Pipe culvert gate intelligent control method based on data analysis

Abstract

The present application relates to the technical field of data processing, and more particularly to a pipe culvert gate intelligent control method based on data analysis, which obtains flow data and water level data of a pipe culvert gate at each moment, flow velocity data of each monitoring position in the pipe, and multi-dimensional state data of the pipe culvert gate; obtains a preliminary proportional adjustment coefficient according to the flow data deviation and water level data variation characteristics at the current moment; obtains a proportional coefficient adjustment factor according to the flow velocity data of each monitoring position at the current moment, the fluctuation characteristics of the water level data and flow data within a preset historical period, the flow data deviation at the current moment, and the multi-dimensional state data within the current moment and the preset historical period; and obtains an adaptive proportional coefficient according to the preliminary proportional adjustment coefficient and the proportional coefficient adjustment factor, which is used to use a PID control method to intelligently control the pipe culvert gate at the current moment, and improve the control accuracy and stability of the pipe culvert gate.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to an intelligent control method for culvert gates based on data analysis. Background Technology

[0002] In the field of water conservancy engineering, culvert gates, as important water flow control facilities, are widely used in irrigation, flood control, and water supply. Traditional culvert gate control methods mainly rely on manual experience or simple timed control, making it difficult to accurately regulate based on real-time water flow conditions, water level changes, and upstream and downstream demand. Manual operation is not only inefficient but also easily affected by subjective factors, leading to unreasonable timing and extent of gate opening or closing, resulting in water waste, localized flooding, or uneven irrigation. Furthermore, traditional control methods lack effective utilization of historical data, failing to extract patterns from large amounts of operational data to optimize control strategies.

[0003] With the development of water conservancy informatization and intelligence, the demand for precise, efficient and intelligent control of culvert gates is becoming increasingly urgent. Developing an intelligent control method for culvert gates based on data analysis can not only improve the efficiency of water resource utilization and the operation and management level of water conservancy projects, but also has important practical significance and broad application prospects.

[0004] Traditional PID control is simple in structure and easy to implement. A basic control framework can be quickly built using mature control theory, providing basic regulation capabilities for general operating conditions and maintaining relatively stable system operation. However, the core parameters of traditional PID control are usually fixed. For example, the proportional coefficient Kp directly affects the system response speed. Different operating conditions require different response speeds for gates. When a culvert gate faces different flow rates, water levels, and flow regimes, a fixed proportional coefficient Kp is difficult to flexibly adapt to complex and changing conditions, easily leading to response lag or overshoot, affecting control accuracy and stability.

[0005] Therefore, how to obtain an adaptive proportional coefficient based on changes in water flow and water level under different operating conditions, and improve the control accuracy and stability of PID control for culvert gates, has become an urgent problem to be solved. Summary of the Invention

[0006] In view of this, embodiments of the present invention provide a data analysis-based intelligent control method for culvert gates to solve the problem of how to obtain adaptive proportional coefficients based on water flow and water level changes under different operating conditions, thereby improving the control accuracy and stability of PID control for culvert gates.

[0007] This invention provides a data analysis-based intelligent control method for culvert gates, which includes the following steps:

[0008] The system acquires the flow rate and water level data of the pipeline where the culvert gate is located at every moment up to the current moment, as well as the flow velocity data at each monitoring location in the pipeline, and also acquires the multi-dimensional status data of the culvert gate at each moment.

[0009] Obtain the ideal flow rate data of the pipeline, and based on the difference between the current flow rate data and the ideal flow rate data, as well as the water level data change characteristics between the current time and the previous time, obtain the preliminary proportional adjustment coefficient for the current time.

[0010] Obtain the Reynolds number corresponding to the current moment. Based on the flow velocity data of each monitoring location at the current moment, the fluctuation characteristics of water level data and flow rate data in the preset historical period before the current moment, and the Reynolds number, obtain the flow stability adjustment factor at the current moment. Based on the difference between the flow rate data at the current moment and the ideal flow rate data, the multi-dimensional state data at the current moment and in the preset historical period, obtain the gate operation state adjustment factor at the current moment. Combine the flow stability adjustment factor and the gate operation state adjustment factor to obtain the proportional coefficient adjustment factor at the current moment.

[0011] Based on the preliminary proportional adjustment coefficient and the proportional coefficient adjustment factor, the initial value of the preset proportional coefficient in the PID control method is adjusted to obtain the adaptive proportional coefficient at the current moment. Based on the adaptive proportional coefficient, the PID control method is used to intelligently control the culvert gate at the current moment.

[0012] Preferably, the step of obtaining the preliminary proportional adjustment coefficient for the current moment based on the difference between the current flow data and the ideal flow data, and the water level data change characteristics between the current moment and the previous moment, includes:

[0013] Obtain the absolute value of the difference between the water level data at the current time and the previous time to get the water level data difference value; obtain the time interval between the current time and the previous time; calculate the ratio of the water level data difference value to the time interval to get the water level data change rate.

[0014] Obtain the absolute value of the difference between the current flow data and the ideal flow data to get the flow data difference value. Normalize the product of the flow data difference value and the water level change rate to get the preliminary proportional adjustment coefficient for the current moment.

[0015] Preferably, the step of obtaining the flow stability adjustment factor at the current moment based on the flow velocity data at each monitoring location at the current moment, the fluctuation characteristics of water level data and flow rate data in a preset historical period prior to the current moment, and the Reynolds number includes:

[0016] The eddy current intensity at each monitoring location in the pipeline at the current moment is obtained, and the mean eddy current intensity is obtained. The water level data in the preset historical period is used to form a water level data sequence. The number of peak data in the water level data sequence is added to the constant 1 to obtain the water level data fluctuation degree. The arithmetic square root of the product of the mean eddy current intensity and the water level data fluctuation degree is normalized to obtain the first flow instability degree at the current moment.

