A method for detecting and removing sedimentation in ultrasonic-assisted ToF water level monitoring equipment

Abstract

The present invention discloses a sediment detection and removal method of an ultrasonic-assisted ToF water level monitoring device, which relates to the field of environmental monitoring. The method includes: performing periodic monitoring of a pipe water inlet; performing sediment accumulation evaluation, configuring a sensor group, and establishing a periodic cleaning strategy; performing periodic cleaning, and performing sediment data collection; performing water level monitoring impact evaluation; generating a first decision-making impact factor according to the water level change prediction result and the timing impact evaluation result; performing a cost analysis of real-time cleaning and accumulation cleaning; performing cleaning effect evaluation of real-time cleaning and accumulation cleaning; performing decision optimization, generating adaptive control parameters, and controlling an ultrasonic module to remove sediment. The method solves the technical problems of the existing sediment detection and removal that the distribution and properties of sediments cannot be accurately identified and quantified, and it is difficult to formulate an effective cleaning strategy, and achieves the technical effects of real-time monitoring, accurate quantification, and dynamic cleaning strategy formulation of sediments.

Description

Technical Field

[0001] The present application relates to the field of environmental monitoring, and in particular to a method for detecting and removing sedimentation of an ultrasonically assisted ToF water level monitoring device. Background Art

[0002] In the field of water resource management and environmental monitoring, it is crucial to accurately monitor water level changes and maintain the normal operation of monitoring equipment. Traditional water level monitoring equipment is often susceptible to sediment accumulation at the pipe inlet, resulting in distorted monitoring data, which in turn affects the prediction and decision-making of water level changes. In addition, the accumulation of sediment may also clog the pipe, increase the cost of cleaning and the difficulty of maintenance. Traditionally, sediment cleaning at the pipe inlet mainly relies on manual cleaning or regular mechanical cleaning. These methods are not only inefficient and costly, but also difficult to respond to changes in sediment accumulation in a timely manner, resulting in poor cleaning results and easy to cause secondary damage to the equipment.

[0003] In the current relevant technologies, sediment detection and removal by water level monitoring equipment has the technical problem of being unable to accurately identify and quantify the distribution and properties of sediments, making it difficult to formulate effective cleaning strategies. Summary of the invention

[0004] The present application provides a sediment detection and removal method for an ultrasonic-assisted ToF water level monitoring device, combines ultrasonic technology and ToF ranging principle, establishes a periodic data set through periodic monitoring, evaluates sediment accumulation, configures a sensor group based on the sediment accumulation evaluation result, formulates a periodic cleaning strategy for the ultrasonic module, controls the ultrasonic module to perform periodic cleaning, establishes a sediment data set, evaluates the impact of water level monitoring, optimizes decisions based on first, second, and third decision influencing factors, generates adaptive control parameters, and other technical means, thereby achieving the technical effects of real-time monitoring, precise quantification, and dynamic cleaning strategy formulation of sediments at the water inlet of the pipeline.

[0005] The present application provides a method for detecting and removing sedimentation of an ultrasonically assisted ToF water level monitoring device, comprising:

[0006] The ToF water level monitoring device is periodically monitored at the water inlet of the pipeline to establish a periodic data set, wherein the water inlet of the pipeline is equipped with a permeable net; sediment accumulation evaluation is performed based on the periodic data set, a sensor group is configured using the sediment accumulation evaluation result, and a periodic cleaning strategy of the ultrasonic module is established using the periodic data set; the ultrasonic module is controlled to perform periodic cleaning using the periodic cleaning strategy, and sediment data collection at the water inlet of the pipeline is performed using the sensor group to establish a sediment data set; water level monitoring impact evaluation is performed using the sediment data set to establish a time series impact evaluation result; water level change prediction is performed in the monitored area, and a first decision influencing factor is generated based on the water level change prediction result and the time series impact evaluation result; cost analysis of real-time cleaning and accumulation cleaning is performed based on the sediment data set to establish a second decision influencing factor; cleaning effect evaluation of real-time cleaning and accumulation cleaning is performed based on the sediment data set to establish a third decision influencing factor; decision optimization is performed based on the first decision influencing factor, the second decision influencing factor, and the third decision influencing factor, and a decision optimization result is established, and adaptive control parameters of the ultrasonic module are generated based on the decision optimization result, and the ultrasonic module is controlled based on the adaptive control parameters to remove sediment from the water inlet of the pipeline.

