A rice field gate anti-clogging intelligent monitoring control method

Abstract

The present application relates to the technical field of data processing, and especially relates to a kind of paddy field gate anti-clogging intelligent monitoring control method, the method obtains the multidimensional monitoring data of gate at each monitoring time instant in real time, the multidimensional monitoring data of gate at each monitoring time instant in each running process is formed into multidimensional monitoring data sequence, and one multidimensional monitoring data sequence corresponds to one gate running process;For any gate running process, according to the multidimensional monitoring data sequence corresponding to any gate running process, the optimized gate clogging coefficient of any gate running process is obtained;The optimized gate clogging coefficient of each gate running process is obtained, the optimized gate clogging coefficient of each gate running process is used to obtain gate clogging trend index, according to the optimized gate clogging coefficient of current gate running process and gate clogging trend index, gate anti-clogging intelligent monitoring control is carried out, and early, quantitative and trend monitoring of gate clogging state is realized.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to an intelligent monitoring and control method for preventing siltation in paddy field gates. Background Technology

[0002] In the typical agricultural water conservancy scenario of paddy field irrigation and drainage systems, the gate, as a key actuator for controlling water flow and regulating field water levels, directly affects irrigation efficiency. To address the common problem of gate clogging, existing technologies primarily rely on single-parameter alarm methods based on fixed thresholds. This involves real-time monitoring of the gate drive motor current or the water level difference before and after the gate, triggering an alarm when these values ​​exceed a preset safety threshold. The advantages of this method are its clear and direct monitoring logic, the mature and low-cost deployment of the current transmitters and water level gauges it relies on, and its ability to effectively alert to faults and prevent equipment overload damage when clogging has already occurred and significantly impacted equipment operation.

[0003] With the development of precision agriculture and smart water conservancy, this type of threshold alarm technology has been widely integrated into remote monitoring platforms, forming a standardized operation and maintenance process from data collection and status display to manual intervention. This provides basic support for upgrading the operation and maintenance mode from relying entirely on manual inspection to remote centralized monitoring, and has important practical value in ensuring the basic functions of gates and avoiding sudden functional failures.

[0004] Although existing single-parameter alarm technology based on fixed thresholds can effectively trigger alarms when the gate is severely blocked or the parameters are significantly exceeded, in the actual dynamic environment of paddy field irrigation and drainage, when faced with normal operating conditions such as water flow fluctuations, seasonal changes in sediment content, and gradual blockage of the gate itself, this method has significant limitations: it cannot identify and quantify the early accumulation process of blockage, resulting in delayed early warning and failing to support preventive maintenance decisions.

[0005] Therefore, how to utilize gate-related data in the dynamic environment of paddy field irrigation and drainage to achieve early, quantitative, and trend-based monitoring of gate blockage has become an urgent problem to be solved. Summary of the Invention

[0006] In view of this, embodiments of the present invention provide an intelligent monitoring and control method for preventing siltation of paddy field gates, in order to solve the problem of how to use gate-related data in the dynamic environment of paddy field irrigation and drainage to achieve early, quantitative and trend monitoring of gate siltation status.

[0007] This invention provides an intelligent monitoring and control method for preventing siltation of paddy field gates, which includes the following steps:

[0008] The gate acquires multidimensional monitoring data at each monitoring moment in real time, and combines the multidimensional monitoring data at each monitoring moment during each gate operation into a multidimensional monitoring data sequence. One gate operation corresponds to one multidimensional monitoring data sequence. The multidimensional monitoring data includes current data, upstream water level data, downstream water level data, and opening degree data.

[0009] After the current gate operation process ends, for any gate operation process, based on the current data, upstream water level data and downstream water level data in the multi-dimensional monitoring data sequence corresponding to the gate operation process, the gate siltation coefficient of the gate operation process is obtained.

[0010] Based on the opening data in the multi-dimensional monitoring data sequence corresponding to any gate operation process, the gate clogging coefficient of any gate operation process is adjusted to obtain the optimized gate clogging coefficient of any gate operation process.

[0011] The optimized gate clogging coefficient for each gate operation is obtained. Using the optimized gate clogging coefficient for each gate operation, a gate clogging trend index is obtained. Based on the optimized gate clogging coefficient for the current gate operation and the gate clogging trend index, intelligent monitoring and control of gate anti-clogging is performed.

