Water and rain condition real-time monitoring method and system based on Internet of Things

Abstract

The invention belongs to the technical field of water and rain condition monitoring, and discloses a water and rain condition real-time monitoring method and system based on the Internet of Things. The method comprises the following steps: deploying an Internet of Things sensing layer and an Internet of Things transmission layer, and connecting the Internet of Things sensing layer and the Internet of Things transmission layer to a cloud data center; the cloud data center constructs an artificial intelligence model; the current data acquisition device is used for acquiring real-time water and rain condition monitoring data; the current data acquisition device plans a transmission path; the current data acquisition device performs monitoring data compression and transmits a real-time water and rain condition monitoring data compression packet to the cloud data center based on a real-time transmission path; the cloud data center decompresses and analyzes the real-time water and rain condition monitoring data compression package; and the cloud data center is used for visually displaying the analysis result and the monitoring data. According to the invention, the problems of poor monitoring real-time performance, low analysis accuracy and low data transmission efficiency in the prior art are solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of water and rainfall monitoring, and in particular relates to a real-time water and rainfall monitoring method and system based on the Internet of Things. Background Art

[0002] Water and rainfall monitoring plays a vital role in many fields. By real-time monitoring of water and rainfall conditions, floods, mountain torrents and other disasters can be predicted in advance, and precious time can be gained for residents' evacuation and emergency response. Monitoring data provides a basis for the rational scheduling and allocation of water resources, ensuring the effective use of water resources. Water and rainfall monitoring is often combined with water quality monitoring, which helps to timely detect water pollution incidents and protect the water ecological environment. With the development of Internet of Things technology, the transmission of real-time data through the Internet of Things has become an important development direction in the field of water and rainfall monitoring.

[0003] The existing water and rainfall monitoring technology has the following defects:

[0004] 1) Poor real-time monitoring: Traditional monitoring methods rely on manual observation, which has time delays and cannot obtain water and rainfall data in real time. In addition, the coverage of data collection and transmission devices is limited, and the data update frequency in some areas is low;

[0005] 2) Low analysis accuracy: Manual observation is affected by subjective factors, and the accuracy of data analysis is difficult to guarantee, resulting in the inability to timely discover and quickly respond to potential water and rainfall disasters, and the water and rainfall monitoring effect cannot meet the requirements;

[0006] 3) Low data transmission efficiency: Existing data transmission methods may have bandwidth limitations, resulting in slow data transmission speeds and affecting real-time performance. In areas with poor network coverage, data transmission may be unstable or interrupted. Summary of the invention

[0007] In order to solve the problems of poor real-time monitoring, low analysis accuracy and low data transmission efficiency in the prior art, the present invention aims to provide a real-time monitoring method and system for water and rainfall conditions based on the Internet of Things.

[0008] The technical solution adopted by the present invention is:

[0009] A real-time monitoring method of water and rainfall conditions based on the Internet of Things comprises the following steps:

[0010] Deploy the IoT perception layer and IoT transmission layer for real-time monitoring of water and rainfall conditions in the monitoring area, and connect the IoT perception layer to the cloud data center through the IoT transmission layer;

[0011] The cloud data center uses artificial intelligence algorithms to build a three-dimensional digital twin model of the monitoring area, a water and rainfall monitoring data analysis model, a monitoring data compression model, and a transmission path planning model, and deploys the monitoring data compression model and the transmission path planning model to all data collection devices in the IoT perception layer;

[0012] The current data collection device collects the real-time water and rainfall monitoring data of the current monitoring point, generates a corresponding real-time data transmission instruction, and sends the real-time data transmission instruction to the first data transmission device in the Internet of Things transmission layer;

[0013] The current data acquisition device obtains the first real-time communication address returned by the first data transmission device, and uses the transmission path planning model to perform transmission path planning according to the first real-time communication address and the fixed communication address of the cloud data center to obtain the real-time transmission path;

[0014] The current data acquisition device uses a monitoring data compression model to compress the real-time water and rainfall monitoring data to obtain a real-time water and rainfall monitoring data compression package, and based on the real-time transmission path, transmits the real-time water and rainfall monitoring data compression package to the cloud data center through the Internet of Things transmission layer;

[0015] The cloud data center decompresses the compressed package of the real-time water and rainfall monitoring data, uses the water and rainfall monitoring data analysis model to perform water and rainfall monitoring data analysis on the decompressed real-time water and rainfall monitoring data to obtain real-time water and rainfall analysis results, and updates the water and rainfall monitoring data analysis model to obtain an updated water and rainfall monitoring data analysis model;

[0016] The cloud data center generates real-time water and rainfall alarm signals based on the real-time water and rainfall analysis results, and uses the three-dimensional digital twin model of the monitoring area to visualize the decompressed real-time water and rainfall monitoring data of all monitoring points, as well as the corresponding real-time water and rainfall analysis results and real-time water and rainfall alarm signals.

[0017] Furthermore, an IoT perception layer and an IoT transmission layer for real-time monitoring of water and rainfall conditions are deployed in the monitoring area, and the IoT perception layer is connected to the cloud data center through the IoT transmission layer, including the following steps:

[0018] Obtain three-dimensional map data of the monitoring area, as well as historical water and rainfall monitoring data and corresponding historical location data of several monitoring points for historical water and rainfall monitoring;

[0019] According to the three-dimensional map data and the historical location data of several monitoring points, several data collection devices are deployed at the corresponding positions of the monitoring area to build the Internet of Things perception layer;

[0020] According to the three-dimensional map data and the real-time location data and device performance parameters of several data collection devices in the IoT perception layer, several cascaded data transmission devices are deployed in the monitoring area to build the IoT transmission layer;

[0021] Each data collection device of the IoT perception layer is connected to several data transmission devices of the IoT transmission layer close to the IoT perception layer in a distributed manner, and several data transmission devices of the IoT transmission layer close to the cloud data center are connected to the cloud data center.