[0007] In a possible implementation, the following processing is performed:

[0008] The first decision influencing factor is calculated as follows:

[0009] Among them, F1(t) represents the first decision-making influencing factor that changes with time, ΔH(t) represents the water level change at time t, S(t) represents the evaluation result of the sediment accumulation time series impact at time t, α(t) is the time-dependent weight factor of water level change, β(t) is the interactive influence weight factor of sediment accumulation time series impact and water level change, Impact seq (S(t), ΔH(t)) is the dependency of the temporal impact of sediment accumulation and water level change, Impact seq (S(t),ΔH(t))=β(t)·S(t)·|ΔH(t)|, which reflects the interactive effect of the temporal influence of sediment accumulation and the water level change.

[0010] In a possible implementation, the following processing is performed:

[0011] The second decision-making influence factor is calculated as follows:

[0012]

[0013] Among them, F2(t) represents the second decision-making influencing factor that changes over time, Cost real-time(τ) represents the real-time cleaning cost at time τ, Cost adaptive-periodic (τ,t c ) represents the cycle cleaning cost, t c It represents the cost-effectiveness time inflection point, c1 is the cleaning cost per unit time before the cost-effectiveness time inflection point, and c2 is the cleaning cost per unit time after the cost-effectiveness time inflection point.

[0014] In a possible implementation, the following processing is performed:

[0015] The sensor group includes at least one or more of an ultrasonic sensor, a turbidity sensor, an optical sensor, a pressure sensor, and a conductivity sensor.

[0016] In a possible implementation, the water level monitoring impact assessment is performed using the sediment data set, a time series impact assessment result is established, and the following processing is performed:

[0017] An evaluation model is established, wherein the evaluation model is a relationship model describing sediment characteristics and water level reading indicators; after the sediment characteristics of the sediment data set are extracted, the sediment characteristics are input into the evaluation model to generate a time series impact evaluation result.

[0018] In a possible implementation, the following processing is performed:

[0019] A self-feedback unit is established, response monitoring of the water inlet of the pipeline is performed based on the self-feedback unit, a response data set is established, and the adaptive control parameters are received through the self-feedback unit; removal fitting is performed using the adaptive control parameters, and a clearing effect verification is performed through the response data set to establish a clearing effect verification result; a feedback strategy is established according to the clearing effect verification result, and parameter feedback optimization of the ultrasonic module is performed according to the feedback strategy.

[0020] In a possible implementation, the sediment accumulation evaluation is performed based on the periodic data set, and the following processing is performed:

[0021] If the sediment accumulation evaluation result fails to meet the preset evaluation threshold, a non-monitoring instruction is generated; and fixed ultrasonic cleaning parameters are configured according to the sediment accumulation evaluation result to control the ultrasonic module to perform sediment removal at the pipe water inlet.

[0022] In a possible implementation, the water level change prediction of the monitored area is performed by performing the following processing:

[0023] Establishing equipment association of ToF water level monitoring equipment; evaluating data accuracy based on the equipment association and the sediment data set of the corresponding equipment pipeline inlet; and performing water level change prediction based on the data accuracy evaluation results, the readings of the ToF water level monitoring equipment, the equipment association and the weather data.

