Channel flow velocity monitoring method, system and equipment based on CSI (Channel State Information) and medium

By installing LoRa radio frequency modules on both sides of the river and using RISC-V processors, combined with CSI and machine learning models, the problem of poor accuracy of traditional river flow rate monitoring methods in harsh environments is solved, and high-precision and low-cost flow rate monitoring is achieved. Suitable for water resource management and ecological environment protection.

CN119064627APending Publication Date: 2024-12-03SHANDONG INSPUR SCI RES INST CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411195815.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-29
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

Traditional river flow rate monitoring methods are prone to damage in harsh environments, are heavily maintained, have poor measurement accuracy in complex flow fields, and are highly invasive in the equipment, making it difficult to adapt to complex environments.

Method used

Using CSI-based river flow rate monitoring method, LoRa radio frequency module is installed on both sides of the river, and the RISC-V processor is used to extract the position and speed of floating objects from the channel state information, calculate the flow rate of river channels, and combine machine learning models to identify the type and position of floating objects. , realize high-precision flow rate monitoring.

Benefits of technology

It realizes non-invasive, high-precision, and adaptable to complex environments. It overcomes the disadvantages of traditional methods and has the advantages of low cost, high efficiency and continuous real-time monitoring. It is suitable for water resource management and ecological environment protection.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119064627A_ABST
    Figure CN119064627A_ABST
Patent Text Reader

Abstract

The invention discloses a channel flow velocity monitoring method, system and device based on CSI and a medium, and relates to the technical field of flow velocity monitoring. In order to overcome the defects of an existing river flow velocity monitoring instrument, the adopted scheme comprises the steps that a plurality of radio frequency modules are installed on the two sides of a river, the radio frequency modules are configured, and an effective Fresnel area covering the whole monitoring area is constructed; each radio frequency module comprises an emitter and a receiver, the emitter sends a signal to a river channel, and the receiver captures the signal propagated through the river channel; based on the captured signal, the RISC-V processor completes the following operations: extracting channel state information, and identifying and outputting the type and position information of the floating object in the river channel by using a machine learning model; and calculating the accurate position of the floating object, and calculating the flow velocity of the floating object according to the position change of the floating object, thereby obtaining the river flow velocity. The monitoring precision can be improved, and the monitoring cost can be reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of flow rate monitoring, and in particular to a method, system, equipment and medium for monitoring river flow rate based on CSI. Background Art

[0002] The monitoring of river flow velocity is of great significance for water resources management, flood prevention and disaster reduction, water conservancy project design and ecological environment protection. Understanding the flow velocity of the river can help relevant departments better predict floods, manage water resources, protect the ecological environment and formulate relevant disaster prevention and mitigation measures.

[0003] Traditional methods of monitoring river flow velocity usually require the use of specialized instruments and equipment, such as flow meters, but these methods have some disadvantages. For example, underwater sensors require regular maintenance and calibration, especially in waters with severe silt deposition, corrosion and biological attachment, where maintenance work is more arduous; in harsh environments such as floods, ice or floating objects, underwater equipment is easily damaged, resulting in monitoring interruptions or data loss; traditional equipment may be disturbed by turbulence, eddies, etc. in complex flow fields, affecting measurement accuracy.

[0004] With the development of wireless technology, the monitoring method using wireless signals has gradually attracted attention. CSI (Channel State Information) is a fine-grained physical layer information of wireless signals. It is used to describe the channel properties of wireless communication links and reflects the attenuation factors of signals on the transmission path, such as signal scattering, environmental attenuation and distance attenuation, which provides new possibilities for river flow velocity monitoring. Summary of the invention

[0005] In view of the needs and deficiencies of current technological development, the present invention provides a river flow velocity monitoring method, system, equipment and medium based on CSI.

[0006] In the first aspect, the present invention provides a river flow velocity monitoring method based on CSI. The technical solution adopted to solve the above technical problems is as follows:

[0007] A river flow velocity monitoring method based on RISC-V and radio frequency, which forms multiple pairs of sensors by installing multiple LoRa transmitters and LoRa receivers on both sides of the river, captures the propagation path and changes of LoRa signals in the river, and uses channel state information for analysis and processing to determine the specific location of floating objects and calculate their speed;

[0008] The specific implementation process of the method is as follows:

[0009] S1. Install multiple LoRa radio frequency modules on both sides of the river, each LoRa radio frequency module includes a LoRa transmitter and a LoRa receiver;

[0010] S2. Configure the LoRa RF module, set the transmission frequency, transmission power and signal rate. Multiple LoRa RF modules form multiple pairs of sensor networks to build an effective Fresnel zone covering the entire monitoring area.

