A hydrological water gauge cleaning state remote monitoring and operation system based on an internet of things

Abstract

The application discloses a hydrological water gauge cleaning state remote monitoring and operation and maintenance system based on Internet of Things and relates to the technical field of Internet of Things application, which comprises a data acquisition terminal arranged at a hydrological water gauge monitoring site and a remote monitoring and analysis platform in Internet of Things communication with the data acquisition terminal; the data acquisition terminal comprises a visual identification module configured to regularly shoot water gauge images, acquire water level visual readings, reading confidence and calculate image definition attenuation values; an auxiliary water level sensing module configured to acquire auxiliary water level readings not affected by water gauge surface dirt; and an environmental state sensing module configured to collect on-site illumination intensity and rainfall; the application solves the problem of high operation and maintenance cost caused by the inability to distinguish real dirt of the water gauge from environmental disturbances such as strong reflection and water ripples in the prior water gauge monitoring.

Description

Technical Field

[0001] This invention relates to the field of Internet of Things (IoT) application technology, specifically to a remote monitoring and maintenance system for the cleaning status of hydrological gauges based on the Internet of Things. Background Technology

[0002] Hydrological gauges are the infrastructure for acquiring water level data in hydrological monitoring, and the accuracy and continuity of their readings directly affect the scientific nature of flood control, drought relief, and water resource allocation. With the development of IoT and AI technologies, remote monitoring systems that use video cameras combined with visual recognition algorithms to automatically read water gauge readings have been gradually applied.

[0003] However, existing systems have revealed significant shortcomings in actual operation. Due to the complex and ever-changing field environment, the reasons for AI recognition failures are diverse. On the one hand, water gauges may be covered by silt, algae, water hyacinth, or floating debris, making the scales unreadable; such cases require manual cleaning. On the other hand, recognition failures may also be caused by temporary environmental interference, such as strong light reflection, water surface fluctuations, rain or fog, faulty supplemental lighting, or spider webs obstructing the lens. Current technology cannot distinguish between these two completely different types of anomalies, often reporting them uniformly as "recognition anomaly" or "equipment alarm." As a result, the operations and maintenance center struggles to determine the actual cause, frequently resulting in the wrong personnel being dispatched due to short-term interference, causing a significant waste of manpower, resources, and time, and reducing the system's economic efficiency and practical value.

[0004] Furthermore, traditional operation and maintenance models generally rely on "passive response," meaning maintenance is only carried out when the water gauge becomes severely contaminated to the point of being unrecognizable. However, water gauge contamination is often a gradual, cumulative process, such as algae growth and sediment buildup, which can lead to a decline in recognition confidence over a long period, causing hydrological data to become increasingly distorted, while the system fails to provide early warnings. This delayed maintenance not only affects data quality but also limits the forward-looking planning of operation and maintenance work, resulting in inefficient resource scheduling.

[0005] Therefore, there is an urgent need to design an IoT-based remote monitoring and maintenance system for hydrological gauges that can accurately identify fault types, avoid ineffective maintenance, quantitatively assess the cleanliness of water gauges, and enable predictive maintenance, so as to improve the intelligence level and operational efficiency of hydrological monitoring. Summary of the Invention

[0006] The purpose of this invention is to provide a remote monitoring and maintenance system for the cleanliness status of hydrological gauges based on the Internet of Things, so as to solve the problems mentioned in the background art.