[0012] Preferably, obtaining the gate siltation coefficient for any given gate operation based on the current data, upstream water level data, and downstream water level data in the multi-dimensional monitoring data sequence corresponding to any given gate operation includes:

[0013] Obtain the reference current data and reference water level difference data for any given gate operation process;

[0014] The cumulative value of the absolute difference between the current data at each monitoring moment during any gate operation and the reference current data is obtained and recorded as the current data difference cumulative value. The number of monitoring moments during any gate operation is obtained and recorded as the data number. The cumulative value of the data number of reference current data is obtained and recorded as the reference current data cumulative value. The ratio of the current data difference cumulative value to the reference current data cumulative value is calculated to obtain the degree of blockage of the first gate.

[0015] The difference between the upstream and downstream water level data at each monitoring moment during any gate operation is obtained. One water level difference data is obtained for each monitoring moment. The cumulative value of the absolute value of the difference between the water level difference data at each monitoring moment during any gate operation and the reference water level difference data is obtained and recorded as the cumulative value of the water level difference data difference. The cumulative value of the data of the reference water level difference data is obtained and recorded as the cumulative value of the reference water level difference data difference. The ratio of the cumulative value of the water level difference data difference to the cumulative value of the reference water level difference data difference is calculated to obtain the degree of siltation of the second gate.

[0016] The gate clogging coefficient for any given gate operation is obtained by weighted summation of the degree of clogging of the first gate and the degree of clogging of the second gate.

[0017] Preferably, the step of adjusting the gate clogging coefficient for any given gate operation process based on the opening data in the multi-dimensional monitoring data sequence corresponding to that gate operation process, to obtain the optimized gate clogging coefficient for that given gate operation process, includes:

[0018] The maximum value of the opening data at each monitoring moment during any gate operation is obtained and recorded as the target opening data of the gate operation. The maximum opening data of the gate is obtained, and the ratio of the target opening data to the maximum opening data of the gate is calculated to obtain the opening percentage of the gate operation.

[0019] Obtain the product of the preset gate opening adjustment coefficient and the opening ratio, substitute the negative of the product into an exponential function with the natural constant as the base, obtain the exponential function result, obtain the difference between the constant 1 and the exponential function result, and obtain the self-cleaning degree of the gate operation process in any given time.

[0020] Obtain the maximum self-cleaning ratio of the gate, calculate the product of the maximum self-cleaning ratio of the gate and the self-cleaning degree of any gate operation process to obtain the self-cleaning index, obtain the difference between the self-cleaning index and the constant 1 to obtain the sludge remaining index of any gate operation process.

[0021] The product of the remaining siltation index and the gate siltation coefficient for any given gate operation is obtained to get the optimized gate siltation coefficient for that given gate operation.

[0022] Preferably, the step of optimizing the gate clogging coefficient and obtaining the gate clogging trend index using each gate operation process includes:

[0023] Based on the time difference between each gate operation process and the current gate operation process, the siltation impact coefficient for each gate operation process is obtained;

[0024] The siltation impact coefficient of each gate operation process is used as the weighting coefficient of the optimized gate siltation coefficient for each gate operation process. The weighted least squares method is used to fit the siltation impact coefficient of each gate operation process to obtain the fitting curve. The slope of the fitting curve is obtained as the gate siltation trend indicator.

[0025] Preferably, the step of obtaining the siltation impact coefficient for each gate operation process based on the time difference between each gate operation process and the current gate operation process includes:

[0026] Each gate operation process is numbered according to time sequence. For any given gate operation process, the difference between the current gate operation process number and the number of the previous gate operation process is obtained to get the number difference value. The negative of the ratio of the number difference value to the preset time decay coefficient is substituted into an exponential function with the natural constant as the base to obtain the siltation impact coefficient of the given gate operation process.

[0027] Preferably, the method for acquiring the reference current data includes:

[0028] During the gate's non-clogging test operation phase, the gate's opening data and the corresponding current data when each preset opening data is reached are obtained. A linear fit is performed with each preset opening data as the horizontal axis and the corresponding current data as the vertical axis to obtain a fitted straight line.

[0029] The current data corresponding to the target opening data of any gate operation process is obtained by using the fitted straight line, and is used as the reference current data.

[0030] Preferably, the reference water level difference data is calculated using the formula for the free outflow rate of the gate opening of a flat sluice gate.