[0022] Furthermore, the cloud data center uses artificial intelligence algorithms to construct a three-dimensional digital twin model of the monitoring area, a water and rainfall monitoring data analysis model, a monitoring data compression model, and a transmission path planning model, and deploys the monitoring data compression model and the transmission path planning model to all data collection devices in the IoT perception layer, including the following steps:

[0023] According to the three-dimensional map data of the monitoring area, a three-dimensional simulation model of the monitoring area is constructed, and the three-dimensional simulation model of the monitoring area is integrated with the digital twin to obtain the three-dimensional digital twin model of the monitoring area;

[0024] Based on some historical water and rainfall monitoring data, a deep learning algorithm is used to build a water and rainfall monitoring data analysis model and a monitoring data compression model;

[0025] Collect the historical transmission paths of several historical water and rainfall monitoring data, and build a transmission path planning model based on several historical transmission paths using swarm intelligence optimization algorithm;

[0026] Obtain model metadata of the monitoring data compression model and the transmission path planning model, and send the model metadata to all data collection devices of the IoT perception layer through the IoT transmission layer;

[0027] Each data collection device in the perception layer of the Internet of Things reconstructs the model according to the model metadata to obtain a reconstructed monitoring data compression model and a reconstructed transmission path planning model.

[0028] Furthermore, the monitoring data compression model is constructed based on the CNN-LSTM-DBN algorithm, and the monitoring data compression model includes a first image data feature extraction module constructed based on the CNN algorithm, a first sequence data feature extraction module constructed based on the LSTM algorithm, and a monitoring data compression module constructed based on the DBN algorithm. The monitoring data compression module is respectively connected to the first image data feature extraction module and the first sequence data feature extraction module.

[0029] Furthermore, the water and rainfall monitoring data analysis model is constructed based on the FPN-LSTM-Attention-MLP-CLA algorithm, and the water and rainfall monitoring data analysis model includes a second image data feature extraction module constructed based on the FPN algorithm, a second sequence data feature extraction module constructed based on the LSTM algorithm, an attention weight module constructed based on the Attention mechanism, a water and rainfall monitoring data analysis module constructed based on the MLP algorithm, and a continuous learning module constructed based on the CLA algorithm. The second image data feature extraction module and the second sequence data feature extraction module are both connected to the attention weight module, and the attention weight module, the water and rainfall monitoring data analysis module and the continuous learning module are connected in sequence, and the continuous learning module is provided with an experience replay pool.

[0030] Furthermore, the transmission path planning model is constructed based on the ISSA algorithm, and the transmission path planning model includes an initial solution generation module, an iterative optimization module and a transmission path decoding module which are connected in sequence.

[0031] Further, the current data acquisition device obtains the first real-time communication address returned by the first data transmission device, and uses the transmission path planning model to perform transmission path planning according to the first real-time communication address and the fixed communication address of the cloud data center to obtain the real-time transmission path, including the following steps:

[0032] The current data collection device obtains the first real-time communication address returned by the first data transmission device, and inputs the first real-time communication address and the fixed communication address of the cloud data center into the transmission path planning model;

[0033] Using an initial solution generation module of a transmission path planning model, a solution vector is set according to the first real-time communication address and the fixed communication address, and a plurality of initial solutions are generated according to the solution vector;

[0034] Use the iterative optimization module of the transmission path planning model to iteratively optimize several initial solutions to obtain the optimal solution;

[0035] The transmission path decoding module of the transmission path planning model is used to decode the solution vector of the optimal solution to obtain a real-time transmission path.

[0036] Furthermore, the current data acquisition device uses a monitoring data compression model to compress the real-time water and rainfall monitoring data to obtain a real-time water and rainfall monitoring data compression package, and based on the real-time transmission path, transmits the real-time water and rainfall monitoring data compression package to the cloud data center through the Internet of Things transmission layer, including the following steps:

[0037] The current data acquisition device performs data analysis on the real-time water and rainfall monitoring data to obtain real-time water and rainfall monitoring image data and real-time water and rainfall monitoring sequence data;

[0038] Using a first image data feature extraction module of a monitoring data compression model, extracting first real-time image data features of real-time water and rainfall monitoring image data;

[0039] Using the first sequence data feature extraction module of the monitoring data compression model, extracting the first real-time sequence data feature of the real-time water and rainfall monitoring sequence data;

[0040] Using a monitoring data compression module of the monitoring data compression model, the first real-time image data feature and the first real-time sequence data feature are divided into sub-blocks to obtain a plurality of real-time sub-blocks;

[0041] Encode each real-time sub-block to obtain a number of real-time compressed codewords, and merge the real-time compressed codewords to obtain an initial real-time water and rainfall monitoring data compression package;

[0042] Post-processing the initial real-time water and rainfall monitoring data compression package to obtain the final real-time water and rainfall monitoring data compression package;

[0043] Based on the real-time transmission path, the real-time water and rainfall monitoring data compression package is transmitted to the cloud data center through several corresponding data transmission devices in the Internet of Things transmission layer.

[0044] Further, the cloud data center decompresses the compressed package of the real-time water-rain monitoring data, uses the water-rain monitoring data analysis model to perform water-rain monitoring data analysis on the decompressed real-time water-rain monitoring data to obtain real-time water-rain analysis results, and updates the water-rain monitoring data analysis model to obtain an updated water-rain monitoring data analysis model, including the following steps:

[0045] The cloud data center decompresses the compressed package of the real-time water and rainfall monitoring data to obtain the decompressed real-time water and rainfall monitoring data;

[0046] Performing data analysis on the decompressed real-time water and rainfall monitoring data to obtain decompressed real-time water and rainfall monitoring image data and decompressed real-time water and rainfall monitoring sequence data;

[0047] Using the second image data feature extraction module of the water and rainfall monitoring data analysis model, extract the second real-time image data features of the decompressed real-time water and rainfall monitoring image data;

[0048] Using the second sequence data feature extraction module of the water and rainfall monitoring data analysis model, extract the second real-time sequence data features of the decompressed real-time water and rainfall monitoring sequence data;