[0007] To solve the above-mentioned technical problems, the present invention provides the following technical solution: a remote monitoring and maintenance system for the cleaning status of hydrological gauges based on the Internet of Things, including a data acquisition terminal set up at the hydrological gauge monitoring site and a remote monitoring and analysis platform that communicates with the data acquisition terminal via the Internet of Things; The data acquisition terminal includes: The visual recognition module is configured to periodically capture images of the water level gauge to obtain visual readings of the water level. Confidence level of readings And calculate the image sharpness attenuation value. ; The auxiliary water level sensing module is configured to acquire auxiliary water level readings that are unaffected by dirt on the surface of the water gauge. ; The environmental condition sensing module is configured to collect the light intensity at the site. and rainfall; The water quality sensor module is configured to measure the turbidity of the water body. and chlorophyll ; The hydro-meteorological module is configured to measure water flow velocity. and water temperature ; The remote monitoring and analysis platform includes: The data receiving and storage module is configured to receive and parse the data reported by the data acquisition terminal; The cross-validation and fault detection module is configured to, at the confidence level of the reading When the water level falls below the first threshold, the auxiliary water level reading will be activated. and the intensity of light on site The system analyzes and determines the fault category, which includes Category A and Category B. Category A represents actual dirt and grime faults, while Category B represents temporary environmental interference faults. The alarm and maintenance scheduling module is configured to generate graded alarms and differentiated maintenance instructions based on the fault categories identified by the fault identification module. The dirt accumulation calculation module is configured to calculate based on the turbidity. chlorophyll Water flow velocity and water temperature An algorithm based on a physicochemical model is used to calculate the instantaneous fouling rate, and the theoretical cumulative fouling value is obtained by integrating the results over time. ; The state calibration and prediction module is configured to utilize the image sharpness attenuation value. Theoretical dirt accumulation value Perform closed-loop feedback calibration, and when the theoretical dirt accumulation value is reached... When the preset maintenance threshold is exceeded, a predictive maintenance work order is triggered.

[0008] According to the above technical solution, the visual recognition module performs sharpness analysis on the image of the water level gauge area, specifically by calculating the image gradient using the Laplacian operator and outputting the quantized image sharpness attenuation value. Among them, the new water gauge Completely blurry .

[0009] According to the above technical solution, the specific method for the cross-validation and fault identification module to analyze and determine the fault category includes: When the confidence level of the reading Below the first threshold, and the auxiliary water level reading When the readings are also abnormal, it is determined to be a hydrological environmental disturbance in a Class B fault. When the confidence level of the reading Below the first threshold, and the auxiliary water level reading If the readings are stable and normal, the initial judgment is that it is a physical blockage, and the light intensity is further adjusted accordingly. ; When the light intensity When the intensity exceeds the strong light threshold, it is classified as optical interference in Class B faults; When the light intensity When the fault is within the normal range, it is classified as a Class A fault.

[0010] According to the above technical solution, the differentiated operation and maintenance instructions generated by the alarm and operation and maintenance scheduling module are as follows: When a fault is identified as Class A, it is generated immediately. The work order is classified as a high-priority work order and pushed to the maintenance personnel; When a fault is identified as a Class B fault, dispatching is suppressed, and a new fault is generated. It is a low-priority log and can be automatically retried after a preset time.

[0011] According to the above technical solution, the physical-chemical model upon which the dirt accumulation calculation module is based is: the total dirt accumulation rate of the water gauge. It is determined by the rate of siltation. and algal growth rate Determined by two physical processes, its calculation expression is: .

[0012] According to the above technical solution, the instantaneous sediment fouling rate The calculation expression is: ;in, The preset mud and sand adhesion coefficient, The baseline for calibrated clear water turbidity. To prevent the compensation value of the flow rate from being divided by zero.

[0013] According to the above technical solution, the instantaneous algal growth rate The calculation expression is: ;in, The preset algae adhesion coefficient, The baseline for chlorophyll content in clear water was established. A temperature growth factor that characterizes the growth activity of algae at different water temperatures; Among them, temperature growth factor It is a nonlinear function.

[0014] According to the above technical solution, the dirt accumulation calculation module calculates the siltation rate. and instantaneous algal growth rate By accumulating and integrating over time, the instantaneous velocity is transformed into a continuous, cumulative state value, thereby calculating the theoretical cumulative dirt value. Wherein, the theoretical cumulative dirt value The iterative calculation expression is: ;in This is the calculation result for the current period. This is the calculation result from the previous period.

[0015] According to the above technical solution, the state calibration and prediction module utilizes the image sharpness attenuation value. The theoretical cumulative dirt value Closed-loop feedback calibration is performed, and the calibration method is as follows: Real-time comparison of image sharpness attenuation values Compared with theoretical cumulative dirt value Deviation between; The calibration coefficient is calculated based on this deviation. ; Using the calibration coefficient The algorithm coefficients in the dirt accumulation calculation module are automatically fine-tuned.