[0024] The present application proposes a method for detecting and removing sediments of an ultrasonic-assisted ToF water level monitoring device. First, the ToF water level monitoring device is periodically monitored at the water inlet of the pipe to establish a periodic data set, wherein the water inlet of the pipe is provided with a permeable net. Then, sediment accumulation is evaluated based on the periodic data set, and a sensor group is configured using the sediment accumulation evaluation result. A periodic cleaning strategy of the ultrasonic module is established using the periodic data set. The ultrasonic module is then controlled to perform periodic cleaning using the periodic cleaning strategy, and sediment data collection at the water inlet of the pipe is performed using the sensor group to establish a sediment data set. The sediment data set is then used to evaluate the impact of water level monitoring, and a time series impact evaluation result is established. Then, a water level change prediction of the monitored area is performed based on the sediment data set. The first decision influencing factor is generated according to the water level change prediction results and the time series impact evaluation results. At the same time, the cost analysis of real-time cleaning and accumulation cleaning is performed based on the sediment data set to establish the second decision influencing factor. At the same time, the cleaning effect evaluation of real-time cleaning and accumulation cleaning is performed based on the sediment data set to establish the third decision influencing factor. Finally, decision optimization is performed based on the first decision influencing factor, the second decision influencing factor and the third decision influencing factor to establish the decision optimization result. According to the decision optimization result, adaptive control parameters of the ultrasonic module are generated, and the ultrasonic module is controlled based on the adaptive control parameters to remove sediments at the pipeline water inlet, thereby achieving the technical effects of real-time monitoring, precise quantification and dynamic cleaning strategy formulation of sediments at the pipeline water inlet. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the method according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0026] Figure 1 A schematic flow chart of a sedimentation detection and removal method for an ultrasonically assisted ToF water level monitoring device provided in an embodiment of the present application.

[0027] Figure 2 A schematic diagram of a flow chart for optimizing the parameter feedback of an ultrasonic module in a sediment detection and removal method of an ultrasonically assisted ToF water level monitoring device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0028] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0029] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0030] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0031] The present application embodiment provides a method for detecting and removing sediments in an ultrasonic-assisted ToF water level monitoring device, such as Figure 1 As shown, the method includes:

[0032] Step S100, periodically monitor the water inlet of the pipeline of the ToF water level monitoring device and establish a periodic data set, wherein the water inlet of the pipeline is equipped with a permeable net. Specifically, a permeable net is installed at the water inlet of the pipeline of the ToF water level monitoring device, and the permeable net is used to filter large particles of impurities to prevent them from entering the pipeline and affecting the measurement accuracy of the ToF sensor. A sediment monitoring sensor (such as an ultrasonic sensor) is installed at the water inlet of the pipeline of the ToF water level monitoring device, and a monitoring cycle is set according to actual needs (such as the expected accumulation rate of sediment, water flow rate, historical data, etc.), such as monitoring once every 24 hours or once a week. In each monitoring cycle, the sediment data (such as sediment thickness, distribution, type, etc.) of the pipeline water inlet is obtained through the sediment monitoring sensor, and the timestamp is recorded. The collected sediment data (including sediment thickness, timestamp, etc.) is stored in the database to form a periodic data set.

[0033] Step S200, based on the periodic data set, the sediment accumulation evaluation is performed, the sensor group is configured using the sediment accumulation evaluation results, and the periodic cleaning strategy of the ultrasonic module is established with the periodic data set. Specifically, the sediment data is extracted from the periodic data set, and necessary cleaning and preprocessing are performed, such as removing outliers, filling missing values, etc. The accumulation trend of the sediment is analyzed using statistical analysis methods (such as time series analysis, etc.), and the change points of the accumulation rate are identified. Assess the impact of sediment accumulation on the ToF water level monitoring equipment, including blocking sensors, changing water flow patterns, affecting the speed of sound, etc. According to the sediment accumulation evaluation results, select suitable sensors (such as ultrasonic sensors, cameras, etc.) to form a sensor group for more accurate monitoring of sediment conditions. Based on the speed and degree of sediment accumulation, set the periodic cleaning strategy of the ultrasonic module, including cleaning cycle, cleaning time length, cleaning intensity, etc., wherein periodic cleaning can be regular cleaning or on-demand cleaning.

[0034] In a possible implementation, step S200 further includes step S210, wherein the sensor group includes at least one or more of an ultrasonic sensor, a turbidity sensor, an optical sensor, a pressure sensor, and a conductivity sensor. Specifically, the configuration of the sensor group in this implementation is not fixed, but one or more sensors are selected for combination according to actual needs. This flexibility enables adjustment and optimization according to factors such as sediment characteristics and environmental conditions at different pipe inlets. By selecting suitable sensors, relevant information about sediments can be obtained in a more targeted manner. For example, if the sediment is mainly composed of suspended particles, a turbidity sensor may be the first choice; and if the thickness or density of the sediment needs to be measured, an ultrasonic sensor is more suitable. By selecting a suitable combination of sensors, it is possible to ensure that the sediment accumulation can be accurately assessed, providing strong support for the formulation of effective cleaning strategies, thereby improving the efficiency and accuracy of sediment removal.