[0049] According to the preset attention weight, the attention weight module of the water and rainfall monitoring data analysis model is used to weightedly fuse the second real-time image data feature and the second real-time sequence data feature to obtain a real-time weighted fusion feature;

[0050] Use the water-rain monitoring data analysis module of the water-rain monitoring data analysis model to analyze the water-rain monitoring data on the real-time weighted fusion features, obtain the real-time water-rain analysis results, and generate real-time water-rain monitoring data analysis experience;

[0051] Randomly extract a number of historical water and rainfall monitoring data analysis experiences from the experience playback pool of the water and rainfall monitoring data analysis model, and mix them with the real-time water and rainfall monitoring data analysis experiences to obtain a number of mixed water and rainfall monitoring data analysis experiences;

[0052] According to the experience of analyzing several mixed water-rainfall monitoring data, the water-rainfall monitoring data analysis model is updated using the continuous learning module of the water-rainfall monitoring data analysis model to obtain an updated water-rainfall monitoring data analysis model.

[0053] A real-time water and rainfall monitoring system based on the Internet of Things is used to implement a real-time water and rainfall monitoring method. The system includes a cloud data center, an Internet of Things perception layer and an Internet of Things transmission layer connected in sequence. The Internet of Things perception layer includes several data acquisition devices, and the Internet of Things transmission layer includes several data transmission devices.

[0054] The beneficial effects of the present invention are:

[0055] The invention discloses a real-time monitoring method and system for water and rainfall conditions based on the Internet of Things. The Internet of Things perception layer and the Internet of Things transmission layer are deployed to realize the real-time collection and transmission of water and rainfall monitoring data, eliminate time delay, expand the coverage of data collection and transmission devices, and enhance the real-time monitoring performance. Through the constructed water and rainfall monitoring data analysis model, the water and rainfall monitoring data are efficiently processed and accurately analyzed, and potential water and rainfall disasters can be discovered, thereby improving the accuracy of data analysis, ensuring a rapid response to water and rainfall disasters, and achieving a water and rainfall monitoring effect that meets the requirements. The Internet of Things perception layer and the Internet of Things transmission layer can cover a wider area, including remote and complex terrain areas, through the flexible deployment of Internet of Things devices, and adopt an efficient data compression model and a transmission path planning model to accelerate the data transmission speed and ensure real-time performance. The Internet of Things device is only responsible for data transmission, has high stability and self-maintenance capability, reduces maintenance cost and frequency, has low power consumption, reduces energy consumption, and is suitable for various environments.

[0056] Other beneficial effects of the present invention will be further described in the specific embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1It is a flow chart of the real-time monitoring method of water and rainfall conditions based on the Internet of Things in the present invention.

[0058] Figure 2 It is a structural block diagram of the real-time monitoring system of water and rainfall conditions based on the Internet of Things in the present invention. DETAILED DESCRIPTION

[0059] The present invention will be further explained below in conjunction with the accompanying drawings and specific embodiments.

[0060] Embodiment 1:

[0061] like Figure 1 As shown, this embodiment provides a real-time monitoring method of water and rainfall conditions based on the Internet of Things, including the following steps:

[0062] S1: Deploy the IoT perception layer and IoT transmission layer for real-time monitoring of water and rainfall conditions in the monitoring area, and connect the IoT perception layer to the cloud data center through the IoT transmission layer, including the following steps:

[0063] S1-1: Obtain three-dimensional map data of the monitoring area, as well as historical water and rainfall monitoring data and corresponding historical location data of several monitoring points for historical water and rainfall monitoring;

[0064] S1-2: Based on the three-dimensional map data and the historical location data of several monitoring points, several data collection devices are deployed at the corresponding locations of the monitoring area to build the IoT perception layer;

[0065] The IoT perception layer is composed of several data acquisition devices, which are arranged at the monitoring points in the monitoring area and are used to collect the water-rain monitoring data of the monitoring points. In order to realize the collection of water-rain monitoring data, the data acquisition device is provided with a main control processor, an IoT communication module and a water-rain monitoring sensor. The main control processor is used to control the normal operation of other hardware, process the collected water-rain monitoring data, and has a monitoring data compression model and a transmission path planning model deployed inside. The IoT communication module is used to access the IoT transmission network. In this embodiment, a wireless local area network authentication and privacy infrastructure (WLAN Authentication and Privacy Infrastructure, WAPI) module is used. The water-rain monitoring sensor is used to collect water-rain monitoring data. In this embodiment, a water level sensor, a rainfall sensor, an environmental temperature and humidity sensor, an environmental sunshine sensor, a water level monitoring camera, a rainfall monitoring camera and other components are provided to collect data in sequence format and image format.

[0066] S1-3: Based on the three-dimensional map data and the real-time location data and device performance parameters of several data acquisition devices in the IoT perception layer, several cascaded data transmission devices are deployed in the monitoring area to build the IoT transmission layer;

[0067] Limited by the device performance of the data acquisition device, the deployment of the data transmission device in the monitoring area needs to be carried out according to the principle of maximum network coverage and minimum device cost, and the cascade can connect different network segments to expand the coverage of the Internet of Things transmission network, ensuring that all data acquisition devices in the monitoring area can access the network, and through cascading, multiple data transmission paths can be established. Even if a certain path fails, data can be transmitted through other paths, thereby improving the reliability of the network; in this embodiment, the data transmission device adopts a WAPI module;

[0068] The IoT transmission layer of this embodiment adopts a multi-level chain structure connection, including multiple IoT transmission segments, each IoT transmission segment is provided with a number of data acquisition devices, and the data acquisition devices of each level are respectively connected to the data acquisition devices of the adjacent level;

[0069] S1-4: Distribute and connect each data collection device of the IoT perception layer to several data transmission devices of the IoT transmission layer close to the IoT perception layer, and connect several data transmission devices of the IoT transmission layer close to the cloud data center to the cloud data center;

[0070] The distributed connection method avoids the problem of data transmission failure due to the failure of a single data transmission device, improves the reliability of data transmission, and limits the data transmission device as the transmission intermediate point to directly connect to the cloud data center, avoids network congestion in the cloud data center, and improves transmission efficiency;