[0016] According to the above technical solution, the logic for the state calibration and prediction module to trigger predictive maintenance work orders is as follows: Continuously monitor the theoretical cumulative dirt value. ; when When the cumulative maintenance threshold is exceeded for the first time, a predictive maintenance work order is immediately triggered without waiting for the confidence level of the reading. Below the first threshold.

[0017] Compared with existing technologies, the beneficial effects achieved by this invention are as follows: By setting up cross-validation and fault identification modules, this invention can analyze visual readings, radar readings, and illumination data in real time. Through multi-level linkage judgment, it can accurately identify whether the real cause of reading failure is actual dirt or environmental interference. This allows the system to suppress or downgrade alarms for environmental interference faults, thereby greatly avoiding invalid maintenance dispatches caused by temporary interference such as strong reflections and water ripples. A dynamic balance is achieved between ensuring that actual dirt is not missed and reducing maintenance costs. Attached Figure Description

[0018] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings: Figure 1 This is a schematic diagram of the system module composition of the present invention. Detailed Implementation

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] Please see Figure 1 This invention provides an IoT-based remote monitoring and maintenance system for the cleanliness of hydrological gauges, deployed in the cloud or monitoring center, referred to as a remote monitoring and analysis platform. This platform communicates bidirectionally with one or more data acquisition terminals deployed at field hydrological stations via IoT (such as 4G / 5G / NB-IoT).

[0021] The data acquisition terminal includes: A visual recognition module, consisting of an industrial camera, has a built-in or connected edge computing unit that runs an OCR algorithm and is configured to periodically (e.g., every 10 minutes) capture water level images to obtain visual readings of the water level. Confidence level of readings And calculate the image sharpness attenuation value. ; The auxiliary water level sensing module, a non-contact sensor, preferably a radar level gauge, is installed near the water gauge and configured to acquire auxiliary water level readings unaffected by dirt on the water gauge surface. Its measurement principle is not affected by dirt on the surface of the water gauge; Environmental condition sensing modules, including but not limited to light sensors and rain gauges, are configured to collect data on the light intensity at the site. and rainfall; The water quality sensing module, with its multi-parameter water quality probe, is configured to measure the turbidity of water bodies. and chlorophyll ; The hydrometeorological module, including a Doppler current meter and a water temperature sensor, is configured to measure water flow velocity. and water temperature ; The remote monitoring and analysis platform includes: The data receiving and storage module is configured to receive and parse the data reported by the data acquisition terminal; The cross-validation and fault detection module is configured to, at the confidence level of the reading When the water level falls below the first threshold, the auxiliary water level reading will be activated. and the intensity of light on site The system analyzes and determines the fault category, which includes Category A and Category B. Category A represents actual dirt and grime faults, while Category B represents temporary environmental interference faults. The alarm and maintenance scheduling module is configured to generate graded alarms and differentiated maintenance instructions based on the fault categories identified by the fault identification module. The dirt accumulation calculation module is configured to calculate based on the turbidity. chlorophyll Water flow velocity and water temperature An algorithm based on a physicochemical model is used to calculate the instantaneous fouling rate, and the theoretical cumulative fouling value is obtained by integrating the results over time. ; The state calibration and prediction module is configured to utilize the image sharpness attenuation value. Theoretical dirt accumulation value Perform closed-loop feedback calibration, and when the theoretical dirt accumulation value is reached... When the preset maintenance threshold is exceeded, a predictive maintenance work order is triggered.

[0022] The visual recognition module performs sharpness analysis on the image of the water level gauge area, specifically by calculating the image gradient using the Laplacian operator and outputting the quantized image sharpness attenuation value. Among them, the new water gauge Completely blurry .

[0023] The specific methods used by the cross-validation and fault identification module to analyze and determine the fault category include: When the confidence level of the reading Below the first threshold, and the auxiliary water level reading When the readings are also abnormal (such as failure or drastic jump), it is judged as hydrological environmental interference in Class B faults; When the confidence level of the reading Below the first threshold, and the auxiliary water level reading If the readings are stable and normal, the initial judgment is that it is a physical blockage, and the light intensity is further adjusted accordingly. ; When the light intensity When the intensity exceeds the strong light threshold, it is classified as optical interference in Class B faults; When the light intensity When the fault is within the normal range, it is classified as a Class A fault.