[0035] In a possible implementation, the sediment accumulation evaluation is performed based on the periodic data set, and step S200 further includes step S220, if the sediment accumulation evaluation result cannot meet the preset evaluation threshold, then a non-monitoring instruction is generated. Specifically, the evaluation result of sediment accumulation is obtained, which can be a numerical value (such as sediment thickness, turbidity value, etc.) or a classification label (such as "mild accumulation", "heavy accumulation", etc.). The evaluation result is compared with the preset evaluation threshold, wherein the preset evaluation threshold is pre-set according to factors such as pipeline operation requirements, water quality standards, and the impact of sediment on pipeline performance. If the evaluation result does not meet (i.e., is lower than or equal to) the preset threshold, it is considered that the amount of sediment accumulation is small and has not reached the level that requires special attention. At this time, a non-monitoring instruction is generated, indicating that no additional monitoring or emergency cleaning operation is required in the current situation, that is, within the current evaluation cycle, the accumulation of sediment is acceptable. Step S230, according to the non-monitoring instruction, a fixed ultrasonic cleaning parameter is configured with the sediment accumulation evaluation result to control the ultrasonic module to perform sediment removal at the pipeline inlet. Specifically, non-monitoring instructions indicate that the current sediment accumulation situation has not reached the standard for emergency treatment, but action is still needed to prevent excessive accumulation in the future, that is, preventive or maintenance cleaning measures are needed. According to the evaluation results of sediment accumulation, a set of fixed ultrasonic cleaning parameters are configured, including the frequency, power, action time, etc. of the ultrasonic wave. These parameters are relatively mild and are intended to perform preventive or low-intensity cleaning to maintain the relative cleanliness of the pipe inlet. Using the configured ultrasonic cleaning parameters, the ultrasonic module is controlled to perform sediment removal operations on the pipe inlet. This implementation method maintains the relative cleanliness of the pipe inlet by performing a certain degree of cleaning even when the threshold is not met, realizing a preventive or maintenance cleaning strategy and achieving the technical effect of improving the stability and reliability of the system.

[0036] Step S300, using the periodic cleaning strategy to control the ultrasonic module to perform periodic cleaning, and using the sensor group to perform sediment data collection at the water inlet of the pipeline to establish a sediment data set. Specifically, according to the periodic cleaning strategy, the ultrasonic module is started at a specified time to perform a cleaning operation. The ultrasonic module emits ultrasonic waves and uses the vibration and cavitation effect of ultrasonic waves to remove sediments. When the set cleaning time is reached, the cleaning operation of the ultrasonic module is stopped. Before and after cleaning, the sensor group is used to collect sediment data (such as sediment thickness, distribution, etc.) at the water inlet of the pipeline. The sediment data before and after cleaning are stored together with the timestamp to form a sediment data set.

[0037] Step S400, using the sediment data set to conduct an impact assessment on water level monitoring, and establish a time series impact assessment result. Specifically, the sediment data is compared and analyzed with the water level monitoring data to identify the impact of sediment accumulation on water level monitoring. Based on the data comparison results, a model between sediment accumulation and water level monitoring error is established. The established model is used to evaluate the specific impact of sediment accumulation on water level monitoring, such as error range, impact time, etc. The results of the impact of sediment accumulation on water level monitoring are sorted and analyzed in time series, the trend of the impact over time is determined, and the time series impact assessment results of sediment accumulation on water level monitoring are established.