[0071] S2: The cloud data center uses artificial intelligence algorithms to build a three-dimensional digital twin model of the monitoring area, a water and rainfall monitoring data analysis model, a monitoring data compression model, and a transmission path planning model, and deploys the monitoring data compression model and the transmission path planning model to all data collection devices in the IoT perception layer, including the following steps:

[0072] S2-1: construct a three-dimensional simulation model of the monitoring area based on the three-dimensional map data of the monitoring area, and perform digital twin integration on the three-dimensional simulation model of the monitoring area to obtain a three-dimensional digital twin model of the monitoring area;

[0073] S2-2: Based on some historical water and rainfall monitoring data, use deep learning algorithms to build water and rainfall monitoring data analysis models and monitoring data compression models;

[0074] The monitoring data compression model is constructed based on a convolutional neural network (CNN)-long short-term memory network (LSTM)-deep belief network (DBN) algorithm, and the monitoring data compression model includes a first image data feature extraction module constructed based on the CNN algorithm, a first sequence data feature extraction module constructed based on the LSTM algorithm, and a monitoring data compression module constructed based on the DBN algorithm, and the monitoring data compression module is respectively connected to the first image data feature extraction module and the first sequence data feature extraction module;

[0075] The CNN network extracts hierarchical features of images through structures such as convolutional layers and pooling layers. The LSTM network realizes the memory function through the gate mechanism and can extract deep features of sequence data. The DBN network is a deep learning model, which consists of multiple restricted Boltzmann machine (RBM) layers and can learn the probability distribution of image features and sequence features. The encoding process involves converting sub-blocks into a set of compressed codewords, which are compact representations of data features. The DBN model can learn an effective representation of data features, thereby removing redundant information during the encoding process and achieving efficient compression. The encoding process of the DBN model can ensure that all information is retained so that the original data can be fully restored during decompression and complete data transmission can be achieved.

[0076] The water and rainfall monitoring data analysis model is constructed based on the Feature Pyramid Networks (FPN)-LSTM-Attention-Multilayer Perceptron (MLP)-Continuous Learning Algorithm (CLA) algorithm, and the water and rainfall monitoring data analysis model includes a second image data feature extraction module constructed based on the FPN algorithm, a second sequence data feature extraction module constructed based on the LSTM algorithm, an attention weight module constructed based on the Attention mechanism, a water and rainfall monitoring data analysis module constructed based on the MLP algorithm, and a continuous learning module constructed based on the CLA algorithm. The second image data feature extraction module and the second sequence data feature extraction module are both connected to the attention weight module, and the attention weight module, the water and rainfall monitoring data analysis module and the continuous learning module are connected in sequence, and the continuous learning module is provided with an experience playback pool;

[0077] The CNN algorithm is used to construct the basic network architecture of the second image feature extraction module; the basic network architecture includes alternately connected convolutional layers and pooling layers; through the alternating connection of convolutional layers and pooling layers, multi-scale feature maps can be effectively extracted from the image, local features of the image can be captured, and the spatial dimension of the features can be reduced through the pooling layer, while maintaining important feature information; the outputs of all convolutional layers are horizontally connected in a top-down order to obtain a feature pyramid, which is used to extract feature maps of image data at different scales, and multi-scale fusion is performed to obtain high-level image features; the attention weight module is used to perform weighted fusion of image features and sequence features according to the preset attention weight value, strengthen the representation of key features that affect the analysis results, and improve the accuracy of the analysis;

[0078] The experience replay pool is used to store the interactive experience of the water and rainfall monitoring data analysis model in the environment. These experiences are usually stored in the form of (s, a, r, s'), where s is the current state, the current model parameters of the water and rainfall monitoring data analysis model, a is the action taken, including model parameter adjustment, deletion, addition and other actions, r is the reward obtained, which is used to characterize the impact of the action on the state, and s' is the next state, that is, the state after the model parameters are adjusted during the training process;

[0079] Since the data in the experience replay pool is randomly drawn, it helps to break the correlation between consecutive experiences, thereby reducing the variance in model training. By reusing experience, the model can learn more from limited experience, which is especially useful in new tasks or when samples are scarce. Experience replay helps stabilize the learning process and reduce fluctuations during training. Regularly check the size of the experience replay pool. If it exceeds the preset capacity, remove some experience according to a certain strategy (such as priority sampling, longest unvisited).

[0080] Used for model training and strategy updating. The continuous learning module enables the model to continuously learn from new data to avoid forgetting old knowledge. The use of the experience replay pool can improve data utilization efficiency and reduce the model's dependence on specific data distribution. For new data, the CLA algorithm can help the model adjust its strategy in a timely manner to maintain the timeliness of the model.

[0081] S2-3: Collect the historical transmission paths of several historical water and rainfall monitoring data, and use the swarm intelligence optimization algorithm to build a transmission path planning model based on several historical transmission paths;

[0082] The transmission path planning model is constructed based on the Improved Sparrow Search Algorithm (ISSA) algorithm, and the transmission path planning model includes an initial solution generation module, an iterative optimization module and a transmission path decoding module which are connected in sequence;

[0083] S2-4: Obtain model metadata of the monitoring data compression model and the transmission path planning model, and send the model metadata to all data collection devices of the IoT perception layer through the IoT transmission layer;

[0084] S2-5: Each data collection device in the IoT perception layer reconstructs the model according to the model metadata to obtain a reconstructed monitoring data compression model and a reconstructed transmission path planning model;

[0085] S3: The current data collection device collects the real-time water and rainfall monitoring data of the current monitoring point, generates a corresponding real-time data transmission instruction, and sends the real-time data transmission instruction to the first data transmission device in the Internet of Things transmission layer;

[0086] S4: The current data collection device obtains the first real-time communication address returned by the first data transmission device, and uses the transmission path planning model to perform transmission path planning according to the first real-time communication address and the fixed communication address of the cloud data center to obtain a real-time transmission path, including the following steps:

[0087] S4-1: The current data collection device obtains the first real-time communication address returned by the first data transmission device, and inputs the first real-time communication address and the fixed communication address of the cloud data center into the transmission path planning model;

[0088] S4-2: using the initial solution generation module of the transmission path planning model, setting a solution vector according to the first real-time communication address and the fixed communication address, and initializing using the Circle chaotic mapping sequence according to the solution vector to generate several initial solutions;

[0089] The formula is:

[0090]

[0091] Where X' c is the initial ISSA individual of the Circle chaos map; X c * is the randomly generated initial ISSA individual, i.e. the initial solution;

[0092] The location of the initial solution is a transmission path of the second real-time communication address starting from the first real-time communication address and ending at the fixed communication address, including several intermediate data transmission devices, and because the transmission path generated by the Circle chaotic map is random and uniform, the diversity of the transmission path is improved, while avoiding the generation of singular individuals;

[0093] S4-3: Use the iterative optimization module of the transmission path planning model to iteratively optimize several initial solutions to obtain the optimal solution, including the following steps:

[0094] S4-3-1: Taking minimizing the transmission path cost as the optimization goal, according to the optimization goal, set the fitness function of the iterative optimization module, and set the algorithm parameters and maximum number of iterations of the ISSA algorithm;

[0095] The formula is:

[0096]

[0097] Where f(X) is the fitness value of ISSA individual X; A(X) is the transmission resource cost function of ISSA individual X; T(X) is the transmission time cost function of ISSA individual X; L(X) is the transmission distance cost function of ISSA individual X; α, β, are weight coefficients; X is the ISSA individual reference parameter;

[0098] S4-3-2: Use the fitness function to obtain the initial fitness values ​​of all initial ISSA populations, and sort the initial ISSA individuals according to the initial fitness values ​​to obtain the initial discoverers, initial joiners, and initial predators;

[0099] S4-3-3: Update the initial ISSA population to obtain an updated ISSA population; the updated ISSA population includes updated discoverers, updated joiners and updated predators;

[0100] The update formula of the discoverer is:

[0101]

[0102] In the formula, are the cth discoverer ISSA individuals of the t+1th and tth iterations respectively; iter max is the maximum number of iterations; ξ is a random number between 0 and 1; Q is a normally distributed random number; L is a 1×D matrix, all elements of which are 1; R2 is the warning value; ST is the safety threshold; c is the ISSA individual indicator; i is the update parameter;

[0103] The update formula for the joiner is:

[0104]

[0105] In the formula, are the cth joiner ISSA individuals in the t+1th and tth iterations respectively; The best position for the exposed person to occupy; is the current worst position; ξ is a random number between 0 and 1; L is a 1×D matrix whose elements are all 1 or -1; A + is the position update parameter; h is the total number of ISSA individuals;

[0106] The update formula of the predator is:

[0107]

[0108] In the formula, are the cth predator ISSA individuals of the t+1th and tth iterations respectively; δ is the step-size control parameter, and δ=a"·γ", a" is the convergence factor, γ" is a non-zero positive real number for step-size control; is the current best position; f c 、f g 、f w are the current, best and worst fitness of the ISSA individual respectively; γ is the minimum constant to prevent the denominator from being 0;

[0109]

[0110] In the formula, a" is the convergence factor; tanh(.) is the hyperbolic tangent function; t is the iteration indicator; t max is the maximum number of iterations; a max 、a min are the maximum and minimum values ​​of the convergence factor, respectively; λ is the decreasing rate parameter, k" is the decreasing period parameter, λ = -2π, k" = π;

[0111] S4-3-4: Use the dynamic reverse learning algorithm to perform dynamic reverse learning on the updated ISSA population to generate a dynamic reverse ISSA population;

[0112] The formula is:

[0113]

[0114] In the formula, is the ISSA individual with dynamic reverse; γ* is the decreasing inertia coefficient; ub is the upper limit of the search space; lb is the lower limit of the search space; For the updated ISSA entity;

[0115] S4-3-5: Using the fitness function, obtain the updated fitness values ​​of all ISSA individuals in the updated ISSA population and the dynamically reversed ISSA population, and obtain the optimal solution based on the updated fitness values;

[0116] S4-4: using the transmission path decoding module of the transmission path planning model, performing transmission path decoding on the solution vector of the optimal solution to obtain a real-time transmission path;

[0117] S5: The current data acquisition device uses the monitoring data compression model to compress the real-time water and rainfall monitoring data to obtain a real-time water and rainfall monitoring data compression package, and transmits the real-time water and rainfall monitoring data compression package to the cloud data center through the Internet of Things transmission layer based on the real-time transmission path, including the following steps:

[0118] S5-1: The current data acquisition device performs data analysis on the real-time water and rainfall monitoring data to obtain real-time water and rainfall monitoring image data and real-time water and rainfall monitoring sequence data;

[0119] S5-2: using a first image data feature extraction module of a monitoring data compression model to extract first real-time image data features of the real-time water and rainfall monitoring image data;

[0120] S5-3: using the first sequence data feature extraction module of the monitoring data compression model to extract the first real-time sequence data feature of the real-time water and rainfall monitoring sequence data;

[0121] S5-4: using the monitoring data compression module of the monitoring data compression model, dividing the first real-time image data feature and the first real-time sequence data feature into sub-blocks to obtain a plurality of real-time sub-blocks;

[0122] S5-5: Encode each real-time sub-block to obtain a number of real-time compressed codewords, and merge the real-time compressed codewords to obtain an initial real-time water and rainfall monitoring data compression package;

[0123] S5-6: post-processing the initial real-time water and rainfall monitoring data compression package to obtain a final real-time water and rainfall monitoring data compression package;

[0124] S5-6: Based on the real-time transmission path, the real-time water and rainfall monitoring data compression package is transmitted to the cloud data center through the corresponding data transmission devices in the Internet of Things transmission layer;