[0017] The mean flow velocity data of all monitoring locations in the pipeline at the current moment is obtained. The absolute value of the difference between the flow velocity data of each monitoring location in the pipeline at the current moment and the mean flow velocity data is calculated. The average value of the absolute value of the difference is obtained and recorded as the average flow velocity difference value. The arithmetic square root of the product of the reciprocal of the average flow velocity difference value and the Reynolds number is normalized to obtain the second flow instability degree at the current moment.

[0018] The flow data within a preset historical time period is organized into a flow data sequence, the standard deviation of the flow data sequence is obtained, and the standard deviation is normalized to obtain the third flow instability level at the current moment.

[0019] The sum of the first flow instability degree, the second flow instability degree, and the third flow instability degree is normalized to obtain the flow stability adjustment factor at the current moment.

[0020] Preferably, the step of obtaining the gate operation status adjustment factor at the current moment based on the difference between the current flow data and the ideal flow data, and the multi-dimensional status data within the current moment and the preset historical time period, includes:

[0021] Multidimensional state data includes gate opening and gate vibration amplitude;

[0022] The gate opening stability index is obtained based on the gate opening at the current moment. The degree of difference between the current flow data and the ideal flow data is obtained based on the difference between the current flow data and the ideal flow data. The reciprocal of the sum of the gate opening stability index and the preset constant is calculated. The square root of the product of the degree of difference between the flow data and the reciprocal is normalized to obtain the first gate instability degree.

[0023] Based on the gate vibration amplitude at each moment within a preset historical period, the gate instability index is obtained, and the gate opening and closing speed of the culvert gate at the last opening and closing before the current moment is obtained. The arithmetic square root of the product of the gate opening and closing speed and the gate instability index is normalized to obtain the second gate instability degree.

[0024] The number of gate actions of the culvert gate within a preset historical period is obtained, and the number of gate actions is normalized to obtain the instability degree of the third gate.

[0025] The sum of the instability levels of the first gate, the second gate, and the third gate is normalized to obtain the gate operation state adjustment factor at the current moment.

[0026] Preferably, obtaining the gate opening stability index based on the gate opening at the current moment includes:

[0027] Obtain the maximum and minimum gate opening of the culvert gate, calculate the perfect square difference between the maximum and minimum gate openings, and obtain the negative of the ratio of constant 4 to the perfect square difference, which is denoted as the stability coefficient.

[0028] The difference between the current gate opening and the minimum gate opening is obtained and recorded as the first difference; the difference between the current gate opening and the maximum gate opening is obtained and recorded as the second difference.

[0029] The stability coefficient, the product of the first difference and the second difference are obtained to obtain the gate opening stability index at the current moment.

[0030] Preferably, the step of obtaining the degree of difference in traffic data at the current moment based on the difference between the current traffic data and the ideal traffic data includes:

[0031] If the current traffic data is greater than or equal to the ideal traffic data, then obtain the ratio of the current traffic data to the ideal traffic data, calculate the difference between the ratio and the constant 1, and obtain the degree of difference in the current traffic data.

[0032] If the current traffic data is less than the ideal traffic data, then the difference in traffic data at the current moment is set to 0.

[0033] Preferably, the step of obtaining the gate instability index based on the gate vibration amplitude at each moment within a preset historical period includes:

[0034] The gate vibration amplitudes within a preset historical time period are used to form a gate vibration amplitude data sequence, and the peak and valley data of the gate vibration amplitude data sequence are obtained respectively.

[0035] If the number of peak or valley data in the gate vibration amplitude data sequence is 0, then the gate instability index is set to 0.

[0036] If the number of peak data and valley data in the gate vibration amplitude data sequence is not 0, then the mean of the peak data and the mean of the valley data in the gate vibration amplitude data sequence are obtained respectively, and the difference between the mean of the peak data and the mean of the valley data is calculated to obtain the gate instability index.

[0037] Preferably, the step of obtaining the proportional coefficient adjustment factor at the current moment by combining the flow stability adjustment factor and the gate operation state adjustment factor includes:

[0038] The reciprocal of the sum of the flow stability adjustment factor, the gate operation state adjustment factor, and the preset constant is normalized to obtain the proportional coefficient adjustment factor at the current moment.

[0039] Preferably, adjusting the initial value of the preset proportional coefficient in the PID control method based on the preliminary proportional adjustment coefficient and the proportional coefficient adjustment factor to obtain the adaptive proportional coefficient at the current moment includes:

[0040] Obtain the product of the preset proportional coefficient adjustment range value, the initial proportional coefficient, and the proportional coefficient adjustment factor to obtain the proportional coefficient adjustment value. Then, obtain the sum of the preset initial proportional coefficient value and the proportional coefficient adjustment value to obtain the adaptive proportional coefficient at the current moment.