[0024] The differentiated operation and maintenance instructions generated by the alarm and operation and maintenance scheduling module are as follows: When a fault is identified as Class A, it is generated immediately. The work order is classified as a high-priority work order and pushed to the maintenance personnel; When a fault is identified as a Class B fault, dispatching is suppressed, and a new fault is generated. It is a low-priority log and can be automatically retried after a preset time.

[0025] The physicochemical model upon which the fouling accumulation calculation module is based is: the total fouling accumulation rate of the water draft. It is determined by the rate of siltation. and algal growth rate Determined by two physical processes, its calculation expression is: .

[0026] Instantaneous sediment fouling rate The calculation expression is: ;in, The preset mud and sand adhesion coefficient, The baseline for calibrated clear water turbidity. To prevent compensation values ​​for flow velocities divided by zero, the value in this embodiment of the invention is taken as 0.1 m / s; where the adhesion rate of sediment on the surface of the water gauge is related to the sediment concentration in the water (derived from turbidity). The characteristics are directly proportional to the scouring capacity of the water flow (as represented by the flow velocity), and also related to the scouring capacity of the water flow (as represented by the flow velocity). The characteristics are inversely proportional.

[0027] Instantaneous algal growth rate The calculation expression is: ;in, The preset algae adhesion coefficient, The baseline for chlorophyll content in clear water was established. The temperature growth factor characterizes the growth activity of algae at different water temperatures; where the algal growth rate depends on the nutrient concentration in the water (composed of chlorophyll). Characterization) and environmental suitability (by water temperature) (characterization); Among them, temperature growth factor This is a nonlinear function, exemplarily, in this embodiment of the invention, a Gaussian function centered at the optimal growth temperature of 28 degrees Celsius: .

[0028] The dirt accumulation calculation module calculates the sediment deposition rate. and instantaneous algal growth rate By accumulating and integrating over time, the instantaneous velocity is transformed into a continuous, cumulative state value, thereby calculating the theoretical cumulative dirt value. Wherein, the theoretical cumulative dirt value The iterative calculation expression is: ;in This is the calculation result for the current period. This is the calculation result from the previous period.

[0029] The state calibration and prediction module utilizes the image sharpness attenuation value. The theoretical cumulative dirt value Closed-loop feedback calibration is performed, and the calibration method is as follows: Real-time comparison of image sharpness attenuation values Compared with theoretical cumulative dirt value Deviation between; The calibration coefficient is calculated based on this deviation. ; Using the calibration coefficient For the algorithm coefficients in the dirt accumulation calculation module (such as...) and It performs automatic fine-tuning so that the next theoretical estimate is closer to the actual observed value.

[0030] The logic for triggering predictive maintenance work orders by the status calibration and prediction module is as follows: Continuously monitor the theoretical cumulative dirt value. ; when When the cumulative maintenance threshold is exceeded for the first time, a predictive maintenance work order is immediately triggered without waiting for the confidence level of the reading. Below the first threshold.

[0031] This invention, by setting up cross-validation and fault identification modules, can analyze visual readings, radar readings, and illumination data in real time. Through multi-level linkage judgment, it can accurately identify whether the real cause of the reading failure is Class A actual dirt or Class B environmental interference. This allows the system to suppress or downgrade alarms for Class B faults, thereby greatly avoiding invalid maintenance dispatches caused by temporary interference such as strong reflections and water ripples. It achieves a dynamic balance between ensuring that actual dirt is not missed and reducing maintenance costs.

[0032] Furthermore, this invention, by setting up a fouling accumulation calculation module, can collect easily assessable parameters such as water quality and hydrology (turbidity, flow velocity, chlorophyll, etc.) in real time. Through a hard-core algorithm based on a physicochemical model, it calculates the current instantaneous fouling rate and then quantifies a theoretical fouling accumulation value that is unknowable by traditional techniques by accumulating and integrating the data. This allows the system to proactively predict rather than rely on passive alarms. When the theoretical fouling accumulation value exceeds a preset maintenance threshold, the system can generate a predictive maintenance work order in advance, even before visual recognition has completely failed, thus preventing hydrological data from entering a sub-healthy state. Simultaneously, by introducing actual visual observations to perform closed-loop calibration of the theoretical fouling accumulation value model, adaptive redundancy of model parameters is preserved. Therefore, this invention not only ensures timely detection of hydrological data in a sub-healthy state but also allows the operation and maintenance center to process work orders in batches and in a planned manner, achieving a dynamic balance between ensuring data quality and minimizing operation and maintenance costs, resulting in intelligent, forward-looking, and highly efficient operation and maintenance.