[0031] The beneficial effects of the embodiments of the present invention compared with the prior art are as follows:

[0032] In this invention, the gate siltation coefficient is obtained for any gate operation process. The mechanical resistance reflected by the current data (a short-term sensitive indicator) and the flow obstruction effect indirectly reflected by the water level data (a long-term development indicator) are quantitatively correlated to more comprehensively and reliably characterize the gate siltation situation after any gate operation process. The larger the gate siltation coefficient, the more severe the gate siltation. The gate siltation coefficient is adjusted according to the opening data to obtain the optimized gate siltation coefficient for any gate operation process, which more accurately characterizes the gate siltation situation after any gate operation process. Gate siltation trend indicators are obtained to analyze the gate siltation development trend after the gate operation process ends. Ultimately, early, quantitative, and trend monitoring of the gate siltation status is achieved. Attached Figure Description

[0033] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0034] Figure 1 This is a flowchart of a method for intelligent monitoring and control of paddy field gates to prevent siltation, provided in Embodiment 1 of the present invention. Detailed Implementation

[0035] Embodiments of this disclosure are described in detail below, with examples of these embodiments illustrated in the accompanying drawings. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this disclosure, and should not be construed as limiting it.

[0036] It should be noted that the terms "first," "second," etc., used in this disclosure and the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure.

[0037] To illustrate the technical solution of the present invention, specific embodiments are described below.

[0038] See Figure 1 This is a flowchart of a method for intelligent monitoring and control of paddy field gates to prevent siltation, provided in Embodiment 1 of the present invention. Figure 1 As shown, the method may include:

[0039] Step S101: Real-time acquisition of multi-dimensional monitoring data of the gate at each monitoring moment. The multi-dimensional monitoring data of the gate at each monitoring moment during each operation are combined into a multi-dimensional monitoring data sequence. One gate operation process corresponds to one multi-dimensional monitoring data sequence. The multi-dimensional monitoring data includes current data, upstream water level data, downstream water level data and opening degree data.

[0040] In the typical agricultural water conservancy scenario of paddy field irrigation and drainage system, the gate is a key actuator for controlling water flow and regulating field water level. Its operation status is directly related to irrigation efficiency. To address the common problem of gate clogging, existing technologies mainly rely on a single-parameter alarm method based on a fixed threshold. This method monitors the gate drive motor current or the water level difference before and after the gate in real time and triggers an alarm when the value exceeds a preset safety threshold.

[0041] This embodiment synchronously collects multi-source time-series data, including gate drive motor current, paddy field water level, and gate opening. This data is then filtered, aligned, and formatted to eliminate noise and unify the time reference. This transforms the raw, chaotic sensor signals into a standardized data sequence that can be directly computed by the algorithm. This data is used to analyze gate blockage and achieve early, quantitative, and trend-based monitoring of gate blockage. This embodiment uses a tilting gate, which differs from a planar gate, and the data acquisition frequency is 10Hz. This is not a limitation and can be set according to the specific implementation scenario.

[0042] The specific steps of data acquisition are as follows: (1) Synchronous acquisition of multi-source data: The controller synchronously acquires the current, water level and opening sensor data of the gate at each monitoring moment to obtain current data (gate drive motor current), upstream water level data, downstream water level data and opening data, ensuring that all data streams have a unified time reference, laying the foundation for subsequent fusion calculation; (2) Timing synchronization and noise removal: Low-pass filtering is used on the acquired current data to eliminate high-frequency electrical noise; Moving average filtering is used on the acquired upstream water level data and downstream water level data to smooth the measurement jitter caused by water surface fluctuations, thereby extracting the signal that reflects the real physical process. Trend; (3) Eliminate outliers: Identify and eliminate non-physical mutations, such as short-term power outages, sampling spikes, sensor jitter, and other outlier data points, and fill them in with the nearest time series data; (4) Data slicing: Based on the changes in gate opening, automatically identify the action range of each opening and closing of the gate, and cut all sensor data within that time period into an independent data segment, that is, the current data, upstream water level data, downstream water level data and opening data of each monitoring moment after preprocessing are combined into multi-dimensional monitoring data, and the multi-dimensional monitoring data of each monitoring moment during each gate operation are combined into a multi-dimensional monitoring data sequence, and one gate operation process corresponds to one multi-dimensional monitoring data sequence.

[0043] In the actual dynamic environment of paddy field irrigation and drainage, existing methods have significant limitations when facing normal operating conditions such as water flow fluctuations, seasonal changes in sediment content, and gradual siltation of the gate itself: they cannot identify and quantify the early accumulation process of siltation, resulting in delayed early warning and inability to support preventive maintenance decisions.

[0044] Therefore, after acquiring multidimensional monitoring data of the gate, this embodiment of the invention obtains the optimized gate siltation coefficient for each gate operation process through current-water level dual-source data fusion and self-cleaning effect correction based on opening degree. This more accurately characterizes the gate siltation situation after the gate operation process ends, thereby obtaining gate siltation trend indicators, analyzing the gate siltation development trend after the gate operation process ends, and ultimately achieving early, quantitative, and trend-based monitoring of the gate siltation status.

