A machine learning-based intelligent fishway operation and maintenance method and operation and maintenance system

Abstract

The application discloses a kind of wisdom fishway operation and maintenance method and operation and maintenance system based on machine learning, its method includes: obtaining monitoring point coordinate information and corresponding water level monitoring information;Wireless network transmits water level monitoring information to data receiving unit, and data operating unit calculates the water level calculation information data corresponding to pool room monitoring point;According to different boundary conditions, the mapping coefficient of water level monitoring information and water level calculation information data is determined, and comparison matching is carried out;When the difference exceeds the preset threshold, data operating unit uses machine learning algorithm, and successively determines the damage or obstacle blocking position of each fishway pool room, and corrects the monitoring point coordinate and water level calculation information data of corresponding pool room;Operation and maintenance prompt unit transmits the damage and obstacle blocking condition in fishway pool room to monitoring terminal, and carries out operation and maintenance processing measure.The present application can realize the practical demand that fishway is long-term sustainable operation and plays the best ecological benefit.

Description

Technical Field

[0001] This invention relates to the field of water conservancy engineering technology, and in particular to a smart fishway operation and maintenance system and its operation and maintenance method. Background Technology

[0002] Fishways, as an effective means of connecting upstream and downstream water flow at sluices and dams and providing passageways for fish to migrate upstream and downstream, have long been used as an important measure for fish protection in water conservancy and hydropower projects. However, due to the immaturity of fishway engineering technology in China, newly built fishways rarely achieve the expected fish passage efficiency. In reality, many fishways lose their original ecological functions due to a lack of regular maintenance and inspection. Numerous problems have been exposed in the monitoring, management, and maintenance of fishways. For example, sediment accumulation or blockage of obstacles in fishways can affect the orifices of bottom-hole pool-type fishways, seriously affecting the efficiency of fish passage and even causing the fishway to fail. Furthermore, in some fishways, about one-third of the fishway above the inlet is destroyed, and a sand dune forms at the outlet, isolating it from the main river channel, resulting in the loss of fishway function.

[0003] Therefore, there is an urgent need for a solution that can accurately determine the malfunction of fish passages, overcome the limitations of manual monitoring and the difficulties of remote operation and maintenance, and realize the practical need for long-term sustainable operation of fish passages and maximize their ecological benefits. Summary of the Invention

[0004] The technical problem to be solved by this invention is to provide a smart fishway operation and maintenance method based on machine learning, which can overcome the limitations of manual monitoring and the difficulties of remote operation and maintenance, and realize the practical needs of long-term sustainable operation of fishways and maximize the ecological benefits of fishways.

[0005] To solve the above-mentioned technical problems, the present invention adopts the following technical solution:

[0006] The intelligent fishway operation and maintenance method based on machine learning proposed in this invention includes the following steps:

[0007] S1. Use a water level sensor to obtain the coordinate information of the monitoring points in the pool and the corresponding water level monitoring information, and define them as the first set; define several different boundary conditions and the first set under these conditions as the second set.

[0008] S2. Using boundary condition variables as initial inputs and basic parameters of the fishway and pool chamber as constraints, the read coordinate information of the monitoring points is used as independent variables to calculate the water level information data corresponding to the monitoring points in the pool chamber. This data and the corresponding coordinate information of the monitoring points in the pool chamber are used to construct a third set. When the upstream boundary conditions change, the third set will be calculated and updated simultaneously.

[0009] S3. Determine the mapping coefficients between the second set and the third set based on different boundary conditions, and compare and match the data in the second set and the data in the third set.

[0010] The determination of the mapping coefficient mainly depends on the fish passage tank itself and related operating conditions. If the fish passage is large and the operating boundary conditions are stable, the mapping coefficient can be more lenient; if the fish passage is small and more sensitive to changes in boundary conditions, the mapping coefficient should be more stringent.

[0011] S4. Based on the comparison and matching results in step S3, determine the degree of difference between the two sets, and perform the following actions according to the relationship between the degree of difference and the preset threshold:

[0012] (1) If the difference meets the preset threshold, no warning is required;

[0013] (2) If the difference exceeds the preset threshold, the abnormal element data in the second set and the third set are filtered to form the fourth set, and the data in the fourth set are divided into several subsets according to the number of fish passage pools, which are then used as the fifth set and sorted.

