Remote control method and system of water and fertilizer integrated intelligent pump house

Abstract

The present application relates to the technical field of remote control, in particular to a remote control method and system for water and fertilizer integrated intelligent pump house, first, the rotational speed and torque current after the opening instruction is issued are collected, and the real-time feature vector is constructed based on the torque balance principle and time sequence change association, so that in the non-steady state process of frequency conversion speed regulation, the real-time pipe network resistance coefficient and real-time turbulent pulsation intensity which are stripped of fluid inertia interference can be accurately decoupled, and the precise quantification of pipe network physical characteristics is realized; further, by calculating the resistance characteristic deviation degree and resistance turbulent coupling deviation degree, the physical coupling characteristics between pipe network resistance and turbulent pulsation are used for double verification, the normal load, pipe network structure abnormality and fluid working condition abnormality such as cavitation and drift which cannot be distinguished by steady-state current are effectively identified, so that the accuracy of pump house remote control under complex communication and hydraulic environment is higher.

Description

Technical Field

[0001] This invention relates to the field of remote control technology, specifically to a remote control method and system for an integrated water and fertilizer intelligent pumping station. Background Technology

[0002] Modern integrated water and fertilizer irrigation systems typically rely on remote wireless networks to control electrically operated valves distributed across the field. Inverters in the pump house adjust the pump speed based on the main pipeline pressure to maintain a constant water supply pressure. Due to unstable communication signal coverage in farmland environments, situations often arise where the control unit fails to receive valve execution feedback messages after a remote opening command is issued. In such cases, the control system struggles to confirm whether the valve has actually opened; blindly resending the command may cause the equipment to repeat its actions, while directly reporting an error and shutting down will interrupt the irrigation process.

[0003] Existing technologies typically determine the valve opening state based on whether the output current of the motor after it enters steady state exceeds a preset load current threshold. However, this method does not take into account the non-steady-state interference of fluid inertial torque on the current signal during variable frequency speed regulation, nor does it consider that the steady-state current value itself cannot distinguish between normal load work and false loads such as cavitation and sensor drift. This makes it difficult for the control system to identify abnormalities in pipeline structure and fluid conditions in communication blind spots, which can easily lead to incorrect control decisions. Therefore, the existing technology has poor performance in remote pump station control based on the output current of the motor after it enters steady state in complex communication and hydraulic environments. Summary of the Invention

[0004] To address the poor performance of existing technologies for remote control of pump stations based on the output current of the motor after it has reached a steady state in complex communication and hydraulic environments, this application aims to provide a remote control method and system for an integrated water and fertilizer intelligent pump station. The specific technical solution adopted is as follows: The first aspect of this application provides a remote control method for an integrated water and fertilizer intelligent pumping station, including: The centrifugal pump impeller speed and motor output torque current are collected at each sampling moment within the sampling period after each valve opening command is issued in the pump room. Based on the torque balance principle, a real-time feature vector is constructed according to the correlation between the motor output torque current and the centrifugal pump impeller speed in time sequence. The real-time feature vector includes the real-time pipeline resistance coefficient and the real-time turbulence pulsation intensity after each start command is issued. Based on the historical operating benchmark deviation of the real-time pipeline resistance coefficient, the resistance characteristic deviation after each start command is issued is determined; based on the relative deviation of the coupling relationship between the real-time pipeline resistance coefficient and the real-time turbulence intensity compared to the historical operating benchmark, the resistance-turbulence coupling deviation after each start command is determined. The pump house is remotely controlled based on the resistance characteristic deviation and the resistance turbulence coupling deviation.

[0005] Furthermore, the process of obtaining the real-time feature vector includes: Construct a torque balance equation; based on the centrifugal pump impeller speed and motor output torque current at each sampling moment, perform polynomial fitting through the torque balance equation to determine the real-time pipeline resistance coefficient after each start command is issued and the instantaneous residual at each sampling moment; The real-time turbulence intensity after each start command is issued is determined based on the overall magnitude of the instantaneous residuals at all sampling times. The vector corresponding to the real-time pipeline resistance coefficient and the real-time turbulence intensity arranged in sequence is used as the real-time feature vector.

[0006] Furthermore, the process of obtaining the real-time turbulence fluctuation intensity includes: Calculate the root mean square value of the instantaneous residuals at all sampling times to determine the real-time turbulence intensity after each start command is issued.

[0007] Furthermore, the process of obtaining the resistance characteristic deviation includes: Obtain the historical feature vector corresponding to each start command issued; the historical feature vector contains the historical pipeline resistance coefficient and the historical turbulence fluctuation intensity arranged in sequence. The resistance coefficient deviation value is determined based on the difference between the historical pipeline resistance coefficient and the real-time pipeline resistance coefficient. The resistance characteristic deviation is determined based on the ratio between the resistance coefficient deviation value and the historical pipeline resistance coefficient.

[0008] Furthermore, the process of obtaining the resistance-turbulence coupling deviation includes: Based on the ratio between the real-time turbulence intensity and the real-time pipeline resistance coefficient, the real-time resistance-turbulence coupling value after each start command is issued is determined; based on the ratio between the historical turbulence intensity and the historical pipeline resistance coefficient, the historical resistance-turbulence coupling value after each start command is determined. Based on the difference between the real-time resistance-turbulence coupling value and the historical resistance-turbulence coupling value, the coupling deviation value after each activation command is issued is determined; The drag-turbulence coupling deviation is determined based on the ratio between the coupling deviation value and the historical drag-turbulence coupling value after each activation command is issued.

[0009] Furthermore, the process of remotely controlling the pump house based on the resistance characteristic deviation and the resistance-turbulence coupling deviation includes: After each start command is issued, if the resistance characteristic deviation is greater than the preset characteristic deviation threshold, the macroscopic structure of the pipeline network is determined to be abnormal; if the resistance characteristic deviation is less than or equal to the preset characteristic deviation threshold, the macroscopic structure of the pipeline network is determined to be normal. After each activation command is issued, the fluid condition state after each activation command is determined based on the resistance-turbulence coupling deviation. The pump room is remotely controlled based on the macroscopic structural state of the pipeline network and the fluid operating conditions after each start command is issued.