[0033] Example: The dirt accumulation calculation module obtains real-time turbidity. and flow rate Substitute the instantaneous rate of sediment contamination The calculation formula assumes the sediment adhesion coefficient. Turbidity of clear water Compensation value for flow rate to prevent division by zero ,but ; The dirt accumulation calculation module obtains real-time chlorophyll levels. and water temperature First, calculate the temperature growth factor. Let the optimal growth temperature be... ,but Then substitute in the instantaneous algal growth rate. The calculation formula is given, where the algae adhesion coefficient is set. Clear water baseline ,but Input the above calculation results into the dirt accumulation calculation module, which uses the theoretical dirt accumulation value from the previous cycle. Based on, cycle Calculate the theoretical cumulative dirt and grime value for the current period, given a time interval of 1 hour. Substitute into the formula: This value is stored and used as the basis for the next step of the judgment. The state calibration and prediction module simultaneously acquires the image sharpness attenuation value reported by the vision module. The system discovered of Theoretical cumulative dirt value for the current cycle of There is a deviation. The system calculates the calibration coefficient. The system uses this coefficient for fine-tuning. and , that is, new ; This allows the next theoretical calculation to more closely approximate the actual observed values. Finally, the system only uses... Compared to the maintenance threshold of 40%, due to Predictive maintenance will not be triggered in this cycle. Subsequent cycles will... Through continuous accumulation, when it first exceeds 40%, even the confidence level of the reading... If the alarm value is still above the alarm threshold of 70%, the alarm and operation and maintenance scheduling module will immediately and proactively trigger a predictive maintenance work order, thereby enabling early intervention before the data enters a sub-healthy state and realizing the planned deployment of operation and maintenance resources.

[0034] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0035] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0036] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0037] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of the present invention without departing from the spirit and scope of the claims. All of these forms are within the protection scope of the present invention.

Claims

1. A remote monitoring and maintenance system for the cleanliness status of hydrological gauges based on the Internet of Things (IoT), comprising a data acquisition terminal installed at the hydrological gauge monitoring site, and a remote monitoring and analysis platform communicating with the data acquisition terminal via the IoT; characterized in that: The data acquisition terminal includes: The visual recognition module is configured to periodically capture images of the water level gauge to obtain visual readings of the water level. Confidence level of readings And calculate the image sharpness attenuation value. ; The auxiliary water level sensing module is configured to acquire auxiliary water level readings that are unaffected by dirt on the surface of the water gauge. ; The environmental condition sensing module is configured to collect the light intensity at the site. and rainfall; The water quality sensor module is configured to measure the turbidity of the water body. and chlorophyll ; The hydro-meteorological module is configured to measure water flow velocity. and water temperature ; The remote monitoring and analysis platform includes: The data receiving and storage module is configured to receive and parse the data reported by the data acquisition terminal; The cross-validation and fault detection module is configured to, at the confidence level of the reading When the water level falls below the first threshold, the auxiliary water level reading will be activated. and the intensity of light on site The system analyzes and determines the fault category, which includes Category A and Category B. Category A represents actual dirt and grime faults, while Category B represents temporary environmental interference faults. The alarm and maintenance scheduling module is configured to generate graded alarms and differentiated maintenance instructions based on the fault categories identified by the fault identification module. The dirt accumulation calculation module is configured to calculate based on the turbidity. chlorophyll Water flow velocity and water temperature An algorithm based on a physicochemical model is used to calculate the instantaneous fouling rate, and the theoretical cumulative fouling value is obtained by integrating the results over time. ; The state calibration and prediction module is configured to utilize the image sharpness attenuation value. Theoretical dirt accumulation value Perform closed-loop feedback calibration, and when the theoretical dirt accumulation value is reached... When the preset maintenance threshold is exceeded, a predictive maintenance work order is triggered.