[0041] The beneficial effects of the embodiments of the present invention compared with the prior art are as follows:

[0042] In this invention, the preliminary proportional adjustment coefficient at the current moment is obtained to quickly capture the main dynamic characteristics of the water conservancy control system and provide a basic benchmark for subsequent adjustments. The flow stability adjustment factor and the gate operation status adjustment factor at the current moment are obtained and used to fuse them to obtain the proportional coefficient adjustment factor at the current moment. The preliminary proportional adjustment coefficient is dynamically corrected to better fit the actual working conditions and improve the accuracy and robustness of the adjustment. Based on the preliminary proportional adjustment coefficient and the proportional coefficient adjustment factor, the adaptive proportional coefficient is generated by integrating information from three aspects: system dynamics, flow stability, and gate status. This is applied to the PID control algorithm, which avoids over-adjustment and ensures timely adjustment, realizing intelligent control of the culvert gate, improving control accuracy and stability, and ensuring the efficient operation of the water conservancy control system. Attached Figure Description

[0043] 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.

[0044] Figure 1 This is a flowchart of a data analysis-based intelligent control method for culvert gates provided in Embodiment 1 of the present invention. Detailed Implementation

[0045] 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.

[0046] 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.

[0047] To illustrate the technical solution of the present invention, specific embodiments are described below.

[0048] See Figure 1 This is a flowchart of a data analysis-based intelligent control method for culvert gates provided in Embodiment 1 of the present invention. Figure 1 As shown, the method may include:

[0049] Step S101: Obtain the flow rate and water level data of the pipeline where the culvert gate is located at each time point up to the current time, as well as the flow velocity data at each monitoring location in the pipeline, and at the same time obtain the multi-dimensional status data of the culvert gate at each time point.

[0050] In the field of water conservancy engineering, culvert gates, as important water flow control facilities, are widely used in irrigation, flood control, and water supply. With the development of water conservancy informatization and intelligentization, the demand for precise, efficient, and intelligent control of culvert gates is becoming increasingly urgent. Developing an intelligent control method for culvert gates based on data analysis can not only improve water resource utilization efficiency and the operation and management level of water conservancy projects, but also has important practical significance and broad application prospects.

[0051] Traditional PID control is simple in structure and easy to implement. A basic control framework can be quickly built using mature control theory, providing basic regulation capabilities for general operating conditions and maintaining relatively stable system operation. However, the core parameters of traditional PID control are usually fixed. For example, the proportional coefficient Kp directly affects the system response speed. Different operating conditions require different response speeds for gates. When a culvert gate faces different flow rates, water levels, and flow regimes, a fixed proportional coefficient Kp is difficult to flexibly adapt to complex and changing conditions, easily leading to response lag or overshoot, affecting control accuracy and stability.

[0052] Therefore, in this embodiment, relevant data of the culvert gate are acquired in real time to obtain the preliminary proportional adjustment coefficient and the proportional coefficient adjustment factor. Then, the initial value of the preset proportional coefficient in the PID control method is adjusted using the preliminary proportional adjustment coefficient and the proportional coefficient adjustment factor to obtain the adaptive proportional coefficient. This adaptive proportional coefficient is then used to intelligently control the culvert gate at the current moment using the PID control method, thereby improving the control accuracy and stability of the PID control method for the culvert gate.

[0053] First, obtain relevant data for the culvert gate: Install flow sensors in straight pipe sections upstream or downstream of the culvert gate (at least 3-5 times the pipe diameter away from the culvert gate), and install water level sensors upstream of the culvert gate in areas with smooth water flow (at least 3-5 times the pipe diameter away from the culvert gate). Collect flow and water level data in real time from the pipe containing the culvert gate. Distribute multiple monitoring locations evenly along the pipe center, near the pipe wall, and along the pipe length (the specific number depends on the actual pipe specifications). Install a flow meter at each monitoring location to acquire the flow velocity data at each location in real time, obtaining the cutoff value. The system collects flow rate and water level data for the pipeline containing the culvert gate at each current moment, as well as flow velocity data at each monitoring location within the pipeline. Simultaneously, it uses an opening sensor to acquire the gate opening (the gate opening is obtained after normalization of the data collected by the opening sensor) and a vibration acceleration sensor to acquire the gate vibration amplitude. The gate opening and vibration amplitude at each moment are combined to form multidimensional state data for that moment, resulting in multidimensional state data of the culvert gate at each moment. The acquisition frequency for flow rate, water level, and multidimensional state data is 10 times per second, which is not limited here and can be set according to the specific implementation scenario.

[0054] In addition, it is necessary to obtain the number of gate actions of the culvert gate through the water conservancy control system (i.e., the water conservancy control system that performs intelligent control of the culvert gate), use the water conservancy control system to record or use displacement sensors to collect displacement data to calculate the opening and closing speed of the culvert gate each time it is opened or closed, use calipers / measuring tapes / laser rangefinders to measure the diameter of the culvert in the pipeline where the culvert gate is located, use vibrating pipe densitometers / float densitometers to measure the fluid density in the pipeline where the culvert gate is located, use rotational viscometers / capillary viscometers to measure the fluid viscosity in the pipeline, and use piezoresistive pressure sensors (installed in the inlet pipe or pool and the outlet pipe or pool of the culvert gate) to obtain the upstream and downstream pressure data of the culvert gate.

[0055] Step S102: Obtain the ideal flow rate data of the pipeline. Based on the difference between the current flow rate data and the ideal flow rate data, as well as the water level data change characteristics between the current time and the previous time, obtain the preliminary proportional adjustment coefficient for the current time.

[0056] In a water control system, flow deviation directly reflects the difference between the actual flow and the target flow, and is the core error signal that the water control system needs to correct. The rate of change of water level data reflects the current motion trend and inertial characteristics of the water control system. Together, they constitute the key characterization of the current state of the water control system.