[0011] S3, the LoRa transmitter of each LoRa radio module sends a signal to the river channel, and the LoRa receiver captures the signal after it propagates through the river channel;

[0012] The S4, RISC-V processor extracts channel state information from the captured signal and loads and runs a pre-trained machine learning model. The machine learning model makes real-time predictions based on the signal state information and identifies and outputs the type and location information of floating objects in the river.

[0013] The S5, RISC-V processor calculates the precise location of floating objects based on the captured signals of multiple LoRa radio modules;

[0014] S6, RISC-V processor calculates the flow velocity of floating objects according to the position changes of floating objects, that is, the flow velocity of the river.

[0015] Optionally, for each LoRa radio frequency module installed on both sides of the river, between its LoRa transmitter and LoRa receiver, the signal forms an elliptical trajectory when propagating through multiple paths, and the area composed of the trajectories corresponding to the specified path difference related to the signal wavelength in these elliptical trajectories is the Fresnel zone;

[0016] The radius formula of the Fresnel zone circular cross section is:

[0017] |AQ n |+|Q n B|=|AB|+nε / 2,

[0018] In the formula, |AQ n |and|Q n B|represents the distance from transmitter A and receiver B to a point Q on the boundary of the nth Fresnel zone ellipse n distance, |AB| represents the straight-line distance between transmitter A and receiver B, ε represents the wavelength of the wireless signal, and n is the serial number of the Fresnel zone, indicating the nth Fresnel zone.

[0019] Optionally, step S4 specifically includes the following operations:

[0020] S4.1,RISC-V processor applies dynamic phase offset correction algorithm to the captured signal to eliminate the influence of environmental noise;

[0021] S4.2, the RISC-V processor extracts channel state information from the phase-corrected signal, which describes various properties of the signal during propagation;

[0022] S4.3. Using the power delay profile technology, the RISC-V processor further extracts the delay information from the channel state information, analyzes the signal changes in the Fresnel zone, and evaluates the propagation characteristics of the signal in the specified area;

[0023] S4.4. Use pre-collected labeled data containing different types and locations of floating objects to train a machine learning model that can identify the characteristics of different floating objects. The RISC-V processor extracts the channel state information and then loads and runs the machine learning model. The machine learning model identifies and outputs the type and location information of floating objects in the river.

[0024] Optionally, step S6 specifically includes the following operations:

[0025] S6.1. Record the location information of floating objects at different times (x 1 ,y 1 ) and (x 2 ,y 2 ), where x 1 and x 2 Indicates the x-axis coordinates of the floating object at the first and second moments, y 1 and 2 Indicates the y-axis coordinates of the floating object at the first moment and the second moment;

[0026] S6.2, calculating the time interval Δt between the first moment and the second moment;

[0027] S6.3. Calculate the Euclidean distance of position change

[0028] S6.4, according to the formula Calculate the velocity v of the floating object, which is the river flow velocity.

[0029] In the second aspect, the present invention provides a river flow velocity monitoring system based on CSI, and the technical solution adopted to solve the above technical problems is as follows:

[0030] A river flow rate monitoring system based on RISC-V and radio frequency, comprising a LoRa radio frequency module and a RISC-V processor, wherein:

[0031] LoRa RF modules are installed on both sides of the river. By configuring the LoRa RF modules and setting the transmission frequency, transmission power and signal rate, multiple LoRa RF modules form multiple pairs of sensor networks to build an effective Fresnel zone covering the entire monitoring area. Each LoRa RF module includes a LoRa transmitter and a LoRa receiver. The LoRa transmitter sends signals to the river, and the LoRa receiver captures the signals after propagation through the river.

[0032] Based on the captured signals, the RISC-V processor completes the following operations: extracting channel state information from the captured signals, using a pre-trained machine learning model to identify and output the type and location information of floating objects in the river; using the captured signals of multiple LoRa RF modules to calculate the precise location of the floating objects, and based on the position changes of the floating objects, calculating the flow speed of the floating objects, that is, obtaining the flow velocity of the river.

