Secondary water supply pump station remote operation and maintenance method and system based on Internet of Things

Abstract

The invention discloses a secondary water supply pump station remote operation and maintenance method and system based on the Internet of Things, relates to the technical field of resource management, and realizes accurate identification of'micro water hammer 'implicit disturbance by collecting water supply related data, constructing a disturbance residual factor Dk, judging a water supply state and obtaining a dislocation characteristic index. The problem of missed judgment of short-time and low-amplitude dislocation behaviors in a traditional method is solved, periodic risk fluctuation is quantified through autocorrelation analysis of a time interval sequence, finally, an adjustment strategy is generated in real time in combination with a disturbance countermeasure library and is issued to a main control system, closed-loop control and self-adaptive correction of structural water hammer risks are achieved, and the accuracy of the structural water hammer risk is improved. And the steady-state operation capability of the secondary water supply pump station is effectively improved.

Description

Technical Field

[0001] This invention relates to the field of resource management technology, specifically to a remote operation and maintenance method and system for secondary water supply pumping stations based on the Internet of Things. Background Technology

[0002] With the intelligent development of urban infrastructure, Internet of Things (IoT) technology has been widely applied in the field of industrial control, especially in smart water systems. As a key link in the water supply chain, secondary water supply pumping stations are widely used in high-rise residential buildings, areas with different elevations, and commercial complexes to repressurize and stably deliver municipal raw water. In the IoT environment, by remotely collecting and intelligently controlling the operating parameters of the pumping stations in real time, the system can dynamically optimize the pump start-up and shutdown logic, frequency response, and safety status. However, in this system, water hammer disturbances caused during the start-up and shutdown of the pumping stations are always a potential threat to the safe operation of the system. In particular, those hidden micro water hammers that are not monitored in real time are gradually becoming key hidden dangers leading to equipment fatigue and pipeline rupture.

[0003] Chinese invention patent application CN119359058B discloses a method for monitoring and managing the operation of a secondary water supply pumping station. The method includes the following steps: collecting performance records, pump speed, and water pressure readings using water quality monitoring sensors and flow meters; cleaning and standardizing the data to obtain standardized data; applying regression analysis to the standardized data to predict the probability of risk events; and combining this with environmental monitoring data to generate regression analysis risk prediction results. This invention employs regression analysis and analysis of variance to conduct in-depth analysis of the collected pump speed, water pressure, and environmental data. This strategy not only makes risk prediction more accurate but also allows for a detailed assessment of the specific impact of various operational variables on pumping station performance. Through this method, managers can generate a list of risk points based on real-time data and dynamically adjust operational parameters, thereby achieving real-time optimization of the pumping station's operating status.

[0004] The above methods generate a risk point list based on real-time data and dynamically adjust operating parameters to achieve real-time optimization of the pump station's operating status. However, in the existing remote operation and maintenance system for secondary water supply pump stations, mechanical facilities such as slow-closing valves and check valves are usually used to suppress water hammer for intelligent control, supplemented by operating strategies such as soft start and constant pressure control, which can theoretically alleviate the risk of water hammer impact. However, although this method can alleviate the risk of water hammer impact, "micro water hammer" events still frequently occur in actual operation. These are slight water flow impacts that are not detected by sensors or control systems. They are mainly manifested as follows: during the start-up and shutdown of the pump station, the system monitoring data shows that the water pressure changes are stable and the operating status is normal, but the pump load experiences short-term jumps, motor vibrations, abnormal operating sounds, etc. This situation is often misjudged by the system as normal fluctuations, and thus the recording and intervention are ignored. As a result, the physical impact of micro water hammer is difficult to archive, assess, and predict the risk of recurrence. Therefore, the phenomenon of "water hammer cycle blind spot" has existed for a long time and it is difficult to intervene or avoid it in a timely manner through existing control methods.

[0005] Therefore, the present invention provides a method and system for remote operation and maintenance of secondary water supply pumping stations based on the Internet of Things. Summary of the Invention