[0057] Therefore, in this embodiment, the ideal flow rate data of the pipeline is obtained. Then, based on the difference between the current flow rate data and the ideal flow rate data, as well as the water level data change characteristics between the current time and the previous time, the preliminary proportional adjustment coefficient for the current time is obtained. This quickly captures the main dynamic characteristics of the water conservancy control system and provides a basic benchmark for subsequent adjustments. The ideal flow rate data of the pipeline is obtained through hydraulic calculations (such as the Manning formula and the Darcy-Weisbach formula) based on design indicators such as the irrigation area, water supply demand, and flood control standards of the water conservancy project, combined with the hydraulic characteristics of the pipeline (such as slope and roughness), and the upstream and downstream pressure data of the culvert gate. The method for obtaining the ideal flow rate data is existing technology and will not be elaborated here.

[0058] The method for obtaining the preliminary proportional adjustment coefficient for the current moment, based on the difference between the current flow data and the ideal flow data, and the water level change characteristics between the current moment and the previous moment, is as follows:

[0059] Obtain the absolute value of the difference between the water level data at the current time and the previous time to get the water level data difference value; obtain the time interval between the current time and the previous time; calculate the ratio of the water level data difference value to the time interval to get the water level data change rate.

[0060] Obtain the absolute value of the difference between the current flow data and the ideal flow data to get the flow data difference value. Normalize the product of the flow data difference value and the water level change rate to get the preliminary proportional adjustment coefficient for the current moment.

[0061] In one embodiment, the formula for calculating the initial proportional adjustment coefficient at the current moment is:

[0062]

[0063] in, This is the initial proportional adjustment factor for the current moment; H represents the current traffic data; H represents the ideal traffic data. This refers to the water level data at the current moment. The current time represents the water level data from the previous time; t represents the time interval between the current time and the previous time. It is the absolute value symbol; This is the normalization function.

[0064] It should be noted that, For traffic data difference values, A larger value indicates that the current flow rate deviates more from the ideal flow rate, requiring stronger adjustments for rapid correction. This means increasing the initial proportional adjustment coefficient to amplify the error signal, making the control action more significant, accelerating the reduction of flow deviation, and overcoming the inertial delay of the water control system. This ensures the water control system responds quickly and stabilizes the flow rate data at the ideal state. The larger it is; The rate of change of water level data at the current moment. The larger the value, the stronger the inertia or external disturbance of the water control system, and the more obvious the lag in flow adjustment. This means that the initial proportional adjustment coefficient needs to be increased to strengthen the control action in advance. The larger it is.

[0065] Thus, we obtain the preliminary proportional adjustment coefficient for the current moment.

[0066] Step S103: Obtain the Reynolds number corresponding to the current moment; based on the flow velocity data of each monitoring location at the current moment, the fluctuation characteristics of water level data and flow rate data in the preset historical period before the current moment, and the Reynolds number, obtain the flow stability adjustment factor at the current moment; based on the difference between the flow rate data at the current moment and the ideal flow rate data, the multi-dimensional state data at the current moment and in the preset historical period, obtain the gate operation state adjustment factor at the current moment; combine the flow stability adjustment factor and the gate operation state adjustment factor to obtain the proportional coefficient adjustment factor at the current moment.

[0067] While the preliminary proportional adjustment coefficient can quickly capture the main dynamic characteristics of a hydraulic control system based on the rate of change of flow deviation and water level data, it does not consider the impact of flow stability and gate operating status on the control effect. Flow stability directly affects the ease of flow regulation, while gate operating status determines the reliability and efficiency of the regulation action. Relying solely on the preliminary proportional adjustment coefficient may lead to over- or under-regulation due to insufficient consideration of flow fluctuations or gate anomalies.

[0068] Since the uniformity of velocity distribution is a key indicator of flow stability, the better the uniformity of velocity distribution, the more stable the flow. Secondly, eddy intensity and Reynolds number reflect the degree of turbulence in the water flow. The stronger the turbulence, the more unstable the flow. That is, the smaller the eddy intensity and Reynolds number, the more stable the flow. At the same time, the frequency of water level fluctuations and the historical flow fluctuation rate reflect the speed of change in flow data. The more frequent the fluctuations, the more unstable the flow. That is, the smaller the frequency of water level fluctuations and the historical flow fluctuation rate, the more stable the flow.

[0069] Therefore, in this embodiment, the Reynolds number corresponding to the current moment is obtained (calculated using the diameter of the culvert in the pipe containing the culvert gate, the fluid density in the pipe, and the fluid viscosity in the pipe). The calculation method of the Reynolds number is existing technology and will not be elaborated here. Based on the flow velocity data of each monitoring location at the current moment, the fluctuation characteristics of water level data and flow rate data in the preset historical period before the current moment, and the Reynolds number, the flow stability adjustment factor at the current moment is obtained to reflect the flow stability in the pipe at the current moment. In this embodiment, the preset historical period is set to 1 minute before the current moment to better capture recent data fluctuation characteristics. This is not limited and can be set according to the specific implementation scenario.

[0070] The method for obtaining the flow stability adjustment factor at the current moment, based on the flow velocity data at each monitoring location at the current moment, the fluctuation characteristics of water level and flow rate data in the preset historical period before the current moment, and the Reynolds number, is as follows:

[0071] The eddy current intensity at each monitoring location in the pipeline at the current moment is obtained, and the corresponding mean eddy current intensity is calculated. The method for obtaining the eddy current intensity is existing technology and will not be elaborated here. Water level data from a preset historical period are used to form a water level data sequence. The number of peak data points in the water level data sequence is added to a constant 1 to obtain the degree of water level fluctuation. The square root of the product of the mean eddy current intensity and the degree of water level fluctuation is normalized using a sliding window using the norm() function to obtain the first flow instability degree at the current moment, denoted as b1. ,in, Let J be the eddy current intensity at the j-th monitoring location in the pipeline at the current moment, and let sum(J) be the number of monitoring locations in the pipeline. This refers to the number of peak data points in the water level data series. For normalization function, This represents the average eddy current intensity. The larger the value of b1, the worse the flow stability in the pipe at the current moment; therefore, a larger b1 indicates a higher flow stability. The larger the value, the greater the frequency of water level fluctuations, and the worse the flow stability in the pipeline at the current moment; therefore, b1 is larger.