[0014] S5. Using machine learning algorithms, determine the location of damage or obstruction in the fishway pool corresponding to each subset in the fifth set, and correct the monitoring point coordinates and water level calculation information of the corresponding pool until the last subset is corrected.

[0015] S6. Transmit the damage and obstruction status of the fishway pool interior determined in step S5 to the monitoring terminal, and the maintenance personnel shall take maintenance measures for the abnormal locations inside the fishway.

[0016] Furthermore, the specific formula for calculating the water level information data of the monitoring points in the pool chamber in step S2 is as follows:

[0017]

[0018] Where: H(x) i ,y i The coordinates of the monitoring point in the i-th chamber are (x, y). i ,y i Water level information data at point Q i For the flow rate entering the i-th pool chamber, D x D y The length of the i-th pool chamber is divided into its transverse and longitudinal lengths, V. i H(x) i ,y i The average flow velocity at the cross section where the monitoring point is located, x i ,y i H(x) i ,yi The horizontal and vertical distances of the monitoring point from the origin of the i-th pool chamber.

[0019] Furthermore, in step S2, the water level information data is calculated, and the flow rate Q when entering the i-th pool chamber is... i The calculation method is as follows:

[0020]

[0021]

[0022] Where Cs is the flow coefficient, h1 is the upstream water level of the i-th pool chamber minus the height of the bottom sill of a single pool chamber, g is the gravitational acceleration; β0, β1 are fishway correction coefficients, which are related to the fishway slope and the structure of the pool chamber, respectively, and h2 is the downstream water level of the i-th pool chamber minus the height of the bottom sill of a single pool chamber.

[0023] Furthermore, in step S4, a preset threshold Δh is defined. i Determined by the following formula:

[0024]

[0025] in, D represents the average inlet flow rate of the target fishway; x D y It is divided into the lateral length and longitudinal length of the i-th pool chamber; S is the slope of the target fishway; λ is the threshold correction coefficient, which is usually taken as 0.05.

[0026] Furthermore, the specific steps of step S5 are as follows:

[0027] Extract the coordinate information of abnormal pool room monitoring points from the first subset of the fifth set, and use machine learning algorithms to determine the location of damage or blockage of fishway pool rooms corresponding to the first subset. At the same time, correct the coordinates of abnormal pool room monitoring points and water level monitoring data in the first subset.

[0028] The elements in the corrected first subset are used as initial conditions to calculate the coordinates of the monitoring points and the water level information in the next pool chamber. This data is then compared and matched with the second subset in the fifth set to re-determine the location of any damage or blockage in the fishway pool chamber and make corrections.

[0029] This process continues until the last subset is corrected.

[0030] Furthermore, in step S5, machine learning algorithms are used to determine whether there is damage or blockage in the fishway. The specific method is as follows:

[0031] S501. Determine the geometric characteristics of the fishway;

[0032] S502. Modify the Cs flow coefficient in the water level information data calculation method for different operation and maintenance situations, and calculate the water level information under different monitoring point coordinates.

[0033] S503: Remove datasets with smaller obstacle sizes and less damage, and continuously train and validate the remaining datasets.

[0034] Furthermore, this invention proposes a machine learning-based intelligent fishway operation and maintenance system to implement the steps of the machine learning-based intelligent fishway operation and maintenance method described above, including a water level sensor module, a wireless network module, a power supply module, and a central control platform:

[0035] The water level sensor module consists of several ultrasonic sensors, which are used to accurately sense the water level information data of monitoring points inside each pool chamber in the fish passage.

[0036] The wireless network module is used to receive water level information data from monitoring points in various chambers inside the fishway transmitted by the water level sensor module, and upload the monitoring point data and corresponding water level information data to the central control platform.

[0037] The power supply module is used to supply power to the water level sensor module, the wireless network module, and the central control platform.

[0038] The central control platform consists of a data receiving unit, a data processing unit, a data operation unit, and an operation and maintenance prompt unit. The data receiving unit receives water level information data of the fish passage in the pool room transmitted by the water level sensor module through the wireless network module. The data processing unit preprocesses the received data. The data operation unit compares the actual water level of the fish passage with the theoretical water level. The operation and maintenance prompt unit provides operation and maintenance prompts based on the operation results.