[0006] To address the shortcomings of existing technologies, this invention provides a remote operation and maintenance method and system for secondary water supply pumping stations based on the Internet of Things (IoT). By collecting water supply-related data, constructing a disturbance residual factor Dk, determining the water supply status, and obtaining misalignment characteristic indicators, it achieves accurate identification of latent disturbances such as "micro-water hammer," overcoming the problem of traditional methods failing to detect short-term, low-amplitude misalignment behaviors. Furthermore, through autocorrelation analysis of time interval sequences, it quantifies periodic risk fluctuations. Finally, by combining a disturbance countermeasure library, it generates adjustment strategies in real time and distributes them to the main control system, achieving closed-loop control and adaptive correction of structural water hammer risks. This effectively improves the steady-state operation capability of secondary water supply pumping stations and solves the problems mentioned in the background technology.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solution: a remote operation and maintenance system for secondary water supply pumping stations based on the Internet of Things, including a multi-dimensional data acquisition module, a local disturbance analysis module, a misalignment feature analysis module, a risk assessment module, and an adaptive adjustment module; The multi-dimensional data acquisition module is used to collect water supply-related data from the secondary water supply pumping station in real time and construct a water supply-related data set S; The local disturbance analysis module is used to obtain the disturbance residual factor Dk based on the water supply related data set S, in order to determine the water supply status of the secondary water supply pumping station, and to trigger the misalignment feature analysis module to identify the misalignment sliding sampling window. The misalignment feature analysis module is used to extract features based on the water supply-related data set S to obtain a feature data set, mark water hammer triggering candidate segments, and construct a candidate time segment set G; The risk assessment module is used to construct a time interval sequence based on the candidate time interval set G, and perform autocorrelation analysis to obtain the periodic fluctuation risk index Fx in order to assess the risk level of micro water hammer phenomenon. The adaptive adjustment module is used to generate strategy adjustment parameters from the disturbance countermeasure library when the risk level of micro water hammer phenomenon is the third risk level, and to perform adaptive adjustment of the secondary water supply pumping station.

[0008] Preferably, the multi-dimensional data acquisition module is used to set up data acquisition nodes in the secondary water supply pumping station, and to install intelligent sensor groups on the data acquisition nodes. A multi-channel high-precision synchronous ADC interface board is used to connect each sensor, and a sliding sampling window is set. ], and in the sliding sampling window [ The system collects water supply-related data from secondary water supply pumping stations to obtain water supply-related data from several sliding sampling windows, and constructs a water supply-related data set S. This water supply-related data includes current signals I... Voltage signal U Input power at the motor end and the mechanical impedance M at the load end ; For the acquired current signal I and voltage signal U Using Fast Fourier Transform to identify the dominant frequency point and the collected current signal I and voltage signal U The frequency spectrum is transformed into a complex spectrum in the frequency domain through DFT transformation, and the dominant frequency point is obtained from the complex spectrum in the frequency domain. The complex spectrum value is used to calculate the phase difference between the current and voltage signals, and further obtain the phase synchronization factor Tb. The specific method for obtaining the phase synchronization factor Tb is as follows: ; In the formula, This indicates the voltage signal at the dominant frequency point. Complex spectral values ​​on This indicates the current signal at the dominant frequency point. Complex spectral values ​​on Indicates the dominant frequency point. Represents a complex phase angle function. This represents the phase angle of the voltage signal at the dominant frequency. denoted by , cos represents the phase angle of the current signal at the main frequency point, and cos represents the cosine function.

[0009] Preferably, the local disturbance analysis module includes a pressure trajectory fitting unit and a residual disturbance identification unit; The pressure trajectory fitting unit is used based on the sliding sampling window. Voltage signal U acquired within and main frequency Construct a periodic fitting pressure curve Among them, the periodically fitted pressure curve The specific manifestations are as follows: ; In the formula, This represents the constant term, which is the average pressure value of the fitted pressure trajectory curve. This represents the amplitude coefficient of the nth harmonic. Indicates the main frequency point The corresponding dominant angular frequency, , where n represents the harmonic order index. This represents the phase shift angle of the nth harmonic. The total harmonic order is represented by t, and the sliding sampling window is represented by t. The time variable within ], t∈[ ].

[0010] Preferably, the residual disturbance identification unit is used to fit the pressure curve based on the period. and voltage signal U By comparing and analyzing the residual energy density per unit time, the perturbation residual factor Dk is obtained. The specific method for obtaining the perturbation residual factor Dk is as follows: ; In the formula, This represents the pressure value at time point t. This represents the pressure value at time point t in the periodically fitted pressure curve. Indicates the sliding sampling window [ The duration of the duration; A preset residual judgment threshold Pd is established, and the residual judgment threshold Pd and the disturbance residual factor Dk are compared and analyzed to evaluate the water supply status of the secondary water supply pumping station. The specific evaluation content is as follows: If the disturbance residual factor Dk is less than or equal to the residual judgment threshold Pd, i.e., Dk≤Pd, then the water supply status of the secondary water supply pumping station is determined to be normal. At this time, the current operation strategy is maintained and water supply-related data is continuously monitored. If the disturbance residual factor Dk > the residual judgment threshold Pd, that is, Dk > Pd, then the water supply state of the secondary water supply pumping station is determined to be a structural disturbance state. At this time, the misalignment feature analysis module is immediately triggered to perform structural fault analysis.