[0072] Obtain the average flow velocity data at all monitoring locations in the pipeline at the current moment. Calculate the absolute value of the difference between the flow velocity data at each monitoring location and the average flow velocity data at the current moment. Calculate the average value of these absolute differences, denoted as the average flow velocity difference value. Use the `norm()` function to perform sliding window normalization on the square root of the product of the reciprocal of the average flow velocity difference value and the Reynolds number to obtain the second flow instability level at the current moment, denoted as b2. ,in, This represents the flow velocity data at the j-th monitoring location in the pipeline at the current moment. Let J be the average flow velocity data at all monitoring locations in the pipeline at the current moment, and let sum(J) be the number of monitoring locations in the pipeline. It is the absolute value symbol. Let Reynolds number be the Reynolds number at the current time. For normalization function, This represents the average velocity difference, reflecting the uniformity of the velocity distribution in the pipe at the current moment. The larger the value of b2, the stronger the uniformity of the flow velocity distribution in the pipe at the current moment, and the stronger the flow stability in the pipe; conversely, the smaller the value of b2. The larger the value, the worse the flow stability in the pipe at the current moment; the larger the value, the greater the value of b2.

[0073] The flow data within a preset historical time period is used to form a flow data sequence. The standard deviation of the flow data sequence is obtained. The standard deviation is normalized by a sliding window using the norm() function to obtain the third flow instability at the current moment, denoted as b3. The larger the standard deviation of the flow data sequence, the more dispersed the distribution of flow data in the flow data sequence, that is, the worse the flow stability in the pipeline at the current moment, and the larger b3 is.

[0074] The sum of the first flow instability degree, the second flow instability degree, and the third flow instability degree is normalized to obtain the flow stability adjustment factor at the current moment.

[0075] In one embodiment, the formula for calculating the flow stability adjustment factor at the current moment is:

[0076]

[0077] in, b1 represents the flow stability adjustment factor at the current moment; b2 represents the first flow instability level at the current moment; b3 represents the second flow instability level at the current moment; b4 represents the third flow instability level at the current moment. This is the normalization function.

[0078] It should be noted that the larger b1, b2, or b3 is, the worse the flow stability in the pipeline at the previous time, and the greater the need for the hydraulic control system to control the culvert gate. The larger it is.

[0079] Since the gate opening is a crucial factor affecting the sensitivity of gate regulation, the regulation is most sensitive when the gate opening is moderate. Secondly, the number of gate actions, the gate vibration amplitude, and the gate opening and closing speed reflect the stability of gate operation. The more gate actions, the greater the gate vibration amplitude, and the faster the gate opening and closing speed, the less stable the gate operation. At the same time, the difference between the current flow data and the ideal flow data can reflect the gate sealing status. The better the gate sealing status, the more stable the gate operation.

[0080] Therefore, in this embodiment, based on the difference between the current flow data and the ideal flow data, and the multi-dimensional state data within the current time and the preset historical period, the gate operation status adjustment factor at the current time is obtained, reflecting the operation status of the culvert gate at the current time. Then, the proportional coefficient adjustment factor at the current time is obtained by combining the flow stability adjustment factor and the gate operation status adjustment factor, and the initial proportional adjustment coefficient is dynamically corrected to make it more in line with the actual working conditions, thereby improving the accuracy and robustness of the adjustment.

[0081] The method for obtaining the gate operation status adjustment factor at the current moment, based on the difference between the current flow data and the ideal flow data, and the multi-dimensional status data of the current moment and the preset historical time period, is as follows:

[0082] Obtain the maximum and minimum gate openings of the culvert gate. Calculate the perfect square difference between the maximum and minimum gate openings. Obtain the negative of the ratio of a constant 4 to the perfect square difference, denoted as the stability coefficient. Obtain the difference between the current gate opening and the minimum gate opening, denoted as the first difference. Obtain the difference between the current gate opening and the maximum gate opening, denoted as the second difference. Calculate the product of the stability coefficient, the first difference, and the second difference to obtain the gate opening stability index at the current moment, denoted as... ,Right now Where Kmax is the maximum gate opening and Kmin is the minimum gate opening. Let the gate opening be at the current moment, when When approaching the maximum or minimum gate opening The closer the value is to 0, the more unstable the gate's operation becomes; conversely, when the gate opening is moderate, The closer the value is to 1, the more stable the gate's operation.

[0083] If the current traffic data is greater than or equal to the ideal traffic data, then the ratio of the current traffic data to the ideal traffic data is obtained, and the difference between the ratio and a constant 1 is calculated to obtain the degree of difference in the current traffic data, denoted as . ,Right now ,in, H represents the current traffic data, and H represents the ideal traffic data. The closer the value is to H, the better the gate's sealing performance at the current moment. If the current flow rate is less than the ideal flow rate, it indicates that the current flow rate is within the normal range. Therefore, the difference in the current flow rate is set to 0. ;

[0084] The reciprocal of the sum of the gate opening stability index and a preset constant is calculated. Then, the square root of the product of the flow rate data difference and the reciprocal is normalized using a sliding window using the norm() function to obtain the first gate instability level, denoted as d1. ,in, This is the stability index of the gate opening at the current moment. The degree of difference in traffic data at the current moment, where c is a preset constant, is set in this embodiment. This is used to ensure that the fraction is meaningful; there are no restrictions here, and it can be set according to the specific implementation scenario. For normalization function, The larger the value, the more stable the gate's operation; the smaller the value, the smaller the d1. The larger the value, the worse the gate's sealing performance at the current moment, and the more likely leakage may occur. In other words, the more unstable the gate's operating state, the larger d1 will be.