[0038] In a possible implementation, the water level monitoring impact evaluation is performed using the sediment data set to establish a time series impact evaluation result. Step S400 further includes step S410, establishing an evaluation model, and the evaluation model is a relationship model that describes the sediment characteristics and water level reading indicators. Specifically, historical data on sediment and water level monitoring are collected, including physical properties such as sediment type, thickness, distribution, density, and water level readings within the corresponding time period. The historical data is preprocessed to improve data quality. Features that have a significant impact on water level readings are selected from the sediment data set, including sediment thickness, density, distribution range, etc. A support vector machine is used as an evaluation model to describe the relationship between sediment characteristics and water level reading indicators. The model is trained using the preprocessed data and features. During the training process, the model learns the relationship between sediment characteristics and water level readings, and adjusts its internal parameters to minimize prediction errors. Step S420, after extracting sediment features from the sediment data set, it is input into the evaluation model to generate a time series impact evaluation result. Specifically, according to the features determined in step S410, corresponding feature values ​​are extracted from the latest sediment data set, and these feature values ​​are the input of the model. The extracted sediment feature values ​​are input into the trained evaluation model, and the model predicts the corresponding water level reading indicator change trend based on these feature values. According to the prediction results of the evaluation model, the time series impact evaluation results are generated, including the change trend of water level readings in different time periods and the quantitative evaluation of the impact of sediment characteristics on water level monitoring. This implementation method generates the time series impact evaluation results by establishing an evaluation model and extracting and predicting features of the sediment data set, thereby achieving the technical effect of more accurately predicting the impact of sediment on water level monitoring.

[0039] Step S500, execute the water level change prediction of the monitored area, and generate the first decision-making influencing factor according to the water level change prediction result and the time series impact evaluation result. Specifically, a water level change prediction model is established using historical water level data and external factors (such as rainfall, river flow, etc.). According to the current and predicted future conditions, the water level change prediction is performed to obtain the water level prediction results for a period of time in the future. The time series impact evaluation result describes the impact of sediment characteristics on the water level reading index. The water level change prediction result is combined with the time series impact evaluation result for a comprehensive analysis, including considering the potential impact of sediments on the change of water level readings, and how this impact changes over time. Based on the water level change prediction result and the time series impact evaluation result, the first decision-making influencing factor is calculated. The first decision-making influencing factor can be a comprehensive score, probability value, risk level or other form of quantitative representation, which is used to evaluate the water level status of the monitored area in the current and future period of time and its impact on related decisions (such as flood control, water resources management, waterway maintenance, etc.).

[0040] In a possible implementation, the water level change prediction of the monitored area is performed, and step S500 further includes step S510, establishing device association of ToF water level monitoring equipment. Specifically, the location and identification information of all ToF water level monitoring equipment involved in water level monitoring are identified and recorded. According to the geographical location of the equipment, the monitoring range and the spatial relationship between each other, an association network between the equipment is established, including determining which equipment monitors different parts of the same water area or which equipment data can be mutually verified. Step S520, data accuracy evaluation is performed based on the equipment association and the sediment data set of the corresponding equipment pipeline inlet. Specifically, the sediment data set near the corresponding equipment pipeline inlet is collected, including information such as the type, thickness, and distribution of the sediment. Evaluate the impact of sediment on the reading of the ToF water level monitoring equipment, that is, the reading deviation caused by sediment coverage. Combined with the equipment association and the sediment data set, the accuracy of the reading of the ToF water level monitoring equipment is evaluated, including comparing the reading differences of different equipment, analyzing the relationship between sediment and reading deviation, etc. Step S530, water level change prediction is performed based on the data accuracy evaluation results, the reading of the ToF water level monitoring equipment, the equipment association and the weather data. Specifically, the readings of ToF water level monitoring equipment, data accuracy evaluation results, equipment-related information, and weather data (such as rainfall, wind speed, etc.) are integrated. Based on the integrated data, a time series analysis prediction model is used to perform water level change predictions, and the latest data is input into the prediction model to obtain water level prediction results for a period of time in the future. This implementation method establishes equipment associations for ToF water level monitoring equipment, integrates data from multiple devices for cross-validation and complementation, and reduces the impact of single device errors on prediction results. At the same time, the impact of sediment on equipment readings is considered and data accuracy is evaluated, which further improves the accuracy of the prediction. By integrating external factors such as weather data, the prediction model can more comprehensively reflect the actual situation, achieving the technical effect of improving the reliability of prediction results.

[0041] In a possible implementation, step S500 further includes step S540, in which the first decision influencing factor is calculated as follows:

[0042]

[0043] Among them, F1(t) represents the first decision-making influencing factor that changes with time, ΔH(t) represents the water level change at time t, S(t) represents the evaluation result of the sediment accumulation time series impact at time t, α(t) is the time-dependent weight factor of water level change, β(t) is the interactive influence weight factor of sediment accumulation time series impact and water level change, Impact seq (S(t), ΔH(t)) is the dependency of the temporal impact of sediment accumulation and water level change, Impact seq(S(t),ΔH(t))=β(t)·S(t)·|ΔH(t)|, which reflects the interactive effect of the temporal influence of sediment accumulation and the water level change.