[0033] Optionally, between the LoRa transmitter and the LoRa receiver of the LoRa radio frequency module, an elliptical trajectory is formed when the signal propagates through multiple paths, and the area composed of the trajectories corresponding to the specified path differences related to the signal wavelength in these elliptical trajectories is the Fresnel zone;

[0034] The formula for the radius of the Fresnel zone circular section involved is:

[0035] |AQ n |+|Q n B|=|AB|+nε / 2,

[0036] In the formula, |AQ n |and|Q n B|represents the distance from transmitter A and receiver B to a point Q on the boundary of the nth Fresnel zone ellipse n distance, |AB| represents the straight-line distance between transmitter A and receiver B, ε represents the wavelength of the wireless signal, and n is the serial number of the Fresnel zone, indicating the nth Fresnel zone.

[0037] Optionally, the RISC-V processor extracts channel state information from the captured signal and uses a pre-trained machine learning model to identify the type and location information of floating objects in the output river, specifically including the following process:

[0038] The RISC-V processor applies a dynamic phase offset correction algorithm to the captured signal to eliminate the effects of ambient noise;

[0039] The RISC-V processor extracts channel state information from the phase-corrected signal, which describes various properties of the signal during propagation.

[0040] Using the power delay profile technology, the RISC-V processor further extracts the delay information from the channel state information and analyzes the signal changes in the Fresnel zone to evaluate the propagation characteristics of the signal in the specified area;

[0041] A machine learning model capable of identifying the characteristics of different floating objects is trained using pre-collected labeled data containing different types and locations of floating objects. The RISC-V processor extracts the channel state information and loads and runs the machine learning model. The machine learning model identifies and outputs the type and location information of floating objects in the river.

[0042] Optionally, the RISC-V processor involved calculates the flow velocity of the floating object according to the position change of the floating object, that is, obtains the river flow velocity, which specifically includes the following process:

[0043] Record the location information of floating objects at different times (x 1 ,y 1 ) and (x 2 ,y 2 ), where x 1 and x 2 Indicates the x-axis coordinates of the floating object at the first and second moments, y 1 and 2 Indicates the y-axis coordinates of the floating object at the first moment and the second moment;

[0044] Calculate the time interval Δt between the first moment and the second moment;

[0045] Calculate the Euclidean distance of position change

[0046] According to the formula Calculate the velocity v of the floating object, which is the river flow velocity.

[0047] In a third aspect, the present invention further provides an electronic device, comprising: a memory and at least one processor;

[0048] Wherein, the memory stores a computer program;

[0049] The at least one processor executes the computer program stored in the memory, so that the at least one processor executes the river flow velocity monitoring method based on RISC-V and radio frequency as described in the first aspect.

[0050] In a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program, which can be executed by a processor to implement the river flow velocity monitoring method based on RISC-V and radio frequency as described in the first aspect.

[0051] Compared with the prior art, the CSI-based river flow velocity monitoring method, system, device and medium of the present invention have the following beneficial effects:

[0052] The present invention has the advantages of non-invasive equipment, high-precision flow rate monitoring, adaptability to complex environments, versatility, low cost and high efficiency, and continuous real-time monitoring. It overcomes many disadvantages of traditional methods and has broad application prospects and significant social benefits. It not only plays an important role in water resources management and ecological environment protection, but also provides new directions and ideas for future water environment monitoring technologies. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Attached Figure 1 is a flow chart of a method according to Embodiment 1 of the present invention;

[0054] Attached Figure 2 It is a schematic diagram of the river flow direction and LoRa signal propagation in the present invention;

[0055] Attached Figure 3 It is a schematic diagram of the Fresnel zone formed by a LoRa radio frequency module in the present invention. DETAILED DESCRIPTION

[0056] In order to make the technical solution, the technical problem solved and the technical effect of the present invention more clearly understood, the technical solution of the present invention is clearly and completely described below in conjunction with specific embodiments.

[0057] Embodiment 1:

[0058] This embodiment proposes a river flow velocity monitoring method based on RISC-V and radio frequency. Multiple LoRa transmitters and LoRa receivers are installed on both sides of the river to form multiple pairs of sensors. The propagation path and changes of LoRa signals in the river are captured, and the channel state information is used for analysis and processing to determine the specific location of floating objects and calculate their speed.