[0010] Furthermore, the process of determining the fluid condition state after each activation command is issued based on the resistance-turbulence coupling deviation includes: When the resistance-turbulent coupling deviation is greater than the preset coupling deviation threshold, the corresponding fluid condition is determined to be abnormal; when the resistance-turbulent coupling deviation is less than or equal to the preset coupling deviation threshold, the corresponding fluid condition is determined to be normal.

[0011] Furthermore, the process of remotely controlling the pump station based on the macroscopic structural state of the pipeline network and the fluid operating condition after each start command is issued includes: When the fluid condition is normal and the macroscopic structure of the pipeline is normal after each opening command is issued, the valve status is updated to "opening successful". The historical feature vector is updated according to the real-time feature vector to determine the historical feature vector after the next opening command is issued. When the macroscopic structure of the pipeline network is normal and the corresponding fluid condition is abnormal after each start command is issued, the water pump is controlled to stop running and a maintenance alarm is issued. When the corresponding macroscopic structure status of the pipeline network is abnormal after each start command is issued, the power supply to the water pump is cut off and a shutdown alarm is issued.

[0012] Furthermore, the process of updating the historical feature vector based on the real-time feature vector to determine the historical feature vector after the next activation command is issued includes: The historical feature vector after each start command is issued is weighted by a preset first weight to determine the weighted historical vector; The real-time feature vector after each start command is issued is weighted by a preset second weight to determine the weighted real-time vector; The weighted historical vector and the weighted real-time vector are added together to determine the historical feature vector after the next start command is issued; wherein the sum of the first weight and the second weight is 1, and both the first weight and the second weight are greater than 0.

[0013] Secondly, this application provides a remote control system for an integrated water and fertilizer intelligent pumping station, the system comprising: The data acquisition module is used to collect the centrifugal pump impeller speed and motor output torque current at each sampling moment within the sampling period after each valve opening command is issued in the pump room; The vector construction module is used to construct a real-time feature vector based on the torque balance principle and the time-series correlation between the motor output torque current and the centrifugal pump impeller speed. The real-time feature vector includes the real-time pipeline resistance coefficient and the real-time turbulence pulsation intensity after each start command is issued. The parameter determination module is used to determine the resistance characteristic deviation after each start command is issued based on the historical operating benchmark deviation of the real-time pipeline resistance coefficient; and to determine the resistance-turbulence coupling deviation after each start command is issued based on the relative deviation of the coupling relationship between the real-time pipeline resistance coefficient and the real-time turbulence pulsation intensity compared to the historical operating benchmark. The pump house remote control module is used to remotely control the pump house based on the resistance characteristic deviation and the resistance turbulence coupling deviation.

[0014] Thirdly, this application provides a computer device including a memory and a processor. The memory is used to store computer program code, and the processor is used to call and run the computer program code from the memory to perform the method as described in the first aspect of this application or any embodiment of the first aspect.

[0015] Fourthly, this application provides a computer program product comprising computer program code, which, when executed, performs the method as described in the first aspect of this application or any embodiment thereof.

[0016] Fifthly, this application provides a computer-readable storage medium that stores computer program code, which, when executed, performs the method as described in the first aspect of this application or any embodiment thereof.

[0017] This application has the following beneficial effects: This application first collects the rotational speed and torque current after the start command is issued, and constructs a real-time feature vector based on the torque balance principle and the correlation with time-series changes. This enables the accurate decoupling of the real-time pipeline resistance coefficient and real-time turbulence pulsation intensity, which are stripped of fluid inertial interference, during the unsteady-state process of variable frequency speed regulation, thus achieving precise quantification of the physical characteristics of the pipeline network. Furthermore, this invention calculates the resistance characteristic deviation and the resistance-turbulence coupling deviation, and uses the physical coupling characteristics between the pipeline network resistance and turbulence pulsation for dual verification. This effectively identifies normal loads, abnormal pipeline structures, and abnormal fluid conditions such as cavitation and drift that cannot be distinguished by steady-state current, making the remote control of pump stations more accurate in complex communication and hydraulic environments. Attached Figure Description

[0018] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, 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.

[0019] Figure 1 A flowchart illustrating a remote control method for an integrated water and fertilizer smart pumping station according to an embodiment of the present invention; Figure 2 This is a structural diagram of a remote control system for an integrated water and fertilizer smart pump station provided in one embodiment of the present invention; Figure 3 This is a schematic diagram of a computer device structure provided in one embodiment of the present invention. Detailed Implementation

[0020] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a remote control method and system for an integrated water and fertilizer intelligent pumping station proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment, and specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of indicated technical features. Thus, a feature defined with "first" or "second" may explicitly or implicitly include one or more of that feature.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0022] The following description, in conjunction with the accompanying drawings, details the specific scheme of the remote control method and system for an integrated water and fertilizer intelligent pumping station provided by this invention.

[0023] This application provides a remote control method for an integrated water and fertilizer intelligent pumping station. Please refer to [link / reference needed]. Figure 1 The diagram illustrates a remote control method for an integrated water and fertilizer smart pumping station according to an embodiment of the present invention. The method includes: Step S101: Collect the centrifugal pump impeller speed and motor output torque current at each sampling moment within the sampling time period after the pump room valve opening command is issued.

[0024] The integrated water and fertilizer pump station of this invention is equipped with a centrifugal pump to provide pressurized water to the farmland irrigation network. The centrifugal pump is coaxially driven by a three-phase AC asynchronous motor through a coupling. To achieve constant pressure water supply and remote start / stop control, the system is equipped with a frequency converter, which is connected between the mains power supply and the motor to adjust the input frequency and voltage of the motor, thereby changing the output speed and torque of the motor. It should be noted that the motor referred to thereafter refers to this three-phase AC asynchronous motor, and will not be further elaborated here.