[0044] Step S600, based on the cost analysis of real-time cleaning and cumulative cleaning of the sediment data set, establish a second decision-making influencing factor. Specifically, collect cost data related to sediment cleaning, including but not limited to cleaning equipment rental fees, labor costs, transportation costs, processing costs (such as waste disposal, environmental protection costs, etc.). Arrange the parts of the sediment data set that are directly related to the cleaning activities, such as the type, distribution, thickness, and cleaning difficulty of the sediment. According to the current sediment conditions (such as thickness, distribution range) and cleaning efficiency, estimate the cost required for immediate cleaning. Combined with the changes in sediments in the future (such as continued accumulation, distribution changes, etc.), estimate the cost required for cleaning the sediment at a certain point in the future. Use a cost-benefit analysis method to compare the costs of real-time cleaning and cumulative cleaning. Based on the results of the cost analysis, establish a quantitative indicator as the second decision-making influencing factor. The second decision-making influencing factor can be a comprehensive score or other forms of quantitative representation, which is used to evaluate the economic feasibility of different cleaning strategies and the degree of influence on the decision.

[0045] In a possible implementation, step S600 further includes step S610, where the second decision influencing factor is calculated as follows:

[0046]

[0047] Among them, F2(t) represents the second decision-making influencing factor that changes over time, Cost real-time (τ) represents the real-time cleaning cost at time τ, Cost adaptive-periodic (τ,t c ) represents the cycle cleaning cost, t c Characterizes the cost-effectiveness time inflection point, c1 is the cleaning cost per unit time before the cost-effectiveness time inflection point, and c2 is the cleaning cost per unit time after the cost-effectiveness time inflection point. Specifically, the real-time cleaning cost refers to the cost required to clean immediately at any given time point; the periodic cleaning cost refers to the average cost required to clean according to a fixed period; the cost-effectiveness time inflection point refers to the time point when the real-time cleaning cost is equal to the periodic cleaning cost.

[0048] Step S700, evaluate the cleaning effect of real-time cleaning and cumulative cleaning according to the sediment data set, and establish a third decision-making influencing factor. Specifically, compare the sediment data and water level monitoring data before and after real-time cleaning and cumulative cleaning to evaluate the effects of the two cleaning strategies. By comparing the sediment data sets before and after cleaning, quantify the effect of the cleaning activities, including calculating the reduction in sediment thickness, changes in distribution range, removal rate of specific types of sediments, reduction in water level monitoring errors, etc. At the same time, evaluate the efficiency of the cleaning activities, that is, the amount of sediment cleaned per unit time or the cleaning effect per unit cost. Based on the results of the cleaning effect evaluation, establish a quantitative indicator as the third decision-making influencing factor. The third decision-making influencing factor can be a comprehensive score, cleaning efficiency ratio or other forms of quantitative representation, which is used to evaluate the actual effects of different cleaning strategies and the degree of influence on the decision.

[0049] Step S800, according to the first decision influencing factor, the second decision influencing factor, and the third decision influencing factor, a decision optimization is performed, and a decision optimization result is established. According to the decision optimization result, an adaptive control parameter of the ultrasonic module is generated, and the ultrasonic module is controlled based on the adaptive control parameter to remove sediments at the water inlet of the pipeline. Specifically, the data of the first decision influencing factor (based on water level change prediction and timing impact evaluation), the second decision influencing factor (based on cost analysis of real-time cleaning and cumulative cleaning), and the third decision influencing factor (based on cleaning effect evaluation) are integrated into a comprehensive decision framework. Based on the analysis of historical data and expert knowledge, a weight is assigned to each decision influencing factor. The decision optimization algorithm is applied to find the optimal ultrasonic module control strategy. The algorithm searches for a control parameter combination that maximizes the comprehensive decision index (the sum of weighted decision influencing factors) under given constraints (cost constraints, cleaning effect requirements, etc.) through an iterative optimization process. According to the output of the decision optimization algorithm, a decision optimization result is established, which is a set of optimal ultrasonic module control parameters, including but not limited to cleaning frequency, cleaning time, cleaning intensity, etc. The decision optimization result is converted into an adaptive control parameter executable by the ultrasonic module. Based on the adaptive control parameter, a control instruction is sent to the ultrasonic module through a programming interface (such as GPIO control, serial communication, etc.) to achieve the removal of sediments at the water inlet of the pipeline. The embodiment of the present application adopts technical means such as establishing a periodic data set through periodic monitoring, evaluating sediment accumulation, configuring a sensor group based on the sediment accumulation evaluation result, formulating a periodic cleaning strategy for the ultrasonic module, controlling the ultrasonic module to perform periodic cleaning, establishing a sediment data set, evaluating the impact of water level monitoring, performing decision optimization according to the first, second, and third decision influencing factors, and generating adaptive control parameters, etc., to achieve the technical effect of real-time monitoring, precise quantification, and dynamic cleaning strategy formulation of sediments at the water inlet of the pipeline.