2. The remote monitoring and maintenance system for the cleaning status of hydrological gauges based on the Internet of Things as described in claim 1, characterized in that: The visual recognition module performs sharpness analysis on the image of the water level gauge area, specifically by calculating the image gradient using the Laplacian operator and outputting the quantized image sharpness attenuation value. Among them, the new water gauge Completely blurry .

3. The remote monitoring and maintenance system for the cleaning status of hydrological gauges based on the Internet of Things as described in claim 1, characterized in that: The specific methods used by the cross-validation and fault identification module to analyze and determine the fault category include: When the confidence level of the reading Below the first threshold, and the auxiliary water level reading When the readings are also abnormal, it is determined to be a hydrological environmental disturbance in a Class B fault. When the confidence level of the reading Below the first threshold, and the auxiliary water level reading If the readings are stable and normal, the initial judgment is that it is a physical blockage, and the light intensity is further adjusted accordingly. ; When the light intensity When the intensity exceeds the strong light threshold, it is classified as optical interference in Class B faults; When the light intensity When the fault is within the normal range, it is classified as a Class A fault.

4. The remote monitoring and maintenance system for the cleaning status of hydrological gauges based on the Internet of Things as described in claim 1, characterized in that: The differentiated operation and maintenance instructions generated by the alarm and operation and maintenance scheduling module are as follows: When a fault is identified as Class A, it is generated immediately. The work order is classified as a high-priority work order and pushed to the maintenance personnel; When a fault is identified as a Class B fault, dispatching is suppressed, and a new fault is generated. It is a low-priority log and can be automatically retried after a preset time.

5. The remote monitoring and maintenance system for the cleaning status of hydrological gauges based on the Internet of Things as described in claim 1, characterized in that: The physicochemical model upon which the fouling accumulation calculation module is based is: the total fouling accumulation rate of the water gauge. It is determined by the rate of siltation. and algal growth rate Determined by two physical processes, its calculation expression is: .

6. The remote monitoring and maintenance system for the cleaning status of hydrological gauges based on the Internet of Things as described in claim 5, characterized in that: The instantaneous sediment fouling rate The calculation expression is: ;in, The preset mud and sand adhesion coefficient, The baseline for calibrated clear water turbidity. To prevent the compensation value of the flow rate from being divided by zero.

7. The remote monitoring and maintenance system for the cleaning status of hydrological gauges based on the Internet of Things as described in claim 5, characterized in that: The instantaneous algal growth rate The calculation expression is: ;in, The preset algae adhesion coefficient, The baseline for chlorophyll content in clear water was established. A temperature growth factor that characterizes the growth activity of algae at different water temperatures; Among them, temperature growth factor It is a nonlinear function.

8. The remote monitoring and maintenance system for the cleaning status of hydrological gauges based on the Internet of Things as described in claim 5, characterized in that: The dirt accumulation calculation module calculates the siltation rate. and instantaneous algal growth rate By accumulating and integrating over time, the instantaneous velocity is transformed into a continuous, cumulative state value, thereby calculating the theoretical cumulative dirt value. Wherein, the theoretical cumulative dirt value The iterative calculation expression is: ;in This is the calculation result for the current period. This is the calculation result from the previous period.

9. A remote monitoring and maintenance system for the cleaning status of hydrological gauges based on the Internet of Things, as described in claim 8, is characterized in that: The state calibration and prediction module utilizes the image sharpness attenuation value. The theoretical cumulative dirt value Closed-loop feedback calibration is performed, and the calibration method is as follows: Real-time comparison of image sharpness attenuation values Compared with theoretical cumulative dirt value Deviation between; The calibration coefficient is calculated based on this deviation. ; Using the calibration coefficient The algorithm coefficients in the dirt accumulation calculation module are automatically fine-tuned.

10. A remote monitoring and maintenance system for the cleaning status of hydrological gauges based on the Internet of Things, as described in claim 9, characterized in that: The logic for triggering predictive maintenance work orders by the status calibration and prediction module is as follows: Continuously monitor the theoretical cumulative dirt value. ; when When the cumulative maintenance threshold is exceeded for the first time, a predictive maintenance work order is immediately triggered without waiting for the confidence level of the reading. Below the first threshold.

Images