[0045] Step S102: After the current gate operation process ends, for any gate operation process, based on the current data, upstream water level data and downstream water level data in the multi-dimensional monitoring data sequence corresponding to the any gate operation process, obtain the gate siltation coefficient for the any gate operation process.

[0046] In existing methods, although current data and water level data are collected, they are only used independently for comparison with fixed thresholds. The siltation status information contained in the two data, which can corroborate or supplement each other, is not effectively correlated and utilized.

[0047] To address the issue that single parameters (current or water level) are easily affected by interference and cannot comprehensively characterize the siltation status, this embodiment, after the current gate operation process ends, for any gate operation process, through data fusion, obtains the gate siltation coefficient for any gate operation process based on the current data, upstream water level data, and downstream water level data in the multi-dimensional monitoring data sequence corresponding to that gate operation process. It quantitatively correlates the mechanical resistance reflected by the current (siltation sticks to the gate, making it heavier, requiring more force to lift, and thus resulting in abnormally high power consumption) with the flow obstruction reflected by the water level (siltation leads to abnormally high local water levels), thus more comprehensively and reliably characterizing the gate siltation situation after any gate operation process ends.

[0048] The method for obtaining the gate siltation coefficient for any given gate operation process based on the current data, upstream water level data, and downstream water level data in the multi-dimensional monitoring data sequence corresponding to any given gate operation process is as follows:

[0049] During the gate's non-clogging test operation phase, the current data corresponding to each preset opening value of the gate is obtained. In this embodiment, the current data when the gate opening value reaches 10%, 20%, 30%, ..., 100% is obtained. With each preset opening value as the horizontal axis and the current data corresponding to each preset opening value as the vertical axis, the least squares method is used for linear fitting to obtain a fitted straight line. The least squares method is an existing technology and will not be described in detail here. The current data corresponding to the target opening value of any gate operation process is obtained using the fitted straight line (the target opening value of the gate is set manually each time it is opened. For example, the target opening value can be set to 90% or 100% when large-scale irrigation is needed, and 10% when drip irrigation is needed). This is used as the reference current data for any gate operation process.

[0050] The reference water level difference data for any gate operation process is obtained by calculating the free outflow flow rate of the flat gate orifice using the formula. The formula for the free outflow flow rate of the flat gate orifice and the calculation of the reference water level difference data using the formula are existing technologies and will not be elaborated here.

[0051] The cumulative value of the absolute difference between the current data at each monitoring moment during any gate operation and the reference current data is obtained and recorded as the current data difference cumulative value. The number of monitoring moments during any gate operation is obtained and recorded as the data number. The cumulative value of the data number of reference current data is obtained and recorded as the reference current data cumulative value. The ratio of the current data difference cumulative value to the reference current data cumulative value is calculated to obtain the degree of blockage of the first gate.

[0052] The difference between the upstream and downstream water level data at each monitoring moment during any gate operation is obtained. One water level difference data is obtained for each monitoring moment. The cumulative value of the absolute value of the difference between the water level difference data at each monitoring moment during any gate operation and the reference water level difference data is obtained and recorded as the cumulative value of the water level difference data difference. The cumulative value of the data of the reference water level difference data is obtained and recorded as the cumulative value of the reference water level difference data difference. The ratio of the cumulative value of the water level difference data difference to the cumulative value of the reference water level difference data difference is calculated to obtain the degree of siltation of the second gate.

[0053] The gate clogging coefficient for any given gate operation is obtained by weighted summation of the degree of clogging of the first gate and the degree of clogging of the second gate.

[0054] In one implementation, taking the i-th gate operation as an example, it is assumed that the target opening data for the i-th gate operation is... The formula for calculating the gate blockage coefficient during the i-th gate operation is:

[0055]

[0056] in, Let be the gate clogging coefficient during the i-th gate operation; For the i-th gate operation (target opening data is...) The current data at the t-th monitoring time; For the i-th gate operation (target opening data is...) The reference current data is T; T is the number of data points, i.e., the number of monitoring moments during the i-th gate operation. For the i-th gate operation (target opening data is...) The water level difference data at the t-th monitoring time is the difference between the upstream water level data and the downstream water level data at the t-th monitoring time during the i-th gate operation. For the i-th gate operation (target opening data is...) (Base water level difference data); It is the first weight; As the second weight; It is the absolute value symbol.