[0011] Preferably, the misalignment feature analysis module includes a feature extraction unit and a misalignment evaluation unit; The feature extraction unit is used to extract features based on the water supply-related data set S, and to construct a feature data set H based on the extracted feature indicators; The maximum instantaneous rate of change of the sum of current and torque response is quantified to obtain the instantaneous load divergence index Fk. The specific method for obtaining the instantaneous load divergence index Fk is as follows: ; In the formula, This represents the input power at the motor terminals at time point t. This represents the mechanical impedance at the load end at time point t. Indicates the gain coefficient. Represents the phase synchronization factor. This indicates the phase synchronization factor of the equipment under rated conditions. Indicates the sliding sampling window The maximum derivative value within; Calculate the degree of deviation of pressure fluctuation within the current sliding sampling window to obtain the pressure stability residual factor Rk. The specific method for obtaining the pressure stability residual factor Rk is as follows: ; In the formula, This represents the pressure value at time point t. This represents the average pressure value across several sampling time points within the sliding sampling window. This represents the standard deviation of pressure within the sliding sampling window.

[0012] Preferably, the misalignment evaluation unit is used to perform a summary calculation for each sliding sampling window based on the feature data set H to obtain the misalignment coherence coefficient Ck, wherein the misalignment coherence coefficient Ck is obtained in the following way: ; In the formula, Indicates the instantaneous load divergence index. This represents the pressure-stabilized residual factor. Indicates a stress-inhibiting regulatory factor. Indicates the phase difference of the main frequency. This represents the phase lag suppression coefficient, and e represents the base of the natural logarithm. Set a misalignment threshold Ckyz, and for each sliding sampling window, compare the misalignment coherence coefficient Ck of the sliding sampling window with the misalignment threshold Ckyz. If the misalignment coherence coefficient Ck is greater than or equal to the misalignment threshold Ckyz, it is determined that dynamic coupling misalignment behavior of the three sides of the electronic control, load and hydraulic system has occurred in the sliding sampling window. At this time, the sliding sampling window is marked as a water hammer trigger candidate window. If the misalignment coherence coefficient Ck is less than the misalignment threshold Ckyz, it is determined that dynamic coupling misalignment behavior of the three sides of the electronic control, load and hydraulic system has not occurred in the sliding sampling window, and no processing is required. The set of all judgment results is a sliding sampling window of the water hammer triggering candidate window. The center time point of each water hammer triggering candidate window is extracted to construct the candidate time segment set G.

[0013] Preferably, the risk assessment module includes an autocorrelation analysis unit and a risk determination unit; The autocorrelation analysis unit is used to calculate the time interval between the center time points of each adjacent water hammer triggering candidate window based on the candidate time interval set G, in order to construct a time interval sequence. Based on this time interval sequence, autocorrelation analysis is performed to construct an autocorrelation function, which is specifically expressed as follows: ; In the formula, Indicates the lag step size as The autocorrelation function value at time, This represents the k-th time interval in the time interval sequence. Indicates the average of time intervals. Indicates the lag step size. Indicates the first There are 1 time intervals, where n represents the total number of time intervals; For autocorrelation function Calculate each lag step size Extract the autocorrelation function value, and then extract the maximum autocorrelation function value. And record the maximum autocorrelation function value. Corresponding lag step size ,in, =1, 2, 3, ..., n- .

[0014] Preferably, the risk assessment unit is used to set the maximum autocorrelation function value. Let Fx be the cyclical volatility risk index, and let the first cyclical volatility risk threshold be preset. Second-cycle volatility risk threshold The cyclical volatility risk index Fx is compared with the first cyclical volatility risk threshold. Second-cycle volatility risk threshold A comparative analysis was conducted to assess the risk level of micro-water hammer phenomena. The specific assessment content is as follows: If the cyclical volatility risk index Fx is less than or equal to the first cyclical volatility risk threshold That is, Fx≤ If the risk level of the micro water hammer phenomenon is determined to be the first risk level, then the time interval has no stable repeating characteristics and is determined to be a micro-occasional disturbance, not dominated by water hammer. If the cyclical volatility risk index Fx is greater than the first cyclical volatility risk threshold And less than the second cycle volatility risk threshold ,Right now <Fx< If the risk level of the micro water hammer phenomenon is determined to be the second risk level, then there is a potential water hammer hazard in the secondary water supply pumping station. The valve should be shut off with a delayed start and the start rate should be adjusted to 80% of the standard start rate. If the cyclical volatility risk index Fx is greater than or equal to the second cyclical volatility risk threshold That is, Fx≥ If the risk level of the micro water hammer phenomenon is determined to be the third risk level, then the secondary water supply pumping station has a structural water hammer risk, the disturbance period is significant, triggering the main control system of the secondary water supply pumping station to perform adaptive adjustment of the secondary water supply pumping station.