[0059] Combined with Figure 1 The specific implementation process of the river flow velocity monitoring method described in this embodiment is as follows:

[0060] S1. Install multiple LoRa radio frequency modules on both sides of the river. Each LoRa radio frequency module includes a LoRa transmitter and a LoRa receiver.

[0061] S2. Configure the LoRa RF module, set the transmission frequency, transmission power and signal rate. Multiple LoRa RF modules form multiple pairs of sensor networks to build an effective Fresnel zone covering the entire monitoring area.

[0062] In wireless communications, the Fresnel zone refers to an area around a direct path where obstacles affect signal propagation. According to the Fresnel zone model, the area between each pair of transmitters and receivers in the signal propagation path is divided into multiple Fresnel zones. The signal attenuation and phase change in different Fresnel zones are different. When an object (such as a floating object) enters the Fresnel zone, it will cause a significant change in the channel state information.

[0063] Combined with Figure 2 , 3 , in the absence of floating objects, it is assumed that the receiver receives a total of n reflection paths. Since the positions of the transmitter and receiver are fixed, the transmission distance of the signal can be determined based on the attenuation characteristics of the LoRa signal. Use this information to construct n concentric ellipses. When floating objects enter the concentric ellipse area, the absorption and blocking of the LoRa signal will cause the power of the corresponding reflection path or LoS path to decrease, thereby determining whether the target is within the test area, and further determining which two concentric ellipses the target is located between. The signal propagation area can be characterized by a series of concentric ellipsoidal areas along the transceiver link, which is called the Fresnel zone.

[0064] The formula for the radius of the Fresnel zone circular cross section is:

[0065] |AQ n |+|Q n B|=|AB|+nε / 2,

[0066] In the formula, |AQ n |and|Q n B|represents the distance from transmitter A and receiver B to a point Q on the boundary of the nth Fresnel zone ellipse n distance, |AB| represents the straight-line distance between transmitter A and receiver B, ε represents the wavelength of the wireless signal, and n is the serial number of the Fresnel zone, indicating the nth Fresnel zone.

[0067] One point that needs to be added is that in order to construct an effective Fresnel zone covering the entire monitoring area, the placement of each LoRa RF module needs to be accurately calculated. Ideally, each LoRa transmitter can communicate effectively with at least one LoRa receiver. This requires a detailed investigation of the topography, width, and specific environment of the river channel. For example, in areas with wider rivers or more complex terrain, in addition to more dense module deployment, the transmission frequency, transmission power, and signal rate can also be changed.

[0068] S3. The LoRa transmitter of each LoRa radio module sends a signal into the river channel, and the LoRa receiver captures the signal after propagating through the river channel.

[0069] S4, RISC-V processor extracts channel status information from the captured signal and loads and runs the pre-trained machine learning model. The machine learning model performs real-time prediction based on the signal status information and identifies and outputs the type and location information of floating objects in the river. The specific operations include the following:

[0070] S4.1,RISC-V processor applies dynamic phase offset correction algorithm to the captured signal to eliminate the influence of environmental noise;

[0071] S4.2, the RISC-V processor extracts channel state information from the phase-corrected signal, which describes various properties of the signal during propagation;

[0072] S4.3. Using the power delay profile technology, the RISC-V processor further extracts the delay information from the channel state information, analyzes the signal changes in the Fresnel zone, and evaluates the propagation characteristics of the signal in the specified area;

[0073] S4.4. Use pre-collected labeled data containing different types and locations of floating objects to train a machine learning model that can identify the characteristics of different floating objects. The RISC-V processor extracts the channel state information and then loads and runs the machine learning model. The machine learning model identifies and outputs the type and location information of floating objects in the river.

[0074] The S5 and RISC-V processors calculate the precise location of floating objects based on the captured signals from multiple LoRa radio frequency modules.

[0075] S6, RISC-V processor calculates the flow velocity of floating objects according to the position change of floating objects, that is, the flow velocity of the river, which specifically includes the following operations:

[0076] S6.1. Record the location information of floating objects at different times (x 1 ,y 1 ) and (x 2 ,y 2 ), where x 1 and x 2 Indicates the x-axis coordinates of the floating object at the first and second moments, y 1 and 2 Indicates the y-axis coordinates of the floating object at the first moment and the second moment;

[0077] S6.2, calculating the time interval Δt between the first moment and the second moment;

[0078] S6.3. Calculate the Euclidean distance of position change

[0079] S6.4, according to the formula Calculate the velocity v of the floating object, which is the river flow velocity.