[0057] It should be noted that, The degree of blockage in the first gate represents the proportion of the current deviation used to overcome blockage to the reference current during the i-th gate operation. The larger the value, the greater the difference between the current data at monitoring time t during the i-th gate operation and the reference current data. In other words, the greater the deviation from the reference current data, the more likely the current deviation is due to gate blockage. The larger it is, the better. The larger it is; The degree of siltation at the second gate represents the proportion of the increase in water level due to siltation during the i-th gate operation to the theoretical normal water level difference. The larger the value, the greater the difference between the water level difference data at monitoring time t during the i-th gate operation and the reference water level difference data. In other words, the greater the deviation from the reference water level difference data, the more likely the deviation is due to gate blockage. The larger it is, the better. The larger it is; The larger the value, the more severe the gate blockage during the i-th gate operation; since the mechanical resistance represented by the current data is highly sensitive, this embodiment sets... , There are no restrictions here; settings can be made according to the specific implementation scenario.

[0058] Thus, the gate clogging coefficient for any given gate operation is obtained.

[0059] Step S103: Based on the opening data in the multi-dimensional monitoring data sequence corresponding to any gate operation process, adjust the gate clogging coefficient of any gate operation process to obtain the optimized gate clogging coefficient of any gate operation process.

[0060] Because the tilting gate has a self-cleaning effect (when the tilting gate is opened, it tilts and presses down, and the water flow will have a brief and rapid backflow to flush, achieving a partial cleaning effect of siltation), if the gate siltation coefficient obtained in step S102 is used directly to analyze the gate siltation situation, the siltation state will be overestimated because the self-cleaning is not considered, making the analysis results of each siltation situation inaccurate.

[0061] Since a larger gate opening results in a greater downward tilt of the gate, a larger volume and degree of water pressure, and a better self-cleaning effect, this embodiment uses opening data to quantify the self-cleaning effect of each gate opening. Based on the opening data in the multi-dimensional monitoring data sequence corresponding to any gate operation process, the gate clogging coefficient of any gate operation process is adjusted to obtain the optimized gate clogging coefficient of any gate operation process, which more accurately characterizes the gate clogging situation after the end of any gate operation process.

[0062] The method for adjusting the gate clogging coefficient for any given gate operation based on the opening data in the multi-dimensional monitoring data sequence corresponding to any given gate operation, to obtain the optimized gate clogging coefficient for any given gate operation, is as follows:

[0063] The maximum value of the opening data at each monitoring moment during any gate operation is obtained and recorded as the target opening data of the gate operation. The maximum opening data of the gate is obtained, and the ratio of the target opening data to the maximum opening data of the gate is calculated to obtain the opening percentage of the gate operation.

[0064] Obtain the product of the preset gate opening adjustment coefficient and the opening ratio, substitute the negative of the product into an exponential function with the natural constant as the base, obtain the exponential function result, obtain the difference between the constant 1 and the exponential function result, and obtain the self-cleaning degree of the gate operation process. The preset gate opening adjustment coefficient is used to adjust the degree of influence of the opening data on the gate self-cleaning. In this embodiment, the value of the gate opening speed (the gate opening speed is a constant value and can be directly obtained from the gate product manual) is taken as the preset gate opening adjustment coefficient. The faster the gate opening speed, the better the gate self-cleaning effect. There is no limitation here, and it can be set according to the specific implementation scenario.

[0065] Obtain the maximum self-cleaning ratio of the gate, calculate the product of the maximum self-cleaning ratio of the gate and the self-cleaning degree of any gate operation process to obtain the self-cleaning index, obtain the difference between the self-cleaning index and the constant 1 to obtain the remaining sludge index of any gate operation process. The maximum self-cleaning ratio of the gate represents the maximum sludge ratio that the gate can clean at the maximum opening (obtained by repeatedly adding sludge manually, taking out and measuring the remaining sludge after the opening is at the maximum, and taking the average value after repeated iterations). There is no limit here, and it can be set according to the specific implementation scenario.

[0066] The product of the remaining siltation index and the gate siltation coefficient for any given gate operation is obtained to get the optimized gate siltation coefficient for that given gate operation.

[0067] In one implementation, taking the i-th gate operation as an example, it is assumed that the target opening data for the i-th gate operation is... The formula for calculating the optimal gate clogging coefficient during the i-th gate operation is:

[0068]

[0069] in, The optimized gate clogging coefficient is given for the i-th gate operation process. Let be the gate clogging coefficient during the i-th gate operation; This represents the maximum self-cleaning ratio of the gate. The preset gate opening adjustment coefficient; This refers to the target opening data for the i-th gate operation. represents the maximum opening degree of the gate; e is the natural constant.