[0085] The gate vibration amplitudes within a preset historical time period are compiled into a gate vibration amplitude data sequence. The peak and trough values ​​of this data sequence are then obtained. If the number of peak and trough values ​​in the data sequence is not zero, the mean of the peak and trough values ​​is obtained. The difference between the mean of the peak and trough values ​​is calculated to obtain the gate instability index, denoted as s. Where F is the mean of the peak data in the gate vibration amplitude data sequence, and G is the mean of the valley data in the gate vibration amplitude data sequence. The greater the difference between F and G, the more unstable the gate vibration amplitude is, and the larger s is. If the number of peak data or valley data in the gate vibration amplitude data sequence is 0, it means that the gate vibration amplitude is more stable, and the gate instability index is set to 0.

[0086] Since the gate vibration amplitude and gate opening and closing speed reflect the mechanical state of the gate at the current moment, the adjustment should be reduced when the gate vibration amplitude is large and the gate opening and closing speed is fast. Therefore, the gate opening and closing speed at the last opening and closing of the culvert gate before the current moment is obtained. The arithmetic square root of the product of the gate opening and closing speed and the gate instability index is normalized to obtain the second gate instability degree, denoted as d2. Where s is the gate instability index, and V is the gate opening and closing speed of the culvert gate at the last opening and closing before the current moment. The larger s is, the more unstable the gate operation state is, and the larger d2 is. The larger V is, the more unstable the gate operation state is, and the larger d2 is.

[0087] The number of gate actions of the culvert gate within a preset historical period is obtained. The number of gate actions is normalized by a sliding window using the norm() function to obtain the instability degree of the third gate, denoted as d3.

[0088] The sum of the instability levels of the first gate, the second gate, and the third gate is normalized to obtain the gate operation state adjustment factor at the current moment.

[0089] In one embodiment, the formula for calculating the gate operating state adjustment factor at the current moment is:

[0090]

[0091] in, Here, d1 represents the instability level of the first gate, d2 represents the instability level of the second gate, and d3 represents the instability level of the third gate. This is the normalization function.

[0092] It should be noted that the larger d1, d2, or d3 is, the more unstable the operating state of the culvert gate is at the current moment, and the more necessary it is for the water conservancy control system to control the culvert gate. The larger it is.

[0093] Furthermore, the method for obtaining the proportional coefficient adjustment factor at the current moment by combining the flow stability adjustment factor and the gate operation state adjustment factor is as follows:

[0094] The reciprocal of the sum of the flow stability adjustment factor, the gate operation state adjustment factor, and the preset constant is normalized to obtain the proportional coefficient adjustment factor at the current moment.

[0095] In one embodiment, the formula for calculating the scaling factor adjustment factor at the current moment is:

[0096]

[0097] in, The scaling factor is the adjustment factor for the current time period. This is the flow stability adjustment factor at the current moment; c is the adjustment factor for the gate's operating status at the current moment; c is a preset constant, set in this embodiment. This is used to ensure that the fraction is meaningful. There are no restrictions here, and it can be set according to the specific implementation scenario. This is the normalization function.

[0098] It should be noted that, The larger, The larger the value, the more unstable the flow pattern and operating state of the culvert gate at the current moment, thus requiring a smaller proportionality coefficient to prevent oscillations or divergence. The smaller it is.

[0099] Thus, the scaling factor adjustment factor for the current moment is obtained.

[0100] Step S104: Adjust the initial value of the preset proportional coefficient in the PID control method according to the preliminary proportional adjustment coefficient and the proportional coefficient adjustment factor to obtain the adaptive proportional coefficient at the current moment. Based on the adaptive proportional coefficient, use the PID control method to perform intelligent control on the culvert gate at the current moment.

[0101] Relying solely on the preliminary proportional adjustment coefficient or the proportional coefficient adjustment factor cannot fully reflect the needs of the water conservancy control system: the preliminary proportional adjustment coefficient may deviate from the optimal value because it does not take into account the flow regime and gate status, while the adjustment factor may lead to unstable regulation due to characteristic fluctuations if it lacks the support of the basic proportional coefficient.

[0102] Therefore, in this embodiment, the initial value of the preset proportional coefficient in the PID control method is adjusted according to the preliminary proportional adjustment coefficient and the proportional coefficient adjustment factor to obtain the adaptive proportional coefficient at the current moment. Based on the adaptive proportional coefficient, the PID control method is used to intelligently control the culvert gate at the current moment. This is applied to the PID control algorithm to realize intelligent control of the culvert gate, improve control accuracy and stability, and ensure the efficient operation of the water conservancy control system.

[0103] The method for adjusting the initial value of the preset proportional coefficient in the PID control method based on the preliminary proportional adjustment coefficient and the proportional coefficient adjustment factor to obtain the adaptive proportional coefficient at the current moment is as follows:

[0104] Obtain the product of the preset proportional coefficient adjustment range value, the initial proportional coefficient, and the proportional coefficient adjustment factor to obtain the proportional coefficient adjustment value. Then, obtain the sum of the preset initial proportional coefficient value and the proportional coefficient adjustment value to obtain the adaptive proportional coefficient at the current moment.