[0039] Furthermore, the data receiving unit is configured to perform the following actions: acquire the coordinate information of the monitoring points in the pool and the corresponding water level monitoring information, and define them as a first set; define several different boundary conditions and the first set under these conditions as a second set.

[0040] The data processing unit is configured to perform the following actions: receive water level information data from the fishway in the pool chamber from the data receiving unit; calculate the water level calculation information data corresponding to the monitoring point in the pool chamber, and define this data and the corresponding coordinate information of the monitoring point in the pool chamber as a third set; determine the mapping coefficient between the second set and the third set, and compare and match the data in the second set and the data in the third set; determine the degree of difference between the two sets based on the comparison and matching results, and perform the following actions based on the relationship between the degree of difference and a preset threshold:

[0041] (1) If the difference meets the preset threshold, no warning is required.

[0042] (2) If the difference exceeds the preset threshold, the abnormal element data in the second set and the third set are filtered to form the fourth set, and the data in the fourth set are divided into several subsets according to the number of fish passage pools, which are then used as the fifth set and sorted.

[0043] The data processing unit is configured to perform the following actions: using a machine learning algorithm, sequentially determining the location of damage or obstruction in the fishway pool corresponding to each subset in the fifth set, and correcting the monitoring point coordinates and water level calculation information data of the corresponding pool, until the last subset is corrected.

[0044] The maintenance notification unit is configured to perform the following actions: transmit the damage and obstruction status of the fishway pool room determined by the data operation unit to the monitoring terminal, and carry out maintenance handling measures.

[0045] Furthermore, the present invention also proposes an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the steps of the machine learning-based intelligent fishway operation and maintenance method described above.

[0046] The present invention adopts the above technical solution, and its significant technical effects compared with the prior art are as follows:

[0047] By leveraging machine learning to provide timely maintenance alerts and integrating monitoring data with maintenance status, it facilitates integrated operation and management by staff. It can accurately determine fishway malfunctions, overcoming the limitations of manual monitoring and the difficulties of remote maintenance. It enables low-cost, intelligent, automated, and information-based fishway maintenance, ensuring the long-term sustainable operation of fishways and meeting the practical needs of maximizing their ecological benefits. Attached Figure Description

[0048] Figure 1 This is a flowchart illustrating the overall implementation of the present invention.

[0049] Figure 2 This is a schematic diagram of the water level change in the fishway according to the present invention.

[0050] Figure 3 This is a schematic diagram showing the water level comparison at the monitoring points of this invention.

[0051] Figure 4 This is a schematic diagram illustrating the repair scenario of the internal pool chamber of the fishway according to the present invention.

[0052] Figure 5 This describes the connections between the modules of the system of the present invention, as well as the components and functions of each module. Detailed Implementation

[0053] The present invention will now be described in further detail with reference to the accompanying drawings and specific embodiments.

[0054] To accurately diagnose fishway malfunctions and meet the practical needs of achieving long-term sustainable operation and maximizing the ecological benefits of fishways, this invention provides a machine learning-based intelligent fishway operation and maintenance method. The overall implementation flowchart is as follows: Figure 1 As shown, the specific steps are as follows:

[0055] S1. Several ultrasonic sensors are arranged above each chamber of the fishway. In this embodiment, the water level data is acquired by the JSN-SR04T ultrasonic sensor. The data set constructed by the coordinate information of the monitoring point of each chamber and the corresponding water level information is called the first set. When the boundary conditions change, each sensor will synchronously monitor the water level information of each monitoring point, and together with the monitoring point coordinates and boundary conditions, they will form the second set.

[0056] The specific installation locations of the ultrasonic sensors are determined based on the dimensions and location of the fishway chamber. They are positioned 1.5m above the fishway chamber, with eight ultrasonic sensors installed from upstream to downstream. The number of sensors matches the number of fishway chambers. A schematic diagram of the fishway's geometric dimensions and monitoring point locations is shown below. Figure 2 As shown in Table 1, the upstream and downstream water levels and flow rates for several typical boundary conditions are as follows:

[0057] Table 1. Upstream and downstream water level and flow rate data under different boundary conditions.