[0070] It should be noted that, Let represent the degree of self-cleaning during the i-th gate operation. Let i be the percentage of the gate opening during the i-th gate operation. The larger the gate, the better its self-cleaning effect. The larger it is, the better. An exponential decay method is used to simulate the phenomenon of gradual saturation as the opening degree increases; The remaining siltation index during the i-th gate operation process. The larger the gate, the better its self-cleaning effect, and the less residual sludge will remain. The smaller the value, the less sludge remains in the gate. This indicates that the gate sludge coefficient during the i-th gate operation may overestimate the sludge situation due to the gate's self-cleaning effect. The smaller it is.

[0071] Thus, the optimized gate clogging coefficient for any given gate operation process is obtained.

[0072] Step S104: Obtain the optimized gate clogging coefficient for each gate operation process; use the optimized gate clogging coefficient for each gate operation process to obtain the gate clogging trend index; and perform intelligent monitoring and control of gate anti-clogging based on the optimized gate clogging coefficient and the gate clogging trend index for the current gate operation process.

[0073] Step S103 quantifies the self-cleaning effect to obtain a more stable and comparable optimized gate clogging coefficient. However, a single coefficient can only describe the instantaneous state and cannot determine whether the clogging is improving or worsening.

[0074] Therefore, this embodiment obtains the optimized gate clogging coefficient for each gate operation process according to the above-mentioned method for obtaining the optimized gate clogging coefficient for any gate operation process. Using the optimized gate clogging coefficient for each gate operation process, the gate clogging trend index is obtained, and the gate clogging development trend after the gate operation process ends is analyzed. The gate clogging situation is intuitively quantified as to whether it is improving, stabilizing, or deteriorating, and finally, the early, quantitative, and trend monitoring of the gate clogging status is achieved.

[0075] The method for obtaining the gate clogging trend index by optimizing the gate clogging coefficient during each gate operation is as follows:

[0076] Each gate operation process is numbered according to time sequence. For any given gate operation process, the difference between the current gate operation process number and the number of the previous gate operation process is obtained to get the number difference value. The negative of the ratio of the number difference value to the preset time decay coefficient is substituted into the exponential function with the natural constant as the base to obtain the siltation impact coefficient of the given gate operation process. The larger the preset time decay coefficient, the faster the siltation impact coefficient decays. According to experimental statistics, the preset time decay coefficient is set to 5 in this embodiment. There is no limitation here, and it can be set according to the specific implementation scenario.

[0077] Similarly, the siltation impact coefficient of each gate operation process is obtained, and the siltation impact coefficient of each gate operation process is used as the weight coefficient of the optimized gate siltation coefficient of each gate operation process. The weighted least squares method is used to perform weighted fitting on the siltation impact coefficient of each gate operation process to obtain the fitting curve. The slope of the fitting curve is obtained as the gate siltation trend indicator.

[0078] In one embodiment, the formula for calculating the gate clogging trend index is:

[0079]

[0080] Where k is the gate clogging trend indicator; This is the number for the current gate operation process; This is the number of the i-th gate operation process; The preset time decay coefficient is N; N is the total number of gate operation cycles. This is a weighted average of the numbering of the gate operation process; The optimized gate clogging coefficient is given for the i-th gate operation process. To optimize the weighted average of the gate clogging coefficient; It is an exponential function with the natural constant as the base.

[0081] It should be noted that, Let be the siltation impact coefficient for the i-th gate operation process, which is also the weighting coefficient of the optimized gate siltation coefficient for the i-th gate operation process. The smaller the value, the closer the time between the i-th gate operation and the current gate operation, and the stronger the importance of the siltation impact coefficient of the i-th gate operation. The larger the value, the better. The use of weighted least squares to perform weighted fitting to obtain the fitted curve, and the calculation formula for the slope of the fitted curve (the calculation formula for the gate blockage trend index) are existing technologies and will not be elaborated here.

[0082] By weighted fitting of the siltation impact coefficient during each gate operation, discrete point information can be transformed into continuous, directional trend judgment. If k is positive, it intuitively quantifies the gradual accumulation and deterioration of siltation on the gate. If k is negative, it indicates that the gate is self-repairing or that the gate is effectively self-cleaning.

[0083] In order to obtain gate blockage trend indicators more accurately and analyze the development trend of gate blockage better, this embodiment starts intelligent monitoring after the gate is opened and closed for the fifth time (i.e. after the fifth gate operation process is completed). After the previous gate operation process is completed, the traditional method (i.e., the single-parameter alarm method based on a fixed threshold) is used for intelligent monitoring.