[0080] Embodiment 2:

[0081] Reference Figure 1 , this embodiment proposes a river flow rate monitoring system based on RISC-V and radio frequency, which includes a LoRa radio frequency module and a RISC-V processor, wherein:

[0082] LoRa RF modules are installed on both sides of the river. By configuring the LoRa RF modules and setting the transmission frequency, transmission power and signal rate, multiple LoRa RF modules form multiple pairs of sensor networks to build an effective Fresnel zone covering the entire monitoring area. Each LoRa RF module includes a LoRa transmitter and a LoRa receiver. The LoRa transmitter sends signals to the river, and the LoRa receiver captures the signals after propagation through the river.

[0083] Based on the captured signals, the RISC-V processor completes the following operations: extracting channel state information from the captured signals, using a pre-trained machine learning model to identify and output the type and location information of floating objects in the river; using the captured signals of multiple LoRa RF modules to calculate the precise location of the floating objects, and based on the position changes of the floating objects, calculating the flow speed of the floating objects, that is, obtaining the flow velocity of the river.

[0084] Combined with Figure 2 , 3 In this embodiment, between the LoRa transmitter and the LoRa receiver of the LoRa radio frequency module, an elliptical trajectory is formed when the signal propagates through multiple paths, and the area composed of the trajectories corresponding to the specified path differences related to the signal wavelength in these elliptical trajectories is the Fresnel zone;

[0085] The formula for the radius of the Fresnel zone circular section involved is:

[0086] |AQ n |+|Q n B|=|AB|+nε / 2,

[0087] In the formula, |AQ n |and|Q n B|represents the distance from transmitter A and receiver B to a point Q on the boundary of the nth Fresnel zone ellipse n distance, |AB| represents the straight-line distance between transmitter A and receiver B, ε represents the wavelength of the wireless signal, and n is the serial number of the Fresnel zone, indicating the nth Fresnel zone.

[0088] In this embodiment, the RISC-V processor extracts channel state information from the captured signal and uses a pre-trained machine learning model to identify the type and location information of floating objects in the output river, which specifically includes the following process:

[0089] The RISC-V processor applies a dynamic phase offset correction algorithm to the captured signal to eliminate the effects of ambient noise;

[0090] The RISC-V processor extracts channel state information from the phase-corrected signal, which describes various properties of the signal during propagation.

[0091] Using the power delay profile technology, the RISC-V processor further extracts the delay information from the channel state information and analyzes the signal changes in the Fresnel zone to evaluate the propagation characteristics of the signal in the specified area;

[0092] A machine learning model capable of identifying the characteristics of different floating objects is trained using pre-collected labeled data containing different types and locations of floating objects. The RISC-V processor extracts the channel state information and loads and runs the machine learning model. The machine learning model identifies and outputs the type and location information of floating objects in the river.

[0093] In this embodiment, the RISC-V processor calculates the flow velocity of the floating object according to the position change of the floating object, that is, obtains the river flow velocity, which specifically includes the following process:

[0094] Record the location information of floating objects at different times (x 1 ,y 1 ) and (x 2 ,y 2 ), where x 1 and x 2 Indicates the x-axis coordinates of the floating object at the first and second moments, y 1 and 2 Indicates the y-axis coordinates of the floating object at the first moment and the second moment;

[0095] Calculate the time interval Δt between the first moment and the second moment;

[0096] Calculate the Euclidean distance of position change

[0097] According to the formula Calculate the velocity v of the floating object, which is the river flow velocity.

[0098] Embodiment three:

[0099] This embodiment provides an electronic device, including: a memory and at least one processor;

[0100] Wherein, the memory stores a computer program;

[0101] The at least one processor executes the computer program stored in the memory, so that the at least one processor executes the river flow velocity monitoring method based on RISC-V and radio frequency as described in Example 1.

[0102] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor may be a microprocessor or any conventional processor, etc.

[0103] The memory can be used to store computer programs and / or modules. The processor realizes various functions of the electronic device by running or executing the computer programs and / or modules stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; the data storage area can store data created according to the use of the terminal, etc. In addition, the memory can also include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (SMC), a secure digital (SD) card, a flash memory card, at least one disk storage period, a flash memory device, or other volatile solid-state storage devices.