[0025] In one specific implementation of this invention, a Hall current sensor is installed on the three-phase output cable between the frequency converter and the motor, and a speed sensor is installed at the coupling between the motor and the centrifugal pump. The Hall current sensor collects the motor output torque current at each sampling moment, and the speed sensor collects the centrifugal pump impeller speed at each sampling moment. It should be noted that although the Hall sensor directly measures the total stator current, the motor flux is in a relatively stable state during centrifugal pump operation, and the excitation current component changes little. Therefore, the amplitude change of the total stator current is mainly caused by the change in load torque. Thus, the collected total stator current can be directly used as a representative quantity of the motor output torque current for subsequent analysis and calculation. Alternatively, the implementer can collect the motor output torque current using other methods depending on the specific implementation environment. For example, after collecting the mechanical torque using a torque-speed sensor installed in the middle of the coupling, the ratio between the mechanical torque and the torque current and the motor constant can be used to calculate the motor output torque current at each sampling moment. Further details are omitted here.

[0026] In one specific implementation of this invention, the sampling frequency is set to 10Hz, and the sampling time period is set to within 30 seconds after each valve opening command is issued. This can be adjusted according to the specific implementation environment and will not be elaborated further here. After acquiring the centrifugal pump impeller speed and motor output torque current at each sampling moment, the data is synchronously transmitted to the pump room's main controller. The controller has a built-in analog-to-digital conversion module and a high-speed counting module, which convert the received signals into digital sequences and mark and store the data based on a unified system timestamp, thereby generating a series of time-aligned speed-current data pairs. This provides a reliable data foundation for subsequent construction of torque balance equations and feature decoupling. It should be noted that after receiving the original centrifugal pump impeller speed data, the main controller first reads the rated speed of the motor. The ratio between the centrifugal pump impeller speed and the rated speed of the motor at each sampling moment is used as the per-unit value of the centrifugal pump impeller speed at each sampling moment. This is used to convert the speed data into dimensionless data. This not only unifies the calculation dimensions of water pumps of different power levels, but also improves the stability of numerical calculation. In the subsequent analysis process of this embodiment, the centrifugal pump impeller speed is analyzed or calculated using the corresponding per-unit value, which will not be further elaborated here.

[0027] Step S102: Based on the torque balance principle, construct a real-time feature vector according to the correlation between the motor output torque current and the centrifugal pump impeller speed in time sequence; the real-time feature vector includes the real-time pipeline resistance coefficient and the real-time turbulence pulsation intensity after each start command is issued.

[0028] After acquiring the raw electrical operating data, directly using this data often makes it difficult to distinguish the true physical state of the pipeline network. This is because during motor startup and speed regulation, the inertial torque used to accelerate the fluid mass is superimposed on the steady-state resistance torque, forming unsteady-state interference and causing inflated current readings. Furthermore, simple current values ​​cannot isolate the crucial flow characteristic of turbulence noise. To address the technical problem of existing technologies failing to accurately identify abnormal pipeline resistance and flow anomalies such as cavitation under unsteady operating conditions and communication blind spots, it is necessary to decouple the steady-state characteristics that can independently characterize the pipeline network's flow capacity from the mixed raw signals, and the random characteristics that characterize the fluid flow state. Therefore, after acquiring the synchronous centrifugal pump impeller speed and motor output torque current, this invention does not directly perform threshold comparison. Instead, based on the torque balance principle, it constructs a dynamic model including fluid inertia terms according to the temporal correlation between the motor output torque current and the centrifugal pump impeller speed. This allows for the accurate extraction of the real-time pipeline resistance coefficient stripped of inertial interference and the quantification of the real-time turbulent pulsation intensity of flow noise, i.e., the construction of a real-time feature vector. This provides a reliable input basis for subsequent dual verification, significantly improving the identification accuracy of complex hydraulic conditions.

[0029] Preferably, in some possible implementations of the embodiments of the present invention, the process of obtaining the real-time feature vector includes: A torque balance equation is constructed. Based on the centrifugal pump impeller speed and motor output torque current at each sampling moment, a polynomial fitting is performed using the torque balance equation to determine the real-time pipeline resistance coefficient after each start-up command is issued and the instantaneous residual at each sampling moment. Specifically, based on rigid body dynamics and the Euler equations for fluid dynamics, the total torque current output by the motor is decomposed into a static component that overcomes the hydrostatic pressure of the pipeline, a steady-state dynamic pressure component that overcomes the frictional resistance of the pipeline, and a dynamic inertial component that accelerates the fluid and rotor mass. The constructed torque balance equation is expressed in the following formula: ;in, For the first Motor output torque current at each sampling time; Let be the hydrostatic pressure load coefficient to be solved, which characterizes the constant torque required to overcome the terrain elevation difference; The real-time pipeline resistance coefficient to be solved represents the flow resistance characteristics of the pipeline network. The fluid inertia coefficient to be solved represents the inertial response of the system during acceleration. For the first Centrifugal pump impeller speed at each sampling time; For the first The rate of change of rotational speed at each sampling time; For the first The instantaneous residuals to be solved at each sampling time point; where the process of obtaining the rate of change of rotational speed is expressed by the formula: ;in, For the first Centrifugal pump impeller speed at each sampling time; The time interval between adjacent sampling moments, in this embodiment of the invention, is based on a sampling frequency of 10Hz. The value is fixed at 0.1 for calculation. It should be noted that, since there is no previous sampling time at the first sampling time, this embodiment of the invention directly sets the rotational speed change rate at the first sampling time to 0.