[0125] S6: The cloud data center decompresses the compressed package of the real-time water and rainfall monitoring data, uses the water and rainfall monitoring data analysis model to perform water and rainfall monitoring data analysis on the decompressed real-time water and rainfall monitoring data to obtain real-time water and rainfall analysis results, and updates the water and rainfall monitoring data analysis model to obtain an updated water and rainfall monitoring data analysis model, including the following steps:

[0126] S6-1: The cloud data center decompresses the compressed package of the real-time water and rainfall monitoring data to obtain the decompressed real-time water and rainfall monitoring data;

[0127] S6-2: performing data analysis on the decompressed real-time water and rainfall monitoring data to obtain decompressed real-time water and rainfall monitoring image data and decompressed real-time water and rainfall monitoring sequence data;

[0128] S6-3: using a second image data feature extraction module of the water and rainfall monitoring data analysis model to extract second real-time image data features of the decompressed real-time water and rainfall monitoring image data;

[0129] S6-4: using the second sequence data feature extraction module of the water and rainfall monitoring data analysis model to extract the second real-time sequence data features of the decompressed real-time water and rainfall monitoring sequence data;

[0130] S6-5: According to the preset attention weight, using the attention weight module of the water and rainfall monitoring data analysis model, weighted fusion is performed on the second real-time image data feature and the second real-time sequence data feature to obtain a real-time weighted fusion feature;

[0131] S6-6: Use the water-rain monitoring data analysis module of the water-rain monitoring data analysis model to analyze the water-rain monitoring data on the real-time weighted fusion features, obtain the real-time water-rain analysis results, and generate real-time water-rain monitoring data analysis experience;

[0132] The real-time water and rainfall analysis results include the real-time data analysis results of water and rainfall (precipitation: current and recent rainfall, including hourly rainfall, daily rainfall, etc., water level: real-time water level of water bodies such as rivers, lakes, and reservoirs, flow: real-time flow of rivers, channels, etc.), future trend analysis results of water and rainfall (rainfall trend: predict the trend of rainfall changes in the future, water level trend: predict the trend of water level changes, such as rising, falling or stable, flow trend: predict the trend of flow changes), water and rainfall disaster warning information (flood warning: issue different levels of flood warnings based on water level and rainfall forecasts, flash flood warning: warning information issued for flash flood prone areas, drought warning: drought warning issued when rainfall continues to be low), spatial distribution of water and rainfall (rainfall distribution map: display the spatial distribution of rainfall in the monitoring area, water level distribution map: display the spatial distribution of water levels at different monitoring points), water resources status analysis results (water storage capacity: water storage capacity analysis of reservoirs, lakes, etc., water resources supply and demand: analyze the supply and demand of water resources, and assess water shortage or surplus), etc.;

[0133] S6-7: randomly extract a number of historical water and rainfall monitoring data analysis experiences from the experience playback pool of the water and rainfall monitoring data analysis model, and mix them with the real-time water and rainfall monitoring data analysis experiences to obtain a number of mixed water and rainfall monitoring data analysis experiences;

[0134] S6-8: Based on the experience of analyzing several mixed water-rain monitoring data, the water-rain monitoring data analysis model is updated using the continuous learning module of the water-rain monitoring data analysis model to obtain an updated water-rain monitoring data analysis model;

[0135] S7: The cloud data center generates real-time water and rainfall warning signals based on the real-time water and rainfall analysis results, and uses the three-dimensional digital twin model of the monitoring area to visualize the decompressed real-time water and rainfall monitoring data of all monitoring points, as well as the corresponding real-time water and rainfall analysis results and real-time water and rainfall warning signals;

[0136] The three-dimensional digital twin model of the monitoring area improves the convenience and intuitiveness of real-time monitoring of water and rainfall conditions, making it easier for staff to discover and locate the location of water and rainfall disasters or the real-time water and rainfall conditions at each monitoring point.

[0137] Embodiment 2:

[0138] like Figure 2 As shown, this embodiment provides a real-time monitoring system for water and rainfall conditions based on the Internet of Things, which is used to implement a real-time monitoring method for water and rainfall conditions. The system includes a cloud data center, an Internet of Things perception layer, and an Internet of Things transmission layer connected in sequence. The Internet of Things perception layer includes several data acquisition devices, and the Internet of Things transmission layer includes several data transmission devices;

[0139] The cloud data center is used to use artificial intelligence algorithms to construct a three-dimensional digital twin model of the monitoring area, a water-rain monitoring data analysis model, a monitoring data compression model, and a transmission path planning model, and deploy the monitoring data compression model and the transmission path planning model to all data acquisition devices in the IoT perception layer; decompress the real-time water-rain monitoring data compression package, use the water-rain monitoring data analysis model to perform water-rain monitoring data analysis on the decompressed real-time water-rain monitoring data, obtain real-time water-rain analysis results, and update the water-rain monitoring data analysis model to obtain an updated water-rain monitoring data analysis model; generate a real-time water-rain alarm signal based on the real-time water-rain analysis results, and use the three-dimensional digital twin model of the monitoring area to visualize the decompressed real-time water-rain monitoring data of all monitoring points, as well as the corresponding real-time water-rain analysis results and real-time water-rain alarm signals;

[0140] The Internet of Things perception layer is used to use the current data collection device to collect the real-time water and rainfall monitoring data of the current monitoring point, generate corresponding real-time data transmission instructions, and send the real-time data transmission instructions to the first data transmission device in the Internet of Things transmission layer; use the monitoring data compression model to compress the real-time water and rainfall monitoring data to obtain a real-time water and rainfall monitoring data compression package, and send the real-time water and rainfall monitoring data compression package to the first data transmission device;

[0141] The Internet of Things transmission layer is used to use the first data transmission device to transmit the real-time water and rainfall monitoring data compression package to the cloud data center based on the real-time transmission path.