[0058]

[0059]

[0060] S2. The actual water level data and monitoring point coordinate information measured by the water level sensor module 1 are transmitted to the data receiving unit 41 via the wireless network module. The data processing unit 42 uses boundary condition variables as initial input conditions, fish passage and basic parameters of the pool chamber as constraints, and the read monitoring point coordinate information as independent variables to calculate the water level calculation information data corresponding to the monitoring point of the pool chamber. This data and the corresponding pool chamber monitoring point coordinate information construct a data set called the third set. When the upstream boundary conditions change, the third set will be calculated and updated simultaneously. In this embodiment, the method for calculating the water level information data corresponding to the monitoring point of the i-th pool chamber is as follows:

[0061]

[0062] Where: H(x) i ,y i The coordinates of the monitoring point in the i-th chamber are (x, y). i ,y i Water level information data at point Qi For the flow rate entering the i-th pool chamber, D x D y The length of the i-th pool chamber is divided into its transverse and longitudinal lengths, V. i H(x) i ,y i The average flow velocity at the cross section where the monitoring point is located, x i ,y i H(x) i ,y i The horizontal and vertical distances of the monitoring point from the origin of the i-th pool chamber.

[0063] When it enters the i-th pool chamber, its flow rate Q i The calculation method is as follows:

[0064]

[0065]

[0066] Where Cs is the flow coefficient, h1 is the upstream water level of the i-th pool chamber minus the height of the bottom sill of a single pool chamber, g is the gravitational acceleration; β0, β1 are fishway correction coefficients, which are related to the fishway slope and the structure of the pool chamber, respectively, and h2 is the downstream water level of the i-th pool chamber minus the height of the bottom sill of a single pool chamber.

[0067] S3. The data processing unit 42 constructs a mapping relationship between the second set and the third set according to different boundary conditions, and compares and matches the coordinate information of the monitoring points and water level monitoring information in the second set with the coordinate information of the monitoring points and water level calculation information in the third set.

[0068] S4. Data processing unit 42 determines the degree of difference between the two sets based on the comparison and matching results in step S3, and finds that the water level difference under the boundary conditions and the measured water level exceed a preset threshold, such as... Figure 3 As shown in the figure. In the data sets of the figure, the measured data and calculated data of some monitoring points in the second and third sets differed significantly. These abnormal elements were included in the fourth set, and the data in the fourth set was divided into several subsets according to the number of fish passage chambers, that is, the abnormal data in each chamber. The data set constructed at this time is called the fifth set, which was sorted and the operating condition of the fish passage was judged by an artificial neural network.

[0069] Determine the preset threshold Δh i The method is as described in the following formula:

[0070]

[0071] in, D represents the average inlet flow rate of the target fishway;x D y λ represents the lateral and longitudinal lengths of the i-th pool chamber, respectively; S represents the slope of the target fishway; and λ represents the threshold correction coefficient, which is usually set to 0.05.

[0072] S5. The data processing unit 43 extracts the coordinate information of abnormal pool chamber monitoring points in the first subset of the fifth set. Based on the geometric characteristics of the fishway, and considering the damage or blockage within the fishway, the flow coefficient Cs in the water level information calculation method is modified. Water level information is calculated at different monitoring point coordinates. Data sets with smaller obstruction sizes and less damage are removed, and the remaining dataset is used to train an artificial neural network. In this embodiment, the artificial neural network uses 24 response variables, 8 predictor variables, and a layer size of 4, and is trained using Bayesian regularization. The machine learning algorithm determines the location of damage or blockage in the fishway pool chamber in the first subset, such as... Figure 3 As shown in maintenance condition 1, chambers 1-5 exhibit obvious anomalies. In maintenance condition 2, chambers 1 and 2 show no obvious anomalies, but the simulated and measured water levels in chambers 3-5 differ by more than a threshold, indicating a significant anomaly. After determining the location of the abnormal chambers, the coordinates of the monitoring points and the water level monitoring data in the first subset are corrected. Using the corrected elements from the previous subset as initial conditions, the coordinates of the monitoring points and the calculated water level data for each chamber are calculated sequentially and compared with the corresponding subset in the fifth set. This process is repeated to determine and correct the location of any damage or blockage in the fishway chamber, until the last subset is corrected. Figure 4 As shown in Scenario 1, after determining that an anomaly has occurred in chambers 3-5, chamber 3 is repaired first until it is fault-free. Using this as the initial condition, simulated values ​​for monitoring points in chambers 4 and 5 are calculated. After repair, the simulated water levels at the monitoring points in chambers 4 and 5 return to normal, thus confirming that the entire fishway fault only occurs in chamber 3. For example... Figure 4 As shown in Scenario 2, if the simulated water level values ​​at the monitoring points of chambers 4-5 are still abnormal after chamber 3 is repaired to a fault-free state, it is determined that chambers 4-5 are still in a fault state. Chamber 4 will then be repaired further until the simulated water level values ​​of the entire chamber return to normal.