[0030] Among them, the hydrostatic pressure load coefficient, since it represents the constant torque required to overcome the terrain elevation difference, is independent of the rotational speed and is directly used in the calculation; for the real-time pipeline resistance coefficient, based on the Darcy-Weisbach formula and centrifugal pump similarity law in fluid mechanics, the frictional resistance generated by the fluid flowing in the pipeline is proportional to the square of the flow velocity, and the flow velocity is proportional to the pump speed. Therefore, the torque required to overcome the dynamic pressure resistance of the pipeline has a strict linear relationship with the square of the rotational speed. Therefore, the product between the real-time pipeline resistance coefficient and the square of the centrifugal pump impeller speed is used in the calculation; for the fluid inertia coefficient, during the acceleration or deceleration of the motor, in addition to overcoming the above steady-state resistance, it is also necessary to provide additional torque to change the angular momentum of the rotor itself and the momentum of the large water body in the pipeline. This torque exists only when the rotational speed changes. According to the rotational form of Newton's second law, its magnitude is proportional to the angular acceleration, that is, it depends on the change in rotational speed per unit time. Therefore, the product between the fluid inertia coefficient and the rate of change of the centrifugal pump impeller speed is used in the calculation. The instantaneous residual characterizes the random fluctuation component that cannot be explained by the above dynamic model. It mainly comes from the unsteady turbulent vortices generated when the fluid flows through valves, elbows and pipe necks, as well as the fluid pulsation noise inside the pump body. Its amplitude directly reflects the degree of turbulence in the fluid flow.

[0031] After substituting the centrifugal pump impeller speed and motor output torque current at all sampling moments into the torque balance equation, each sampling moment corresponds to a linear equation containing unknown parameters. The least squares method is used to perform regression solving on the system of equations formed by the linear equations at all sampling moments to calculate the hydrostatic load coefficient, real-time pipeline resistance coefficient, and fluid inertia coefficient corresponding to the minimum sum of squared residuals at all sampling moments. Then, the centrifugal pump impeller speed and motor output torque current at each sampling moment are input into the torque balance equation with the specific values ​​of these three parameters to calculate the specific magnitude of the instantaneous residual corresponding to each sampling moment.

[0032] The real-time turbulent pulsation intensity after each activation command is issued is determined based on the overall magnitude of the instantaneous residuals at all sampling times. Specifically, the process of obtaining the real-time turbulent pulsation intensity includes: calculating the root mean square (RMS) value of the instantaneous residuals at all sampling times to determine the real-time turbulent pulsation intensity after each activation command is issued. Since the magnitude of the instantaneous residuals directly reflects the degree of turbulence in fluid flow, the real-time turbulent pulsation intensity can be directly determined by the magnitude of the instantaneous residuals. The reason for using the RMS value is that the instantaneous residuals, as random fluctuation components, fluctuate around zero on the time axis, including deviations in both positive and negative directions. If the arithmetic mean is directly calculated, the positive and negative fluctuations will cancel each other out, resulting in an inability to accurately reflect the energy magnitude of the fluctuations, i.e., the intensity of turbulence. The RMS value, by first squaring, then averaging, and finally taking the square root, effectively accumulates the energy amplitude of all fluctuations, thereby accurately characterizing the real-time turbulent pulsation intensity of the fluid throughout the entire sampling period.

[0033] Since the decoupled hydrostatic load coefficient mainly depends on the terrain elevation difference and is a constant value when the pump station location is fixed, it has no value for state identification. The fluid inertia coefficient only appears during speed regulation and cannot reflect the steady-state characteristics of the system. In contrast, the real-time pipeline resistance coefficient directly reflects the frictional resistance and local head loss of the pipeline, and is the only steady-state physical quantity characterizing valve opening and pipeline patency. However, a single steady-state resistance characteristic, namely the real-time pipeline resistance coefficient, cannot distinguish between low resistance caused by pipeline structural anomalies such as pipe bursts and false loads caused by fluid condition anomalies such as cavitation, and is easily affected by power grid fluctuations, leading to misjudgments. By introducing turbulent pulsation, a fluid dynamics-related characteristic, the physical authenticity of the steady-state resistance characteristic can be effectively verified, thereby achieving decoupled identification of complex fault types. Therefore, the vector corresponding to the real-time pipeline resistance coefficient and the real-time turbulent pulsation intensity, arranged sequentially, is used as the real-time feature vector after each opening command is issued.

[0034] Step S103: Based on the historical operating benchmark deviation of the real-time pipeline resistance coefficient, determine the resistance characteristic deviation after each start command is issued; based on the relative deviation of the coupling relationship between the real-time pipeline resistance coefficient and the real-time turbulence pulsation intensity compared to the historical operating benchmark, determine the resistance-turbulence coupling deviation after each start command is issued.

[0035] After completing the dynamic decoupling and feature extraction of the unsteady raw data, the system obtains a real-time pipeline resistance coefficient that can independently characterize the flow capacity of the pipeline network. However, the absolute value of this coefficient does not have direct discriminative significance because the pipeline structure itself has huge physical differences in different irrigation areas and different crop planting patterns. In order to accurately identify whether the current pipeline structure has undergone abnormal changes, such as main pipe bursting or valves not being fully opened, without preset fixed thresholds, a relative evaluation mechanism based on its own historical state must be established. Therefore, this invention uses the historical operating benchmark of the pump house under normal operating conditions recorded in the memory as a reference system. Based on the deviation of the historical operating benchmark of the real-time pipeline resistance coefficient, the resistance characteristic deviation after each start command is issued is determined. Thus, by quantifying the degree of drift of the current state relative to its own benchmark, adaptive verification of the stability of the macroscopic topology of the pipeline network is achieved.

[0036] Preferably, in some possible implementations of the embodiments of the present invention, the process of obtaining the drag characteristic deviation includes: Obtain the historical feature vector corresponding to each start command issued; the historical pipeline resistance coefficient and historical turbulence intensity are arranged in the historical feature vector in sequence. It should be noted that during subsequent analysis, when the fluid condition and macroscopic structure of the pipeline network are normal after each opening command is issued (i.e., the valve is successfully opened), the historical feature vector will be updated based on the real-time feature vector to determine the historical feature vector after the next opening command is issued. Therefore, in this embodiment of the invention, the historical feature vector corresponding to each opening command needs to be analyzed based on the valve opening status at the time of the previous opening command. If the historical feature vector was updated normally at the time of the previous opening command (i.e., the valve was successfully opened), then the historical feature vector can be directly obtained. If there is no previous opening command (i.e., the equipment is initially installed) or the valve failed to open and needs to be reset under the previous opening command, the historical feature vector cannot be determined from the previous opening command and needs to be initialized. That is, in this embodiment of the invention, when the historical feature vector at the time of a certain opening command cannot be obtained, the valve status after the corresponding opening command is issued is directly updated to successful opening, and the calculated real-time feature vector is used as the historical feature vector after the next opening command is issued for subsequent analysis and calculation. The subsequent analysis process of this embodiment of the invention only applies to the case where the historical feature vector can be obtained at the time of the opening command.