[0105] In one embodiment, the formula for calculating the adaptive scaling factor at the current moment is:

[0106]

[0107] in, This represents the adaptive scaling factor at the current moment; The initial value of the preset proportional coefficient is set according to the characteristics of the water control system, such as in inertial-driven systems (e.g., large-scale water conservancy projects). It is advisable to choose a smaller value (such as 0.5-1.0) to avoid overshoot or oscillation caused by an excessively strong proportional effect, especially in fast-response systems (such as urban flood control gates). The value can be appropriately increased (e.g., 1.0-2.0) to accelerate error correction. In this embodiment... Set it to 0.5; there is no limit here, and it can be set according to the specific implementation scenario. The preset proportional coefficient adjustment range value is set according to the working requirements of the culvert gate. For example, if it is used in a reservoir with a large water flow, then... Set to 3-4. If used in ditches where the water flow is small, then... Set to 2-3, in this embodiment... The value is 3 (equivalent to a scaling factor ranging from 0.5 to 3.5), and there is no limit here; it can be set according to the specific implementation scenario. This is the initial proportional adjustment factor for the current moment; This is the scaling factor for the current time.

[0108] It should be noted that in this embodiment... Set it to 0.5, which is the minimum value in the scaling factor range. The larger it is, the more it needs to be increased. , The smaller, the more... The smaller the increase is required.

[0109] After obtaining the adaptive proportional coefficient at the current moment, it is substituted into the PID control algorithm to obtain an improved PID control algorithm. This improved PID control algorithm is then used to achieve intelligent control of the culvert gate. The use of this improved PID control algorithm for intelligent control of the culvert gate is existing technology, and will be briefly described here: First, water level data from upstream and downstream is collected in real time using a water level sensor, and the current position is fed back by the gate opening encoder to calculate the deviation value and rate of change between the actual water level and the target water level. Then, the deviation value is input into the PID controller (using the improved PID control algorithm). The PID controller integrates the three components (proportional, integral, and derivative) to output a control signal, driving the electric actuator to adjust the gate opening. During execution, the hydraulic control system continuously collects water level data and gate opening data, forming a closed-loop feedback, dynamically correcting the control quantity, and ultimately achieving adaptive intelligent control of the culvert gate for complex water conditions.

[0110] In summary, in this embodiment of the invention, the preliminary proportional adjustment coefficient at the current moment is obtained to quickly capture the main dynamic characteristics of the water conservancy control system, providing a basic benchmark for subsequent adjustments. The flow stability adjustment factor and the gate operation status adjustment factor at the current moment are obtained and used to fuse them to obtain the proportional coefficient adjustment factor at the current moment, dynamically correcting the preliminary proportional adjustment coefficient to make it more in line with the actual working conditions and improve the accuracy and robustness of the adjustment. Based on the preliminary proportional adjustment coefficient and the proportional coefficient adjustment factor, an adaptive proportional coefficient is generated by integrating information from three aspects: system dynamics, flow stability, and gate status. This coefficient is then applied to the PID control algorithm, avoiding over-adjustment while ensuring timely adjustment, realizing intelligent control of the culvert gate, improving control accuracy and stability, and ensuring the efficient operation of the water conservancy control system.

[0111] 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 data analysis-based intelligent control method for culvert gates, characterized in that, The intelligent control method for culvert gates based on data analysis includes: The system acquires the flow rate and water level data of the pipeline where the culvert gate is located at every moment up to the current moment, as well as the flow velocity data at each monitoring location in the pipeline, and also acquires the multi-dimensional status data of the culvert gate at each moment. Obtain the ideal flow rate data of the pipeline, and based on the difference between the current flow rate data and the ideal flow rate data, as well as the water level data change characteristics between the current time and the previous time, obtain the preliminary proportional adjustment coefficient for the current time. Obtain the Reynolds number corresponding to the current moment. Based on the flow velocity data of each monitoring location at the current moment, the fluctuation characteristics of water level data and flow rate data in the preset historical period before the current moment, and the Reynolds number, obtain the flow stability adjustment factor at the current moment. Based on the difference between the flow rate data at the current moment and the ideal flow rate data, the multi-dimensional state data at the current moment and in the preset historical period, obtain the gate operation state adjustment factor at the current moment. Combine the flow stability adjustment factor and the gate operation state adjustment factor to obtain the proportional coefficient adjustment factor at the current moment. Based on the preliminary proportional adjustment coefficient and the proportional adjustment factor, the initial value of the preset proportional coefficient in the PID control method is adjusted to obtain the adaptive proportional coefficient at the current moment. Based on the adaptive proportional coefficient, the PID control method is used to intelligently control the culvert gate at the current moment. The step of obtaining the flow stability adjustment factor at the current moment based on the flow velocity data at each monitoring location at the current moment, the fluctuation characteristics of water level data and flow rate data in a preset historical period before the current moment, and the Reynolds number includes: The eddy current intensity at each monitoring location in the pipeline at the current moment is obtained, and the mean eddy current intensity is obtained. The water level data in the preset historical period is used to form a water level data sequence. The number of peak data in the water level data sequence is added to the constant 1 to obtain the water level data fluctuation degree. The arithmetic square root of the product of the mean eddy current intensity and the water level data fluctuation degree is normalized to obtain the first flow instability degree at the current moment. The mean flow velocity data of all monitoring locations in the pipeline at the current moment is obtained. The absolute value of the difference between the flow velocity data of each monitoring location in the pipeline at the current moment and the mean flow velocity data is calculated. The average value of the absolute value of the difference is obtained and recorded as the average flow velocity difference value. The arithmetic square root of the product of the reciprocal of the average flow velocity difference value and the Reynolds number is normalized to obtain the second flow instability degree at the current moment. The flow data within a preset historical time period is organized into a flow data sequence, the standard deviation of the flow data sequence is obtained, and the standard deviation is normalized to obtain the third flow instability level at the current moment. The sum of the first flow instability degree, the second flow instability degree, and the third flow instability degree is normalized to obtain the flow stability adjustment factor at the current moment.