[0104] Embodiment 4:

[0105] This embodiment proposes a computer-readable storage medium storing a computer program, which can be executed by a processor to implement the river flow velocity monitoring method based on RISC-V and radio frequency as described in Example 1. Specifically, a system or device equipped with a storage medium can be provided, on which a software program code for implementing the method described in Example 1 is stored, and a computer (or CPU or MPU) of the system or device reads and executes the program code stored in the storage medium.

[0106] In this case, the program code itself read from the storage medium can realize the function of any one of the above-mentioned embodiments, and thus the program code and the storage medium storing the program code constitute a part of the present invention.

[0107] The storage medium embodiments for providing the program code include a floppy disk, a hard disk, a magneto-optical disk, an optical disk (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RYM, DVD-RW, DVD+RW), a magnetic tape, a non-volatile memory card, and a ROM. Alternatively, the program code can be downloaded from a server computer via a communication network.

[0108] In addition, it should be clear that the functions of any of the above embodiments can be implemented not only by executing the program code read by the computer, but also by enabling an operating system operating on the computer to complete part or all of the actual operations based on instructions from the program code.

[0109] In addition, it can be understood that the program code read from the storage medium is written to a memory provided in an expansion board inserted into the computer or written to a memory provided in an expansion unit connected to the computer, and then based on the instructions of the program code, a CPU installed on the expansion board or the expansion unit is enabled to perform part or all of the actual operations, thereby realizing the functions of any of the above-mentioned embodiments.

[0110] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A river flow velocity monitoring method based on CSI, characterized in that: By installing multiple LoRa transmitters and LoRa receivers on both sides of the river to form multiple pairs of sensors, the propagation path and changes of LoRa signals in the river are captured, and the channel state information is used for analysis and processing to determine the specific location of floating objects and calculate their speed; The specific implementation process of the method is as follows: S1. Install multiple LoRa radio frequency modules on both sides of the river, each LoRa radio frequency module includes a LoRa transmitter and a LoRa receiver; S2. Configure the LoRa RF module, set the transmission frequency, transmission power and signal rate. Multiple LoRa RF modules form multiple pairs of sensor networks to build an effective Fresnel zone covering the entire monitoring area. S3, the LoRa transmitter of each LoRa radio module sends a signal to the river channel, and the LoRa receiver captures the signal after it propagates through the river channel; The S4, RISC-V processor extracts channel state information from the captured signal and loads and runs a pre-trained machine learning model. The machine learning model makes real-time predictions based on the signal state information and identifies and outputs the type and location information of floating objects in the river. The S5, RISC-V processor calculates the precise location of floating objects based on the captured signals of multiple LoRa radio modules; S6, RISC-V processor calculates the flow velocity of floating objects according to the position changes of floating objects, that is, the flow velocity of the river.

2. The method for monitoring river flow velocity based on CSI according to claim 1, characterized in that: For each LoRa RF module installed on both sides of the river, between its LoRa transmitter and LoRa receiver, the signal forms an elliptical trajectory when propagating through multiple paths. The area composed of the trajectories corresponding to the specified path difference related to the signal wavelength in these elliptical trajectories is the Fresnel zone; The radius formula of the Fresnel zone circular cross section is: |AQ n |+|Q n B|=|AB|+nε / 2, In the formula, |AQ n |and|Q n B|represents the distance from transmitter A and receiver B to a point Q on the boundary of the nth Fresnel zone ellipse n distance, |AB| represents the straight-line distance between transmitter A and receiver B, ε represents the wavelength of the wireless signal, and n is the serial number of the Fresnel zone, indicating the nth Fresnel zone.

3. The method for monitoring river flow velocity based on CSI according to claim 1, characterized in that: The step S4 specifically includes the following operations: S4.1,RISC-V processor applies dynamic phase offset correction algorithm to the captured signal to eliminate the influence of environmental noise; S4.2, the RISC-V processor extracts channel state information from the phase-corrected signal, which describes various properties of the signal during propagation; S4.

3. Using the power delay profile technology, the RISC-V processor further extracts the delay information from the channel state information, analyzes the signal changes in the Fresnel zone, and evaluates the propagation characteristics of the signal in the specified area; S4.

4. Use pre-collected labeled data containing different types and locations of floating objects to train a machine learning model that can identify the characteristics of different floating objects. The RISC-V processor extracts the channel state information and then loads and runs the machine learning model. The machine learning model identifies and outputs the type and location information of floating objects in the river.