[0037] Further, based on the difference between the historical and real-time network resistance coefficients, the resistance coefficient deviation value is determined; and based on the ratio between the resistance coefficient deviation value and the historical network resistance coefficient, the resistance characteristic deviation is determined. For the real-time network resistance coefficient after each opening command is issued, the larger the deviation from the historical network resistance coefficient, the more significant the drift in the actual flow resistance characteristics of the current network relative to the expected normal state, suggesting a possible sudden drop in resistance due to pipeline rupture or a surge in resistance due to valve mechanical jamming. Under normal circumstances, since the physical topology of the irrigation network, such as pipe length, pipe diameter, and valve stroke, is relatively fixed, its network resistance coefficient should remain within a very small fluctuation range. Therefore, the larger the calculated resistance characteristic deviation, the higher the probability of an anomaly in the macroscopic structure of the network. The purpose of using the historical network resistance coefficient as the denominator here is to standardize the deviation, eliminate the dimensional influence caused by the different basic resistances of different irrigation branches, and make the deviation index have a uniform evaluation scale under different load conditions.

[0038] It should be noted that since the historical pipeline resistance coefficient is based on the system's previous confirmed normal operation and successful valve opening status record, in the real physical world, any fluid flowing in a pipeline will inevitably generate frictional resistance and local head loss. That is, the pipeline resistance coefficient is objectively always a positive value. Therefore, the historical pipeline resistance coefficient in this embodiment of the invention cannot be 0, and the formula will not be meaningless. It should also be noted that if the historical pipeline resistance coefficient is 0 after a certain opening command is issued, it means that the historical reference itself is invalid. In this case, the valve status after the current opening command is issued is directly updated to successful opening, and the calculated real-time feature vector is used as the historical feature vector after the next opening command is issued for subsequent analysis and calculation.

[0039] While resistance characteristic deviation can effectively identify macroscopic anomalies in pipeline structures, under certain specific operating conditions, such as falsely high current readings caused by zero-point drift of pressure sensors, or pump cavitation and idling caused by excessively low water levels, the system may calculate a seemingly normal or excessively high resistance coefficient, thus misleading the single-dimensional resistance verification logic. To further eliminate such non-physical false signals, it is necessary to introduce multi-dimensional physical consistency constraints from fluid mechanics, namely, that the actual resistance work must be accompanied by a specific proportion of turbulent energy dissipation. Therefore, after verifying the stability of the pipeline structure, this invention further delves into the microscopic level of the flow regime. Utilizing the inherent relationship between the two orthogonal components in the real-time feature vector, and based on the relative deviation of the coupling relationship between the real-time pipeline resistance coefficient and the real-time turbulent pulsation intensity compared to the historical operating benchmark, the resistance-turbulence coupling deviation is determined after each start-up command is issued. By verifying the self-consistency of this accompanying physical law of resistance-turbulence, the authenticity of fluid operating conditions is deeply identified.

[0040] Preferably, in some possible implementations of the embodiments of the present invention, the process of obtaining the drag-turbulence coupling deviation includes: Based on the ratio between real-time turbulence intensity and real-time pipeline resistance coefficient, the real-time resistance-turbulence coupling value after each start command is issued is determined; based on the ratio between historical turbulence intensity and historical pipeline resistance coefficient, the historical resistance-turbulence coupling value after each start command is determined; based on the difference between the real-time resistance-turbulence coupling value and the historical resistance-turbulence coupling value, the coupling deviation value after each start command is determined; based on the ratio between the coupling deviation value and the historical resistance-turbulence coupling value, the resistance-turbulence coupling deviation degree after each start command is determined.

[0041] The real-time resistance-turbulence coupling value characterizes the turbulent pulsation energy density associated with a unit network resistance under current operating conditions, reflecting the transient physical ratio between work and noise within the current fluid system. The historical resistance-turbulence coupling value characterizes the inherent resistance-turbulence co-occurrence ratio of the network structure under confirmed normal baseline operating conditions. Since in real fluid physics processes, defined network resistance components such as valves and elbows will generate a defined proportion of turbulent vortices under normal flow conditions, and this ratio is physically conserved, it typically does not produce large numerical fluctuations. Therefore, the relationship between the real-time and historical resistance-turbulence coupling values ​​is relatively stable. The larger the relative deviation, i.e. the larger the coupling deviation value, the more it indicates that the current fluid flow state has disrupted the original physical associated laws, suggesting the existence of non-physical interference factors in the system, such as sensor drift causing only resistance readings without turbulent response, or pump cavitation causing a surge in turbulent noise and insufficient effective resistance. The purpose of calculating the resistance-turbulent coupling deviation degree based on the coupling deviation value and using the historical resistance-turbulent coupling value as the denominator is to standardize the deviation amount, eliminate the dimensional influence caused by the different turbulent base levels due to differences in pipe diameter and pump type in different irrigation systems, and make the deviation degree index have universal dimensionless evaluation significance across different equipment.

[0042] It should be noted that when the real-time pipeline resistance coefficient has an extreme mathematical fitting error or is 0 under completely unloaded conditions, the real-time pipeline resistance coefficient is replaced with a preset minimum positive value to calculate the real-time resistance turbulence coupling value. This avoids the situation where the denominator is 0, which would be meaningless. In a specific implementation of this invention, the preset minimum positive value is 0.001, which can be adjusted according to the specific implementation environment. Further details are not provided here. Since in actual fluid transportation, as long as there is fluid flow, there will inevitably be friction between fluid molecules and microscopic vortices, the historical turbulence pulsation intensity obtained under normal operating conditions cannot be 0, and the calculated historical resistance turbulence coupling value cannot be 0 either. Therefore, there is no problem of the denominator being 0 here.