[0073] S6. The maintenance prompt unit 44 transmits the damage and obstruction status of the fishway pool interior determined in step S5 to the monitoring terminal, and the maintenance personnel take maintenance measures for the abnormal locations inside the fishway.

[0074] This invention also proposes a machine learning-based intelligent fishway operation and maintenance system to implement the steps of the machine learning-based intelligent fishway operation and maintenance method described above. The system includes a water level sensor module, a wireless network module, a power supply module, and a central control platform. Figure 5As shown. It should be noted that each module in the above system corresponds to a specific step of the method provided in the embodiments of the present invention, and has the corresponding functional modules and beneficial effects for executing the method. Technical details not described in detail in this embodiment can be found in the method provided in the embodiments of the present invention.

[0075] This invention also proposes an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. It should be noted that each module in the above system corresponds to a specific step of the method provided in this invention, possessing the corresponding functional modules and beneficial effects for executing the method. Technical details not described in detail in this embodiment can be found in the method provided in this invention.

[0076] Various implementations of the systems and techniques described in this embodiment can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, software, and / or combinations thereof. These various implementations may include: implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0077] The above embodiments are merely illustrative of the technical concept of the present invention and should not be construed as limiting the scope of protection of the present invention. Any modifications made to the technical solutions based on the technical concept proposed in this invention shall fall within the scope of protection of this invention.

Claims

1. A smart fishway operation and maintenance method based on machine learning, characterized in that, Includes the following steps: S1. Use a water level sensor to obtain the coordinate information of the monitoring points in the pool and the corresponding water level monitoring information, and define them as the first set; define several different boundary conditions and the first set under these conditions as the second set. S2. Using boundary condition variables as initial inputs and fishway and pool room basic parameters as constraints, the read monitoring point coordinate information is used as independent variables for calculation. The water level information data corresponding to the pool room monitoring point is calculated, and the data and the corresponding pool room monitoring point coordinate information are constructed into a third set. S3. Determine the mapping coefficients between the second set and the third set based on different boundary conditions, and compare and match the data in the second set and the data in the third set. S4. Based on the comparison and matching results in step S3, determine the degree of difference between the two sets, and perform the following actions according to the relationship between the degree of difference and the preset threshold: (1) If the difference meets the preset threshold, no warning is required; (2) If the difference exceeds the preset threshold, the abnormal element data in the second set and the third set are filtered to form the fourth set, and the data in the fourth set are divided into several subsets according to the number of fish passage pools, which are then used as the fifth set and sorted. S5. Using machine learning algorithms, determine the location of the fishway tank chamber that is damaged or blocked by obstacles in each subset of the fifth set, and correct the monitoring point coordinates and water level calculation information of the corresponding tank chamber until the last subset is corrected. S6. Transmit the damage and obstruction status of the fishway pool interior determined in step S5 to the monitoring terminal and carry out maintenance and repair measures.

2. The intelligent fishway operation and maintenance method based on machine learning according to claim 1, characterized in that, The specific formula for calculating the water level information data of the monitoring points in the pool chamber in step S2 is as follows: ； in, For the first i The coordinates of the monitoring points in each pool chamber are: Water level information data at the location, To enter the i The flow rate in each pool room Divided into the first i The transverse and longitudinal lengths of each pool chamber for The average flow velocity of the cross section where the monitoring point is located. They are respectively The distance of the monitoring point from the first i The horizontal and vertical distances between the origins of each pool chamber.

