2, then obtain and compare their horizontal and vertical screenshots, generate the total overlap area dlm and the total non-overlap area elm, wherein the total non-overlap area elm is the offset of the reservoir water level, S604, through the formula: Where Pi is the water level deviation index, q is a constant, and Ψ is the deviation factor.

9. The water conservancy Internet of Things platform based on Xinchuang information according to claim 8 is characterized in that: The specific working process of generating water level deviation signal is as follows: S701, preset a water level deviation index threshold Fmax, and obtain a water level deviation index Pi of the reservoir; S702: If Pi is greater than and equal to Pmax, a water level deviation signal is generated and sent to the early warning and prediction unit; If Pi is less than Pmax, no signal is generated.

10. The water affairs Internet of Things platform based on Xinchuang information according to claim 2 is characterized in that: The specific working process of water level prediction is as follows: S801, obtaining reservoir-related data and environmental data, wherein the environmental data includes the temperature, relative humidity and pressure of the surrounding environment of the reservoir, and performing feature extraction on the reservoir-related data, wherein the reservoir-related data includes the historical flow of the reservoir in the same period, the historical water level in the same period, the real-time flow of the reservoir, the real-time water level of the reservoir and the physical parameters of the reservoir; S802, normalization processing: enhancing the reservoir-related data by rotation, scaling, and cropping, and normalizing the reservoir-related data by using the mean-to-standard deviation method so that its value is between 0 and 1, and integrating it into a reservoir-related database; S803, training the reservoir-related database through a radial basis function-back propagation neural network, and dividing the input features of the reservoir-related database into a training set, a verification set, and a test set; S804, using the trained and verified radial basis function-back propagation neural network to predict future water level changes, and reflecting the water level changes in real time through images.

Images