[0043] Step S104: Perform remote control of the pump house based on the resistance characteristic deviation and the resistance turbulence coupling deviation.

[0044] Through the above steps, the system has successfully quantified the resistance characteristic deviation, which characterizes the degree of deviation of the macroscopic structure of the pipeline network, and the resistance turbulence coupling deviation, which characterizes the authenticity of the microscopic flow state of the fluid, from complex unsteady electrical signals. These two indicators constitute two orthogonal criteria for judging whether the pipeline is normal and whether the water flow is real. In order to transform these physical-level diagnostic results into precise control commands for pump station equipment, especially to avoid blind operation or erroneous shutdown in the critical state of lost remote communication feedback, this invention further establishes a multi-dimensional logic arbitration mechanism. Based on the resistance characteristic deviation and the resistance turbulence coupling deviation, the system performs remote control of the pump station. According to different deviation combination modes, it accurately identifies normal operation, pipeline structural faults such as pipe bursts, and fluid condition faults such as cavitation, and executes differentiated closed-loop feedback, shutdown protection, or alarm strategies accordingly, thereby enabling adaptive remote control of the pump station in complex communication and hydraulic environments.

[0045] Preferably, in some possible implementations of the embodiments of the present invention, the process of remotely controlling the pump house based on the deviation of resistance characteristics and the deviation of resistance-turbulence coupling includes: After each start command is issued, if the resistance characteristic deviation is greater than the preset characteristic deviation threshold (i.e., the resistance characteristic deviation is relatively large), it indicates that the resistance characteristics of the current pipeline network have undergone a significant abrupt change beyond the normal aging range relative to the historical benchmark. This indicates that the physical topology of the pipeline network may have suffered structural damage, such as pipe bursting or actuator failure, such as valve jamming. Therefore, the macroscopic structural state of the pipeline network is judged as abnormal. When the resistance characteristic deviation is less than or equal to the preset characteristic deviation threshold (i.e., the resistance characteristic deviation is relatively small), it indicates that the flow resistance characteristics of the pipeline network remain stable and conform to the expected physical structural characteristics. Therefore, the macroscopic structural state of the pipeline network is judged as normal.

[0046] After each activation command is issued, the fluid condition status is determined based on the resistance-turbulence coupling deviation. Specifically: when the resistance-turbulence coupling deviation is greater than the preset coupling deviation threshold, it indicates that the current fluid flow violates the normal physical co-occurrence law of resistance-turbulence, that is, the detected turbulence noise does not match the resistance work, indicating the presence of non-physical false signals such as sensor drift or abnormal flow states such as cavitation idling, and the corresponding fluid condition status is judged as abnormal. When the resistance-turbulence coupling deviation is less than or equal to the preset coupling deviation threshold, it indicates that the steady-state resistance of the fluid and the microscopic turbulence characteristics corroborate each other and conform to the physical consistency of the real hydraulic conditions, and the corresponding fluid condition status is judged as normal.

[0047] In one specific implementation of this invention, the preset feature deviation threshold is set to 0.25 based on experience, and the preset coupling deviation threshold is set to 0.4. These values ​​can be adjusted according to the specific implementation environment. When adjusting, the suggested range for the preset feature deviation threshold is 0.15 to 0.3, and the suggested range for the preset coupling deviation threshold is 0.3 to 0.5. The smaller the value, the higher the system's sensitivity to minor changes in the pipeline structure and abnormal flow patterns, the stricter the judgment criteria, and the earlier potential faults can be detected. However, it may also lead to an increase in the false alarm rate due to normal operating condition fluctuations such as viscosity drift caused by water temperature changes. Conversely, the larger the value, the stronger the system's fault tolerance, but it may miss minor leaks or early cavitation phenomena, which will not be further elaborated here.

[0048] Furthermore, the pump station is remotely controlled based on the macroscopic structure and fluid condition status of the pipeline network after each start command is issued. Specifically, when the fluid condition status and the macroscopic structure status of the pipeline network are both normal after each start command is issued, the valve status is updated to "successfully opened," and the historical feature vector is updated based on the real-time feature vector to determine the historical feature vector after the next start command is issued. In a specific implementation of this invention, after the valve status is updated to "successfully opened," the control logic deadlock caused by packet loss in the remote communication link (i.e., the host computer not receiving feedback and remaining in a waiting state) is eliminated. The main controller generates a virtual execution feedback message locally. The data structure of this message is completely consistent with the real valve controller feedback message, including the target valve ID and the successful opening status code. The main controller injects this virtual message into its own command execution status queue or sends it to the host computer, actively closing the control process to ensure that the irrigation task sequence can continue to execute, avoiding the interruption of the entire irrigation plan due to a single communication failure.

[0049] In one specific implementation of this invention, the process of updating historical feature vectors based on real-time feature vectors to determine the historical feature vectors after the next start command is issued includes: weighting the historical feature vectors after each start command is issued using a preset first weight to determine a weighted historical vector; weighting the real-time feature vectors after each start command is issued using a preset second weight to determine a weighted real-time vector; and adding the weighted historical vector and the weighted real-time vector to determine the historical feature vector after the next start command is issued. Here, the sum of the first weight and the second weight is 1, and both the first weight and the second weight are greater than 0. This update of historical feature vectors based on the weighted moving average algorithm allows the baseline data to retain long-term historical trend information while gently incorporating the latest valid observation data. This enables adaptive tracking of the slowly changing characteristics of the pipeline network caused by long-term operation, such as pipe wall scaling and wear, ensuring continuous verification accuracy.