[0050] like Figure 2As shown, in a possible implementation, step S800 further includes step S810, establishing a self-feedback unit, performing response monitoring of the pipe water inlet based on the self-feedback unit, establishing a response data set, and receiving the adaptive control parameters through the self-feedback unit. Specifically, a self-feedback unit is designed, which is integrated in the ultrasonic-assisted ToF water level monitoring device for real-time monitoring of the cleaning response of the pipe water inlet. The self-feedback unit includes a sensor and a data processing module, which starts the sensor for data acquisition, and records various parameter changes in the cleaning process in real time, such as water flow rate, pressure change, sediment reduction, etc., to establish a response data set. The self-feedback unit receives adaptive control parameters for adjusting its own monitoring or response strategy according to these parameters. Step S820, using the adaptive control parameters to perform removal fitting, and verifying the cleaning effect through the response data set, and establishing a cleaning effect verification result. Specifically, using a simulation tool, using the received adaptive control parameters, combined with the working characteristics of the ultrasonic module, the removal process is fitted to predict the removal effect of the sediment under given control parameters. By comparing the fitting results with the actual removal effects in the response data set (such as the amount of sediment reduction, the degree of water quality improvement, etc.), the effectiveness of the adaptive control parameters is verified. According to the verification results, the removal effect is quantified, and it is evaluated whether the expected goal is achieved. Step S830, a feedback strategy is established based on the verification results of the removal effect, and the parameter feedback optimization of the ultrasonic module is performed according to the feedback strategy. Specifically, the verification results are analyzed to find out the gap between the actual removal effect and the expected goal and its reasons. According to the analysis results, a feedback strategy is formulated, including adjusting the rules of the adaptive control parameters, optimizing the working mode of the ultrasonic module, or improving the monitoring method of the self-feedback unit. According to the feedback strategy, the control parameters of the ultrasonic module are feedback optimized, including fine-tuning, reconfiguration or complete replacement of the parameters to ensure that the sediment removal effect is optimal. In the sediment detection and removal process of the ultrasonic-assisted ToF water level monitoring equipment, due to the complexity and variability of environmental factors (such as water quality, sediment type, pipeline conditions, etc.), the pre-set adaptive control parameters cannot achieve the best results in all cases. This implementation method introduces a self-feedback unit and a cleaning effect verification mechanism to monitor and evaluate the cleaning effect in real time, and dynamically adjust and optimize the control parameters according to actual conditions, thereby achieving the technical effect of improving system performance and stability.

[0051] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A method for detecting and removing sedimentation of an ultrasonically assisted ToF water level monitoring device, characterized in that: The method comprises: Performing periodic monitoring of a pipe water inlet on a ToF water level monitoring device to establish a periodic data set, wherein the pipe water inlet is provided with a permeable net; performing a sediment accumulation evaluation based on the periodic data set, configuring a sensor group using the sediment accumulation evaluation result, and establishing a periodic cleaning strategy for an ultrasonic module using the periodic data set; The ultrasonic module is controlled to perform periodic cleaning using a periodic cleaning strategy, and the sediment data at the water inlet of the pipeline is collected using a sensor group to establish a sediment data set; Conduct water level monitoring impact assessment using the sediment dataset and establish time series impact assessment results; Execute water level change prediction in the monitored area, and generate a first decision-making influencing factor according to the water level change prediction result and the time series impact evaluation result; Conducting a cost analysis of real-time cleaning and accumulation cleaning based on the sediment data set to establish a second decision-making influencing factor; Conducting cleaning effect evaluation of real-time cleaning and accumulation cleaning based on the sediment data set, and establishing a third decision-making influencing factor; Decision optimization is performed according to the first decision influencing factor, the second decision influencing factor, and the third decision influencing factor, and a decision optimization result is established. Adaptive control parameters of the ultrasonic module are generated according to the decision optimization result, and the ultrasonic module is controlled based on the adaptive control parameters to remove sediment at the water inlet of the pipeline.