[0142] The invention discloses a real-time monitoring method and system for water and rainfall conditions based on the Internet of Things. The Internet of Things perception layer and the Internet of Things transmission layer are deployed to realize the real-time collection and transmission of water and rainfall monitoring data, eliminate time delay, expand the coverage of data collection and transmission devices, and enhance the real-time monitoring performance. Through the constructed water and rainfall monitoring data analysis model, the water and rainfall monitoring data are efficiently processed and accurately analyzed, and potential water and rainfall disasters can be discovered, thereby improving the accuracy of data analysis, ensuring a rapid response to water and rainfall disasters, and achieving a water and rainfall monitoring effect that meets the requirements. The Internet of Things perception layer and the Internet of Things transmission layer can cover a wider area, including remote and complex terrain areas, through the flexible deployment of Internet of Things devices, and adopt an efficient data compression model and a transmission path planning model to accelerate the data transmission speed and ensure real-time performance. The Internet of Things device is only responsible for data transmission, has high stability and self-maintenance capability, reduces maintenance cost and frequency, has low power consumption, reduces energy consumption, and is suitable for various environments.

[0143] The present invention is not limited to the above optional implementations, and anyone can derive other various forms of products under the enlightenment of the present invention. The above specific implementations should not be understood as limiting the scope of protection of the present invention. The scope of protection of the present invention should be based on the definition in the claims, and the description can be used to interpret the claims.

Claims

1. A real-time monitoring method of water and rainfall conditions based on the Internet of Things, characterized in that: The steps include: Deploy the IoT perception layer and IoT transmission layer for real-time monitoring of water and rainfall conditions in the monitoring area, and connect the IoT perception layer to the cloud data center through the IoT transmission layer; The cloud data center uses artificial intelligence algorithms to build a three-dimensional digital twin model of the monitoring area, a water and rainfall monitoring data analysis model, a monitoring data compression model, and a transmission path planning model, and deploys the monitoring data compression model and the transmission path planning model to all data collection devices in the IoT perception layer; The current data collection device collects the real-time water and rainfall monitoring data of the current monitoring point, generates a corresponding real-time data transmission instruction, and sends the real-time data transmission instruction to the first data transmission device in the Internet of Things transmission layer; The current data acquisition device obtains the first real-time communication address returned by the first data transmission device, and uses the transmission path planning model to perform transmission path planning according to the first real-time communication address and the fixed communication address of the cloud data center to obtain the real-time transmission path; The current data acquisition device uses a monitoring data compression model to compress the real-time water and rainfall monitoring data to obtain a real-time water and rainfall monitoring data compression package, and based on the real-time transmission path, transmits the real-time water and rainfall monitoring data compression package to the cloud data center through the Internet of Things transmission layer; The cloud data center decompresses the compressed package of the real-time water and rainfall monitoring data, uses the water and rainfall monitoring data analysis model to perform water and rainfall monitoring data analysis on the decompressed real-time water and rainfall monitoring data to obtain real-time water and rainfall analysis results, and updates the water and rainfall monitoring data analysis model to obtain an updated water and rainfall monitoring data analysis model; The cloud data center generates real-time water and rainfall alarm signals based on the real-time water and rainfall analysis results, and uses the three-dimensional digital twin model of the monitoring area to visualize the decompressed real-time water and rainfall monitoring data of all monitoring points, as well as the corresponding real-time water and rainfall analysis results and real-time water and rainfall alarm signals.

2. The method for real-time monitoring of water and rainfall conditions based on the Internet of Things according to claim 1 is characterized in that: Deploy the IoT perception layer and IoT transmission layer for real-time monitoring of water and rainfall conditions in the monitoring area, and connect the IoT perception layer to the cloud data center through the IoT transmission layer, including the following steps: Obtain three-dimensional map data of the monitoring area, as well as historical water and rainfall monitoring data and corresponding historical location data of several monitoring points for historical water and rainfall monitoring; According to the three-dimensional map data and the historical location data of several monitoring points, several data collection devices are deployed at the corresponding positions of the monitoring area to build the Internet of Things perception layer; According to the three-dimensional map data and the real-time location data and device performance parameters of several data collection devices in the IoT perception layer, several cascaded data transmission devices are deployed in the monitoring area to build the IoT transmission layer; Each data collection device of the IoT perception layer is connected to several data transmission devices of the IoT transmission layer close to the IoT perception layer in a distributed manner, and several data transmission devices of the IoT transmission layer close to the cloud data center are connected to the cloud data center.

3. The method for real-time monitoring of water and rainfall conditions based on the Internet of Things according to claim 2 is characterized in that: The cloud data center uses artificial intelligence algorithms to build a three-dimensional digital twin model of the monitoring area, a water and rainfall monitoring data analysis model, a monitoring data compression model, and a transmission path planning model, and deploys the monitoring data compression model and the transmission path planning model to all data collection devices in the IoT perception layer, including the following steps: According to the three-dimensional map data of the monitoring area, a three-dimensional simulation model of the monitoring area is constructed, and the three-dimensional simulation model of the monitoring area is integrated with the digital twin to obtain the three-dimensional digital twin model of the monitoring area; Based on some historical water and rainfall monitoring data, a deep learning algorithm is used to build a water and rainfall monitoring data analysis model and a monitoring data compression model; Collect the historical transmission paths of several historical water and rainfall monitoring data, and build a transmission path planning model based on several historical transmission paths using swarm intelligence optimization algorithm; Obtain model metadata of the monitoring data compression model and the transmission path planning model, and send the model metadata to all data collection devices of the IoT perception layer through the IoT transmission layer; Each data collection device in the perception layer of the Internet of Things reconstructs the model according to the model metadata to obtain a reconstructed monitoring data compression model and a reconstructed transmission path planning model.

4. The method for real-time monitoring of water and rainfall conditions based on the Internet of Things according to claim 3 is characterized in that: The monitoring data compression model is constructed based on the CNN-LSTM-DBN algorithm, and the monitoring data compression model includes a first image data feature extraction module constructed based on the CNN algorithm, a first sequence data feature extraction module constructed based on the LSTM algorithm, and a monitoring data compression module constructed based on the DBN algorithm. The monitoring data compression module is respectively connected to the first image data feature extraction module and the first sequence data feature extraction module.