[0084] Furthermore, based on the optimized gate clogging coefficient and the gate clogging trend index during the current gate operation, intelligent monitoring and control for gate clogging prevention is implemented. This embodiment employs a mature multi-level control strategy for intelligent monitoring and control of gate clogging prevention, which can automatically trigger different levels of response measures according to the severity of the clogging trend, realizing a shift from passive alarm to proactive prevention in intelligent operation and maintenance. The general operation steps are as follows:

[0085] (1) Status judgment and threshold comparison: The optimized gate siltation coefficient obtained during the current gate operation process is compared with the preset multi-level threshold in real time to accurately judge the current siltation status of the gate. For example, an optimized gate siltation coefficient of 0.2 means that the gate siltation degree is 20%, which is usually the upper limit of normal factors such as sensor noise and water flow fluctuation. Therefore, 0-0.2 is normal. An optimized gate siltation coefficient of 0.5 means that the gate siltation degree is 50%. At this time, the siltation has begun to significantly affect the gate operation. Therefore, 0.2-0.5 is a first-level warning. An optimized gate siltation coefficient of 0.8 means that the gate siltation degree is 80%, which is close to the equipment's limit and requires immediate intervention. Therefore, 0.5-0.8 is a second-level warning. An optimized gate siltation coefficient of 1 means that the gate siltation degree is 100%. The equipment has reached its limit and must be shut down immediately. Therefore, 0.8-1 is a third-level warning. There is no restriction here, and it can be set according to the specific implementation scenario.

[0086] (2) Multi-level early warning threshold matching: Based on the current siltation status of the gate, the gate siltation trend index is used to determine whether the status is deteriorating or recovering and the degree of change. If it is deteriorating, the risk level is increased according to the degree of change. If it is recovering, the risk level is reduced or remains unchanged according to the degree of change, based on the risk level of the current siltation status of the gate.

[0087] (3) Risk level matching and early warning: Based on the obtained risk level, the corresponding control scheme is called from the preset strategy library. The strategy library contains response measures of different levels, such as adjusting the frequency of gate opening, modifying operating parameters, triggering self-cleaning program, arranging manual inspection, etc., and generates specific execution instructions and time plans.

[0088] (4) Command issuance and execution feedback: The generated control commands are issued to the gate actuator (such as BayDrive controller) and monitoring platform through the control network to perform adaptive adjustments. At the same time, the effect of command execution is continuously monitored, and the effectiveness of control measures is verified by the feedback real-time data. If the sludge condition continues to worsen, manual intervention is activated.

[0089] In summary, in this embodiment of the invention, the gate siltation coefficient for any given gate operation is obtained. The mechanical resistance reflected by the current data (a short-term sensitive indicator) and the flow obstruction effect indirectly reflected by the water level data (a long-term development indicator) are quantitatively correlated. This provides a more comprehensive and reliable characterization of the gate siltation situation after any given gate operation. The larger the gate siltation coefficient, the more severe the siltation. The gate siltation coefficient is adjusted based on the opening data to obtain an optimized gate siltation coefficient for any given gate operation, providing a more accurate characterization of the siltation situation after any given gate operation. Gate siltation trend indicators are obtained to analyze the development trend of gate siltation after the end of the gate operation. Ultimately, this achieves early, quantitative, and trend-based monitoring of the gate siltation status.