3. The intelligent fishway operation and maintenance method based on machine learning according to claim 2, characterized in that, The aforementioned water level information data calculation, when entering the first... i When the pool is indoors, its flow rate The calculation method is as follows: ； ； in, For flow coefficient, For the first i The water level at the upstream end of the pool chamber minus the height of the bottom sill of a single pool chamber. g It is the acceleration due to gravity; These are fishway correction factors, which are related to the fishway slope and the pool interior structure, respectively. For the first i The water level downstream of the pool chamber minus the height of the bottom sill of a single pool chamber.

4. The intelligent fishway operation and maintenance method based on machine learning according to claim 1, characterized in that, Preset threshold in step S4 Determined by the following formula: ； in, The average inlet flow rate of the target fishway; The first i The transverse and longitudinal lengths of each pool chamber; S The slope of the target fishway; This is the threshold correction coefficient.

5. The intelligent fishway operation and maintenance method based on machine learning according to claim 1, characterized in that, The specific steps of step S5 are as follows: Extract the coordinate information of abnormal pool chamber monitoring points from the first subset of the fifth set, and use machine learning algorithms to determine the location of damage or blockage of fishway pool chambers corresponding to the first subset. At the same time, correct the coordinates of abnormal pool chamber monitoring points and water level monitoring data in the first subset. The elements in the first modified subset are used as initial conditions to calculate the coordinates of the monitoring points in the next pool room and the water level calculation information data. They are then compared and matched with the second subset in the fifth set to determine and correct the location of the fishway pool room where damage or obstruction has occurred. This process continues until the last subset is corrected.

6. The intelligent fishway operation and maintenance method based on machine learning according to claim 1, characterized in that, In step S5, a machine learning algorithm is used to determine whether there is damage or blockage in the fishway. The specific formula is as follows: S501. Determine the geometric characteristics of the fishway; S502. Modify the water level information data calculation method according to different operation and maintenance situations. Flow coefficient is used to calculate water level information at different monitoring point coordinates. S503: Remove datasets with relatively small obstacle sizes and damage levels, and continuously train and validate the remaining datasets.

7. A smart fishway operation and maintenance system based on machine learning, characterized in that, Includes a water level sensor module, a wireless network module, a power supply module, and a central control platform: The water level sensor module consists of several ultrasonic sensors, which are used to accurately sense the water level information data of each monitoring point inside the fish passage. The wireless network module is used to receive water level information data of monitoring points in each pool chamber inside the fishway transmitted by the water level sensor module, and upload the monitoring point data and the corresponding water level information data to the central control platform. The power supply module is used to supply power to the water level sensor module, the wireless network module and the central control platform; The central control platform consists of a data receiving unit, a data processing unit, a data operation unit, and an operation and maintenance prompt unit. The data receiving unit receives water level information data of the fish passage in the pool room transmitted by the water level sensor module through the wireless network module. The data processing unit preprocesses the received data. The data operation unit compares the actual water level of the fish passage with the theoretical water level. The operation and maintenance prompt unit provides operation and maintenance prompts based on the operation results. The data receiving unit is configured to perform the following actions: acquire the coordinate information of the monitoring points in the pool and the corresponding water level monitoring information, and define them as a first set; define several different boundary conditions and the first set under these conditions as a second set; The data processing unit is configured to perform the following actions: receive water level information data of the fishway in the pool chamber from the data receiving unit; calculate the water level calculation information data corresponding to the monitoring point in the pool chamber, and define this data and the corresponding coordinate information of the monitoring point in the pool chamber as a third set; determine the mapping coefficient between the second set and the third set, and compare and match the data in the second set and the data in the third set; determine the degree of difference between the two sets based on the comparison and matching results, and perform the following actions based on the relationship between the degree of difference and a preset threshold: (1) If the difference meets the preset threshold, no warning is required; (2) If the difference exceeds the preset threshold, the abnormal element data in the second set and the third set are filtered to form the fourth set, and the data in the fourth set are divided into several subsets according to the number of fish passage pools, which are then used as the fifth set and sorted. The data processing unit is configured to perform the following actions: using a machine learning algorithm, sequentially determining the location of damage or obstruction in the fishway pool corresponding to each subset in the fifth set, and correcting the monitoring point coordinates and water level calculation information data of the corresponding pool, until the last subset is corrected; The maintenance notification unit is configured to perform the following actions: transmit the damage and obstruction status of the fishway pool room determined by the data operation unit to the monitoring terminal, and carry out maintenance handling measures.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

Images