5. The method for real-time monitoring of water and rainfall conditions based on the Internet of Things according to claim 4 is characterized in that: The water-rain monitoring data analysis model is constructed based on the FPN-LSTM-Attention-MLP-CLA algorithm, and the water-rain monitoring data analysis model includes a second image data feature extraction module constructed based on the FPN algorithm, a second sequence data feature extraction module constructed based on the LSTM algorithm, an attention weight module constructed based on the Attention mechanism, a water-rain monitoring data analysis module constructed based on the MLP algorithm, and a continuous learning module constructed based on the CLA algorithm. The second image data feature extraction module and the second sequence data feature extraction module are both connected to the attention weight module, and the attention weight module, the water-rain monitoring data analysis module and the continuous learning module are connected in sequence, and the continuous learning module is provided with an experience playback pool.

6. The method for real-time monitoring of water and rainfall conditions based on the Internet of Things according to claim 5 is characterized in that: The transmission path planning model is constructed based on the ISSA algorithm, and the transmission path planning model includes an initial solution generation module, an iterative optimization module and a transmission path decoding module which are connected in sequence.

7. The method for real-time monitoring of water and rainfall conditions based on the Internet of Things according to claim 6 is characterized by: The current data acquisition device obtains the first real-time communication address returned by the first data transmission device, and uses the transmission path planning model to perform transmission path planning according to the first real-time communication address and the fixed communication address of the cloud data center to obtain the real-time transmission path, including the following steps: The current data collection device obtains the first real-time communication address returned by the first data transmission device, and inputs the first real-time communication address and the fixed communication address of the cloud data center into the transmission path planning model; Using an initial solution generation module of a transmission path planning model, a solution vector is set according to the first real-time communication address and the fixed communication address, and a plurality of initial solutions are generated according to the solution vector; Use the iterative optimization module of the transmission path planning model to iteratively optimize several initial solutions to obtain the optimal solution; The transmission path decoding module of the transmission path planning model is used to decode the solution vector of the optimal solution to obtain a real-time transmission path.

8. The method for real-time monitoring of water and rainfall conditions based on the Internet of Things according to claim 7 is characterized in that: The current data acquisition device uses a monitoring data compression model to compress the real-time water and rainfall monitoring data to obtain a real-time water and rainfall monitoring data compression package, and transmits the real-time water and rainfall monitoring data compression package to a cloud data center through the Internet of Things transmission layer based on a real-time transmission path, including the following steps: The current data acquisition device performs data analysis on the real-time water and rainfall monitoring data to obtain real-time water and rainfall monitoring image data and real-time water and rainfall monitoring sequence data; Using a first image data feature extraction module of a monitoring data compression model, extracting first real-time image data features of real-time water and rainfall monitoring image data; Using the first sequence data feature extraction module of the monitoring data compression model, extracting the first real-time sequence data feature of the real-time water and rainfall monitoring sequence data; Using a monitoring data compression module of the monitoring data compression model, the first real-time image data feature and the first real-time sequence data feature are divided into sub-blocks to obtain a plurality of real-time sub-blocks; Encode each real-time sub-block to obtain a number of real-time compressed codewords, and merge the real-time compressed codewords to obtain an initial real-time water and rainfall monitoring data compression package; Post-processing the initial real-time water and rainfall monitoring data compression package to obtain the final real-time water and rainfall monitoring data compression package; Based on the real-time transmission path, the real-time water and rainfall monitoring data compression package is transmitted to the cloud data center through several corresponding data transmission devices in the Internet of Things transmission layer.

9. The method for real-time monitoring of water and rainfall conditions based on the Internet of Things according to claim 8, characterized in that: The cloud data center decompresses the compressed package of the real-time water and rainfall monitoring data, uses the water and rainfall monitoring data analysis model to perform water and rainfall monitoring data analysis on the decompressed real-time water and rainfall monitoring data to obtain real-time water and rainfall analysis results, and updates the water and rainfall monitoring data analysis model to obtain an updated water and rainfall monitoring data analysis model, including the following steps: The cloud data center decompresses the compressed package of the real-time water and rainfall monitoring data to obtain the decompressed real-time water and rainfall monitoring data; Performing data analysis on the decompressed real-time water and rainfall monitoring data to obtain decompressed real-time water and rainfall monitoring image data and decompressed real-time water and rainfall monitoring sequence data; Using the second image data feature extraction module of the water and rainfall monitoring data analysis model, extract the second real-time image data features of the decompressed real-time water and rainfall monitoring image data; Using the second sequence data feature extraction module of the water and rainfall monitoring data analysis model, extract the second real-time sequence data features of the decompressed real-time water and rainfall monitoring sequence data; According to the preset attention weight, the attention weight module of the water and rainfall monitoring data analysis model is used to weightedly fuse the second real-time image data feature and the second real-time sequence data feature to obtain a real-time weighted fusion feature; Use the water-rain monitoring data analysis module of the water-rain monitoring data analysis model to analyze the water-rain monitoring data on the real-time weighted fusion features, obtain the real-time water-rain analysis results, and generate real-time water-rain monitoring data analysis experience; Randomly extract a number of historical water and rainfall monitoring data analysis experiences from the experience playback pool of the water and rainfall monitoring data analysis model, and mix them with the real-time water and rainfall monitoring data analysis experiences to obtain a number of mixed water and rainfall monitoring data analysis experiences; According to the experience of analyzing several mixed water-rainfall monitoring data, the water-rainfall monitoring data analysis model is updated using the continuous learning module of the water-rainfall monitoring data analysis model to obtain an updated water-rainfall monitoring data analysis model.

10. A real-time monitoring system for water and rainfall conditions based on the Internet of Things, used to implement the real-time monitoring method for water and rainfall conditions as claimed in any one of claims 1 to 8, characterized in that: The system includes a cloud data center, an Internet of Things perception layer and an Internet of Things transmission layer connected in sequence. The Internet of Things perception layer includes several data acquisition devices, and the Internet of Things transmission layer includes several data transmission devices.

Images