4. The method for monitoring river flow velocity based on CSI according to claim 1, characterized in that: The step S6 specifically includes the following operations: S6.

1. Record the position information (x1, y1) and (x2, y2) of the floating object at different times, wherein x1 and x2 represent the x-axis coordinates of the floating object at the first time and the second time, and y1 and y2 represent the y-axis coordinates of the floating object at the first time and the second time; S6.2, calculating the time interval Δt between the first moment and the second moment; S6.

3. Calculate the Euclidean distance of position change S6.4, according to the formula Calculate the velocity v of the floating object, which is the river flow velocity.

5. A river flow velocity monitoring system based on CSI, characterized in that: It includes a LoRa radio frequency module and a RISC-V processor, including: LoRa RF modules are installed on both sides of the river. By configuring the LoRa RF modules and setting the transmission frequency, transmission power and signal rate, multiple LoRa RF modules form multiple pairs of sensor networks to build an effective Fresnel zone covering the entire monitoring area. Each LoRa RF module includes a LoRa transmitter and a LoRa receiver. The LoRa transmitter sends signals to the river, and the LoRa receiver captures the signals after propagation through the river. Based on the captured signals, the RISC-V processor completes the following operations: extracting channel state information from the captured signals, using a pre-trained machine learning model to identify and output the type and location information of floating objects in the river; using the captured signals of multiple LoRa RF modules to calculate the precise location of the floating objects, and based on the position changes of the floating objects, calculating the flow speed of the floating objects, that is, obtaining the flow velocity of the river.

6. The CSI-based river flow monitoring system according to claim 5, characterized in that: Between the LoRa transmitter and the LoRa receiver of the LoRa RF module, the signal forms an elliptical trajectory when propagating through multiple paths. The area composed of the trajectories corresponding to the specified path differences related to the signal wavelength in these elliptical trajectories is the Fresnel zone; The radius formula of the Fresnel zone circular cross section is: |AQ n |+|Q n B|=|AB|+nε / 2, In the formula, |AQ n |and|Q n B|represents the distance from transmitter A and receiver B to a point Q on the boundary of the nth Fresnel zone ellipse n distance, |AB| represents the straight-line distance between transmitter A and receiver B, ε represents the wavelength of the wireless signal, and n is the serial number of the Fresnel zone, indicating the nth Fresnel zone.

7. The CSI-based river flow monitoring system according to claim 5, characterized in that: The RISC-V processor extracts channel state information from the captured signal and uses a pre-trained machine learning model to identify the type and location information of floating objects in the output river, specifically including the following process: The RISC-V processor applies a dynamic phase offset correction algorithm to the captured signal to eliminate the effects of ambient noise; The RISC-V processor extracts channel state information from the phase-corrected signal, which describes various properties of the signal during propagation. Using the power delay profile technology, the RISC-V processor further extracts the delay information from the channel state information and analyzes the signal changes in the Fresnel zone to evaluate the propagation characteristics of the signal in the specified area; A machine learning model capable of identifying the characteristics of different floating objects is trained using pre-collected labeled data containing different types and locations of floating objects. The RISC-V processor extracts the channel state information and loads and runs the machine learning model. The machine learning model identifies and outputs the type and location information of floating objects in the river.

8. The CSI-based river flow velocity monitoring system according to claim 5, characterized in that: The RISC-V processor calculates the flow velocity of the floating object according to the position change of the floating object, that is, obtains the river flow velocity, which specifically includes the following process: Record the position information (x1, y1) and (x2, y2) of the floating object at different times, where x1 and x2 represent the x-axis coordinates of the floating object at the first time and the second time, and y1 and y2 represent the y-axis coordinates of the floating object at the first time and the second time; Calculate the time interval Δt between the first moment and the second moment; Calculate the Euclidean distance of position change According to the formula Calculate the velocity v of the floating object, which is the river flow velocity.

9. An electronic device, characterized in that: include: memory and at least one processor; Wherein, the memory stores a computer program; The at least one processor executes the computer program stored in the memory, so that the at least one processor performs the river flow velocity monitoring method based on CSI as described in any one of claims 1 to 4.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which can be executed by a processor to implement the CSI-based river flow velocity monitoring method as described in any one of claims 1 to 4.