2. The intelligent control method for culvert gates based on data analysis according to claim 1, characterized in that, The step of obtaining the preliminary proportional adjustment coefficient for the current moment based on the difference between the current flow data and the ideal flow data, and the water level data change characteristics between the current moment and the previous moment, includes: Obtain the absolute value of the difference between the water level data at the current time and the previous time to get the water level data difference value; obtain the time interval between the current time and the previous time; calculate the ratio of the water level data difference value to the time interval to get the water level data change rate. Obtain the absolute value of the difference between the current flow data and the ideal flow data to get the flow data difference value. Normalize the product of the flow data difference value and the water level change rate to get the preliminary proportional adjustment coefficient for the current moment.

3. The intelligent control method for culvert gates based on data analysis according to claim 1, characterized in that, The step of obtaining the gate operation status adjustment factor at the current moment based on the difference between the current flow data and the ideal flow data, and the multi-dimensional status data of the current moment and the preset historical period includes: Multidimensional state data includes gate opening and gate vibration amplitude; The gate opening stability index is obtained based on the gate opening at the current moment. The degree of difference between the current flow data and the ideal flow data is obtained based on the difference between the current flow data and the ideal flow data. The reciprocal of the sum of the gate opening stability index and the preset constant is calculated. The square root of the product of the degree of difference between the flow data and the reciprocal is normalized to obtain the first gate instability degree. Based on the gate vibration amplitude at each moment within a preset historical period, the gate instability index is obtained, and the gate opening and closing speed of the culvert gate at the last opening and closing before the current moment is obtained. The arithmetic square root of the product of the gate opening and closing speed and the gate instability index is normalized to obtain the second gate instability degree. The number of gate actions of the culvert gate within a preset historical period is obtained, and the number of gate actions is normalized to obtain the instability degree of the third gate. The sum of the instability levels of the first gate, the second gate, and the third gate is normalized to obtain the gate operation state adjustment factor at the current moment.

4. The intelligent control method for culvert gates based on data analysis according to claim 3, characterized in that, The step of obtaining the gate opening stability index based on the gate opening at the current moment includes: Obtain the maximum and minimum gate opening of the culvert gate, calculate the perfect square difference between the maximum and minimum gate openings, and obtain the negative of the ratio of constant 4 to the perfect square difference, which is denoted as the stability coefficient. The difference between the current gate opening and the minimum gate opening is obtained and recorded as the first difference; the difference between the current gate opening and the maximum gate opening is obtained and recorded as the second difference. The stability coefficient, the product of the first difference and the second difference are obtained to obtain the gate opening stability index at the current moment.

5. The intelligent control method for culvert gates based on data analysis according to claim 3, characterized in that, The step of obtaining the degree of difference in traffic data at the current moment based on the difference between the current traffic data and the ideal traffic data includes: If the current traffic data is greater than or equal to the ideal traffic data, then obtain the ratio of the current traffic data to the ideal traffic data, calculate the difference between the ratio and the constant 1, and obtain the degree of difference in the current traffic data. If the current traffic data is less than the ideal traffic data, then the difference in traffic data at the current moment is set to 0.

6. The intelligent control method for culvert gates based on data analysis according to claim 3, characterized in that, The step of obtaining gate instability indicators based on the gate vibration amplitude at each moment within a preset historical time period includes: The gate vibration amplitudes within a preset historical time period are used to form a gate vibration amplitude data sequence, and the peak and valley data of the gate vibration amplitude data sequence are obtained respectively. If the number of peak or valley data in the gate vibration amplitude data sequence is 0, then the gate instability index is set to 0. If the number of peak data and valley data in the gate vibration amplitude data sequence is not 0, then the mean of the peak data and the mean of the valley data in the gate vibration amplitude data sequence are obtained respectively, and the difference between the mean of the peak data and the mean of the valley data is calculated to obtain the gate instability index.

7. The intelligent control method for culvert gates based on data analysis according to claim 1, characterized in that, The step of obtaining the proportional coefficient adjustment factor at the current moment by combining the flow stability adjustment factor and the gate operation state adjustment factor includes: The reciprocal of the sum of the flow stability adjustment factor, the gate operation state adjustment factor, and the preset constant is normalized to obtain the proportional coefficient adjustment factor at the current moment.

8. The intelligent control method for culvert gates based on data analysis according to claim 1, characterized in that, The step of adjusting the initial value of the preset proportional coefficient in the PID control method according to the preliminary proportional adjustment coefficient and the proportional coefficient adjustment factor to obtain the adaptive proportional coefficient at the current moment includes: Obtain the product of the preset proportional coefficient adjustment range value, the initial proportional coefficient, and the proportional coefficient adjustment factor to obtain the proportional coefficient adjustment value. Then, obtain the sum of the preset initial proportional coefficient value and the proportional coefficient adjustment value to obtain the adaptive proportional coefficient at the current moment.

Images