[0050] In one specific implementation of this invention, the first preset weight is set to 0.95 and the second preset weight is set to 0.05. This means that the new historical benchmark mainly continues the old benchmark state and only incorporates 5% of the current real-time features, making the benchmark update have extremely high anti-interference inertia. It can effectively filter out occasional random fluctuations in a single run and prevent the benchmark data from being skewed by transient noise. It can be adjusted automatically according to the specific implementation environment. The larger the first preset weight, the stronger the stability of the benchmark, but the slower the response to the real changes in the pipeline characteristics. The larger the second preset weight, the faster the system adapts to new changes, but the volatility of the benchmark data will also increase, which may reduce the robustness of the verification.

[0051] When the macroscopic structure of the pipeline is normal but the corresponding fluid condition is abnormal after each start command is issued, the control pump stops running and a maintenance alarm is issued. At this time, although no obvious damage is observed in the physical structure of the pipeline, the fluid system may be in an abnormal operating state such as cavitation, cavitation, or severe sensor drift. Continuing operation may lead to pump impeller damage or control inaccuracy. Therefore, the system executes a "soft shutdown" strategy and prompts maintenance personnel to check the water level and sensor status to prevent the equipment from operating under adverse conditions for an extended period.

[0052] When the corresponding macroscopic structure of the pipeline network is found to be abnormal after each start command is issued, the power supply to the water pump is cut off and a shutdown alarm is issued. At this time, the system determines that there has been substantial physical damage to the pipeline network, such as a main pipe burst or a serious actuator failure, such as a valve not being opened causing pump stalling. Continued operation would lead to serious water and fertilizer leakage accidents or motor overload and burnout. Therefore, the system executes the highest priority "hard interruption" strategy, immediately cutting off the power supply to physically prevent the risk of the accident escalating.

[0053] In summary, a remote control method for an integrated water and fertilizer intelligent pumping station first collects the rotational speed and torque current after the start command is issued, and constructs a real-time feature vector based on the torque balance principle and the correlation of time-series changes. This allows for accurate decoupling of the real-time pipeline resistance coefficient and real-time turbulence pulsation intensity, stripped of fluid inertial interference, during the unsteady-state process of variable frequency speed regulation, thus achieving precise quantification of the pipeline network's physical characteristics. Furthermore, this invention calculates the resistance characteristic deviation and the resistance-turbulence coupling deviation, utilizing the physical coupling characteristics between pipeline network resistance and turbulence pulsation for dual verification. This effectively identifies normal loads, abnormal pipeline structures, and abnormal fluid conditions such as cavitation and drift that cannot be distinguished by steady-state current, making remote control of the pumping station more accurate in complex communication and hydraulic environments.

[0054] This application also provides a remote control system for an integrated water and fertilizer intelligent pumping station; please refer to [link / reference needed]. Figure 2 The diagram shows a structure of a remote control system for an integrated water and fertilizer smart pumping station according to an embodiment of the present invention. The system includes: a data acquisition module 201, a vector construction module 202, a parameter determination module 203, and a pumping station remote control module 204.

[0055] Data acquisition module 201 is used to collect the centrifugal pump impeller speed and motor output torque current at each sampling moment within the sampling period after each valve opening command is issued in the pump room; The vector construction module 202 is used to construct a real-time feature vector based on the torque balance principle and the time-series correlation between the motor output torque current and the centrifugal pump impeller speed. The real-time feature vector includes the real-time pipeline resistance coefficient and the real-time turbulence pulsation intensity after each start command is issued. The parameter determination module 203 is used to determine the resistance characteristic deviation after each start command is issued based on the historical operating benchmark deviation of the real-time pipeline resistance coefficient; and to determine the resistance-turbulence coupling deviation after each start command is issued based on the relative deviation of the coupling relationship between the real-time pipeline resistance coefficient and the real-time turbulence pulsation intensity compared to the historical operating benchmark. The pump house remote control module 204 is used for remote control of the pump house based on the resistance characteristic deviation and the resistance-turbulence coupling deviation.

[0056] It should be noted that the system provided in the above embodiments is only an example of the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device can be divided into different functional modules to complete all or part of the functions described above. In addition, the remote control system of the integrated water and fertilizer intelligent pumping station and the remote control method embodiment of the integrated water and fertilizer intelligent pumping station provided in the above embodiments belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0057] This application also provides a computer device; please refer to [link / reference]. Figure 3 The diagram illustrates a computer device structure according to an embodiment of the present invention. The computer device includes a memory 301, a processor 302, and a computer program 303 stored in the memory 301 and running on the processor 302. When the processor 302 executes the computer program 303, the computer device can execute any of the aforementioned remote control methods for integrated water and fertilizer intelligent pumping stations.

[0058] This application also provides a computer program product that, when run on a computer device, enables the computer device to execute any of the aforementioned remote control methods for integrated water and fertilizer smart pumping stations.

[0059] This application also provides a computer-readable storage medium storing computer program code. When the computer program code is run on a computer device, the computer device can execute any of the aforementioned remote control methods for integrated water and fertilizer intelligent pumping stations.

[0060] In the embodiments provided in this application, it should be understood that the computer device, computer program product and computer-readable storage medium provided are all used to perform the corresponding methods provided above, and therefore the beneficial effects they can achieve can be referred to the beneficial effects of the methods provided above, which will not be repeated here.

[0061] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0062] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A remote control method for an integrated water and fertilizer intelligent pumping station, characterized in that, The method includes: The centrifugal pump impeller speed and motor output torque current are collected at each sampling moment within the sampling period after each valve opening command is issued in the pump room. Based on the torque balance principle, a real-time feature vector is constructed according to the correlation between the motor output torque current and the centrifugal pump impeller speed in time sequence. The real-time feature vector includes the real-time pipeline resistance coefficient and the real-time turbulence pulsation intensity after each start command is issued. Based on the historical operating benchmark deviation of the real-time pipeline resistance coefficient, the resistance characteristic deviation after each start command is issued is determined; based on the relative deviation of the coupling relationship between the real-time pipeline resistance coefficient and the real-time turbulence intensity compared to the historical operating benchmark, the resistance-turbulence coupling deviation after each start command is determined. The pump house is remotely controlled based on the resistance characteristic deviation and the resistance turbulence coupling deviation.