2. A method for detecting and removing sedimentation of an ultrasonic-assisted ToF water level monitoring device as claimed in claim 1, characterized in that: The first decision influencing factor is calculated as follows: Among them, F1(t) represents the first decision-making influencing factor that changes with time, ΔH(t) represents the water level change at time t, S(t) represents the evaluation result of the sediment accumulation time series impact at time t, α(t) is the time-dependent weight factor of water level change, β(t) is the interactive influence weight factor of sediment accumulation time series impact and water level change, Impact seq (S(t), ΔH(t)) is the dependency of the temporal impact of sediment accumulation and water level change, Impact seq (S(t),ΔH(t))=β(t)·S(t)·|ΔH(t)|, which reflects the interactive effect of the temporal influence of sediment accumulation and the water level change.

3. The method for detecting and removing sedimentation of an ultrasonic-assisted ToF water level monitoring device according to claim 1, characterized in that: The second decision-making influence factor is calculated as follows: Among them, F2(t) represents the second decision-making influencing factor that changes over time, Cost real-time (τ) represents the real-time cleaning cost at time τ, Cost adaptive-periodic (τ,t c ) represents the cycle cleaning cost, t c It represents the cost-effectiveness time inflection point, c1 is the cleaning cost per unit time before the cost-effectiveness time inflection point, and c2 is the cleaning cost per unit time after the cost-effectiveness time inflection point.

4. The method for detecting and removing sediments of an ultrasonic-assisted ToF water level monitoring device according to claim 1, characterized in that: The sensor group includes at least one or more of an ultrasonic sensor, a turbidity sensor, an optical sensor, a pressure sensor, and a conductivity sensor.

5. The method for detecting and removing sedimentation of an ultrasound-assisted ToF water level monitoring device according to claim 1, characterized in that: The step of performing water level monitoring impact assessment using the sediment data set and establishing a time series impact assessment result further includes: Establishing an evaluation model, wherein the evaluation model is a relationship model describing sediment characteristics and water level reading indicators; After the sediment features are extracted from the sediment data set, the data are input into the evaluation model to generate a temporal impact evaluation result.

6. The method for detecting and removing sedimentation of an ultrasound-assisted ToF water level monitoring device according to claim 1, characterized in that: The method further comprises: Establishing a self-feedback unit, performing response monitoring of the water inlet of the pipeline based on the self-feedback unit, establishing a response data set, and receiving the adaptive control parameter through the self-feedback unit; Using the adaptive control parameters to perform removal fitting, and verifying the removal effect through the response data set, and establishing a removal effect verification result; A feedback strategy is established according to the cleaning effect verification result, and parameter feedback optimization of the ultrasound module is performed according to the feedback strategy.

7. The method for detecting and removing sediments of an ultrasonic-assisted ToF water level monitoring device according to claim 1, characterized in that: The sediment accumulation assessment based on the periodic data set further includes: If the sediment accumulation evaluation result fails to meet the preset evaluation threshold, a non-monitoring instruction is generated; The fixed ultrasonic cleaning parameters are configured according to the non-monitoring instructions and the sediment accumulation evaluation result to control the ultrasonic module to perform sediment removal at the water inlet of the pipeline.

8. The method for detecting and removing sediments of an ultrasound-assisted ToF water level monitoring device according to claim 1, characterized in that: The step of executing the water level change prediction of the monitored area also includes: Establish device association for ToF water level monitoring equipment; Performing data accuracy evaluation based on the equipment association and the sediment data set at the water inlet of the corresponding equipment pipeline; Water level change prediction is performed based on data accuracy evaluation results, readings from ToF water level monitoring devices, device correlation, and weather data.

Images