[0090] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A method for intelligent monitoring and control of siltation prevention in paddy field gates, characterized in that, The aforementioned intelligent monitoring and control method for preventing siltation and blockage of paddy field gates includes: The gate acquires multidimensional monitoring data at each monitoring moment in real time, and combines the multidimensional monitoring data at each monitoring moment during each gate operation into a multidimensional monitoring data sequence. One gate operation corresponds to one multidimensional monitoring data sequence. The multidimensional monitoring data includes current data, upstream water level data, downstream water level data, and opening degree data. After the current gate operation process ends, for any gate operation process, based on the current data, upstream water level data and downstream water level data in the multi-dimensional monitoring data sequence corresponding to the gate operation process, the gate siltation coefficient of the gate operation process is obtained. Based on the opening data in the multi-dimensional monitoring data sequence corresponding to any gate operation process, the gate clogging coefficient of any gate operation process is adjusted to obtain the optimized gate clogging coefficient of any gate operation process. The optimized gate clogging coefficient for each gate operation process is obtained. Using the optimized gate clogging coefficient for each gate operation process, the gate clogging trend index is obtained. Based on the optimized gate clogging coefficient for the current gate operation process and the gate clogging trend index, intelligent monitoring and control of gate anti-clogging is carried out. The step of obtaining the gate siltation coefficient for any given gate operation based on the current data, upstream water level data, and downstream water level data in the multi-dimensional monitoring data sequence corresponding to any given gate operation includes: Obtain the reference current data and reference water level difference data for any given gate operation process; The cumulative value of the absolute difference between the current data at each monitoring moment during any gate operation and the reference current data is obtained and recorded as the current data difference cumulative value. The number of monitoring moments during any gate operation is obtained and recorded as the data number. The cumulative value of the data number of reference current data is obtained and recorded as the reference current data cumulative value. The ratio of the current data difference cumulative value to the reference current data cumulative value is calculated to obtain the degree of blockage of the first gate. The difference between the upstream and downstream water level data at each monitoring moment during any gate operation is obtained. One water level difference data is obtained for each monitoring moment. The cumulative value of the absolute value of the difference between the water level difference data at each monitoring moment during any gate operation and the reference water level difference data is obtained and recorded as the cumulative value of the water level difference data difference. The cumulative value of the data of the reference water level difference data is obtained and recorded as the cumulative value of the reference water level difference data difference. The ratio of the cumulative value of the water level difference data difference to the cumulative value of the reference water level difference data difference is calculated to obtain the degree of siltation of the second gate. The gate clogging coefficient for any given gate operation is obtained by weighted summation of the degree of clogging of the first gate and the degree of clogging of the second gate. The step of adjusting the gate clogging coefficient for any given gate operation based on the opening data in the multidimensional monitoring data sequence corresponding to any given gate operation to obtain the optimized gate clogging coefficient for any given gate operation includes: The maximum value of the opening data at each monitoring moment during any gate operation is obtained and recorded as the target opening data of the gate operation. The maximum opening data of the gate is obtained, and the ratio of the target opening data to the maximum opening data of the gate is calculated to obtain the opening percentage of the gate operation. Obtain the product of the preset gate opening adjustment coefficient and the opening ratio, substitute the negative of the product into an exponential function with the natural constant as the base, obtain the exponential function result, obtain the difference between the constant 1 and the exponential function result, and obtain the self-cleaning degree of the gate operation process in any given time. Obtain the maximum self-cleaning ratio of the gate, calculate the product of the maximum self-cleaning ratio of the gate and the degree of self-cleaning during any gate operation to obtain the self-cleaning index, obtain the difference between the constant 1 and the self-cleaning index to obtain the remaining sludge index during any gate operation. The product of the remaining siltation index and the gate siltation coefficient for any given gate operation is obtained to get the optimized gate siltation coefficient for that given gate operation.

2. The intelligent monitoring and control method for preventing siltation of paddy field gates according to claim 1, characterized in that, The method of optimizing the gate clogging coefficient during each gate operation to obtain gate clogging trend indicators includes: Based on the time difference between each gate operation process and the current gate operation process, the siltation impact coefficient for each gate operation process is obtained; The siltation impact coefficient of each gate operation process is used as the weighting coefficient of the optimized gate siltation coefficient for each gate operation process. The weighted least squares method is used to fit the siltation impact coefficient of each gate operation process to obtain the fitting curve. The slope of the fitting curve is obtained as the gate siltation trend indicator.

3. The intelligent monitoring and control method for preventing siltation of paddy field gates according to claim 2, characterized in that, The process of obtaining the siltation impact coefficient for each gate operation based on the time difference between each gate operation and the current gate operation includes: Each gate operation process is numbered according to time sequence. For any given gate operation process, the difference between the current gate operation process number and the number of the previous gate operation process is obtained to get the number difference value. The negative of the ratio of the number difference value to the preset time decay coefficient is substituted into an exponential function with the natural constant as the base to obtain the siltation impact coefficient of the given gate operation process.

4. The intelligent monitoring and control method for preventing siltation of paddy field gates according to claim 1, characterized in that, The method for obtaining the reference current data includes: During the gate's non-clogging test operation phase, the gate's opening data and the corresponding current data when each preset opening data is reached are obtained. A linear fit is performed with each preset opening data as the horizontal axis and the corresponding current data as the vertical axis to obtain a fitted straight line. The current data corresponding to the target opening data of any gate operation process is obtained by using the fitted straight line, and is used as the reference current data.

5. The intelligent monitoring and control method for preventing siltation of paddy field gates according to claim 1, characterized in that, The reference water level difference data is calculated using the formula for the free outflow rate of the gate opening of a flat sluice gate.

Images