2. The remote control method for an integrated water and fertilizer intelligent pumping station according to claim 1, characterized in that, The process of obtaining the real-time feature vector includes: Construct a torque balance equation; based on the centrifugal pump impeller speed and motor output torque current at each sampling moment, perform polynomial fitting through the torque balance equation to determine the real-time pipeline resistance coefficient after each start command is issued and the instantaneous residual at each sampling moment; The real-time turbulence intensity after each start command is issued is determined based on the overall magnitude of the instantaneous residuals at all sampling times. The vector corresponding to the real-time pipeline resistance coefficient and the real-time turbulence intensity arranged in sequence is used as the real-time feature vector.

3. The remote control method for an integrated water and fertilizer intelligent pumping station according to claim 2, characterized in that, The process of obtaining the real-time turbulence fluctuation intensity includes: Calculate the root mean square value of the instantaneous residuals at all sampling times to determine the real-time turbulence intensity after each start command is issued.

4. The remote control method for an integrated water and fertilizer intelligent pumping station according to claim 1, characterized in that, The process of obtaining the resistance characteristic deviation includes: Obtain the historical feature vector corresponding to each start command issued; the historical feature vector contains the historical pipeline resistance coefficient and the historical turbulence fluctuation intensity arranged in sequence. The resistance coefficient deviation value is determined based on the difference between the historical pipeline resistance coefficient and the real-time pipeline resistance coefficient. The resistance characteristic deviation is determined based on the ratio between the resistance coefficient deviation value and the historical pipeline resistance coefficient.

5. The remote control method for an integrated water and fertilizer intelligent pumping station according to claim 4, characterized in that, The process of obtaining the resistance turbulence coupling deviation includes: Based on the ratio between the real-time turbulence intensity and the real-time pipeline resistance coefficient, the real-time resistance-turbulence coupling value after each start command is issued is determined; based on the ratio between the historical turbulence intensity and the historical pipeline resistance coefficient, the historical resistance-turbulence coupling value after each start command is determined. Based on the difference between the real-time resistance-turbulence coupling value and the historical resistance-turbulence coupling value, the coupling deviation value after each activation command is issued is determined; The drag-turbulence coupling deviation is determined based on the ratio between the coupling deviation value and the historical drag-turbulence coupling value after each activation command is issued.

6. The remote control method for an integrated water and fertilizer intelligent pumping station according to claim 4, characterized in that, The process of remotely controlling the pump house based on the resistance characteristic deviation and the resistance-turbulence coupling deviation includes: After each start command is issued, if the resistance characteristic deviation is greater than the preset characteristic deviation threshold, the macroscopic structure of the pipeline network is determined to be abnormal; if the resistance characteristic deviation is less than or equal to the preset characteristic deviation threshold, the macroscopic structure of the pipeline network is determined to be normal. After each activation command is issued, the fluid condition state after each activation command is determined based on the resistance-turbulence coupling deviation. The pump room is remotely controlled based on the macroscopic structural state of the pipeline network and the fluid operating conditions after each start command is issued.

7. The remote control method for an integrated water and fertilizer intelligent pumping station according to claim 6, characterized in that, The process of determining the fluid condition state after each activation command is issued based on the resistance-turbulence coupling deviation includes: When the resistance-turbulent coupling deviation is greater than the preset coupling deviation threshold, the corresponding fluid condition is determined to be abnormal; when the resistance-turbulent coupling deviation is less than or equal to the preset coupling deviation threshold, the corresponding fluid condition is determined to be normal.

8. The remote control method for an integrated water and fertilizer intelligent pumping station according to claim 7, characterized in that, The process of remotely controlling the pump station based on the macroscopic structural state of the pipeline network and the fluid operating condition after each start command is issued includes: When the fluid condition is normal and the macroscopic structure of the pipeline is normal after each opening command is issued, the valve status is updated to "opening successful". The historical feature vector is updated according to the real-time feature vector to determine the historical feature vector after the next opening command is issued. When the macroscopic structure of the pipeline network is normal and the corresponding fluid condition is abnormal after each start command is issued, the water pump is controlled to stop running and a maintenance alarm is issued. When the corresponding macroscopic structure status of the pipeline network is abnormal after each start command is issued, the power supply to the water pump is cut off and a shutdown alarm is issued.

9. The remote control method for an integrated water and fertilizer intelligent pumping station according to claim 8, characterized in that, The process of updating the historical feature vector based on the real-time feature vector to determine the historical feature vector after the next start command is issued includes: The historical feature vector after each start command is issued is weighted by a preset first weight to determine the weighted historical vector; The real-time feature vector after each start command is issued is weighted by a preset second weight to determine the weighted real-time vector; The weighted historical vector and the weighted real-time vector are added together to determine the historical feature vector after the next start command is issued; wherein the sum of the first weight and the second weight is 1, and both the first weight and the second weight are greater than 0.

10. A remote control system for an integrated water and fertilizer intelligent pumping station, characterized in that, The system includes: The data acquisition module is used to collect the centrifugal pump impeller speed and motor output torque current at each sampling moment within the sampling period after each valve opening command is issued in the pump room; The vector construction module is used to construct a real-time feature vector based on the torque balance principle and the time-series correlation between the motor output torque current and the centrifugal pump impeller speed. The real-time feature vector includes the real-time pipeline resistance coefficient and the real-time turbulence pulsation intensity after each start command is issued. The parameter determination module is used to determine the resistance characteristic deviation after each start command is issued based on the historical operating benchmark deviation of the real-time pipeline resistance coefficient; and to determine the resistance-turbulence coupling deviation after each start command is issued based on the relative deviation of the coupling relationship between the real-time pipeline resistance coefficient and the real-time turbulence pulsation intensity compared to the historical operating benchmark. The pump house remote control module is used to remotely control the pump house based on the resistance characteristic deviation and the resistance turbulence coupling deviation.

Images