[0015] Preferably, the adaptive adjustment module is used to automatically generate strategy adjustment parameters based on the disturbance countermeasure library in the secondary water supply pumping station when the risk level of micro water hammer phenomenon is the third risk level, and package the strategy adjustment parameters into strategy control instructions, and send the strategy control instructions to the PLC control platform through the standard interface protocol to drive the system components of the secondary water supply pumping station to perform adaptive adjustment.

[0016] Preferably, a method for remote operation and maintenance of a secondary water supply pumping station based on the Internet of Things includes the following steps: Step 1: Collect water supply-related data from the secondary water supply pumping station in real time and construct a water supply-related data set S; Step 2: Based on the water supply-related data set S, obtain the disturbance residual factor Dk to determine the water supply status of the secondary water supply pumping station and trigger the misalignment feature analysis module to identify the misalignment sliding sampling window. Step 3: Based on the water supply-related data set S, perform feature extraction to obtain the feature data set, mark the candidate segments for water hammer triggering, and construct the candidate time segment set G; Step 4: Based on the candidate time interval set G, construct a time interval sequence and perform autocorrelation analysis to obtain the periodic fluctuation risk index Fx, so as to assess the risk level of the micro water hammer phenomenon. Step 5: When the risk level of micro-water hammer phenomenon is the third risk level, use the disturbance countermeasure library to generate strategy adjustment parameters and carry out adaptive adjustment of the secondary water supply pumping station.

[0017] This invention provides a remote operation and maintenance method and system for secondary water supply pumping stations based on the Internet of Things, which has the following beneficial effects: (1) By constructing the “misaligned coherence coefficient Ck” and cooperating with the disturbance residual factor Dk, the response behavior of the “electric control-load-hydraulic” three sides in the sliding sampling window is collaboratively judged. This can identify the “micro water hammer” phenomenon that is difficult to detect by conventional technical means, significantly improve the system’s monitoring sensitivity to structural disturbance chains, effectively avoid the control lag problem caused by missed judgment or misjudgment, and realize early perception and accurate locking of water hammer risk of secondary water supply pumping station.

[0018] (2) By constructing a set of candidate time intervals G and introducing the autocorrelation analysis method of time interval series, an evaluation mechanism for the periodic fluctuation risk index Fx was established. This mechanism can accurately quantify the periodicity and regularity of water hammer behavior, distinguish between occasional disturbances and structural periodic risks. This mechanism not only improves the scientific nature of risk level judgment, but also provides a basis for the graded response of control strategies, and enhances the intelligent decision-making level of the system.

[0019] (3) By setting up a disturbance countermeasure library and a linkage mechanism with the PLC control interface, when the risk level of micro water hammer phenomenon is determined to be level three, adjustment strategy parameters can be automatically generated and issued to realize dynamic optimization of key operating parameters such as start-stop rhythm and valve response sequence. The adjustment process has closed-loop feedback capability and can continuously correct the adjustment logic according to the actual system operating status, thereby effectively suppressing water hammer causes, extending equipment life, and improving system operation safety and energy efficiency. Attached Figure Description

[0020] Figure 1 This is a block diagram of a remote operation and maintenance system for a secondary water supply pumping station based on the Internet of Things according to the present invention. Figure 2 This is a schematic diagram of the process of a remote operation and maintenance system for a secondary water supply pumping station based on the Internet of Things according to the present invention. Figure 3 This is a schematic diagram of the process for obtaining the candidate time segment set G in this invention; Figure 4 The autocorrelation function of this invention With lag step size A trend chart showing the changes. Detailed Implementation

[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] Example 1 Please see Figure 1 This invention provides a remote operation and maintenance system for secondary water supply pumping stations based on the Internet of Things, including a multi-dimensional data acquisition module, a local disturbance analysis module, a misalignment feature analysis module, a risk assessment module, and an adaptive adjustment module; The multi-dimensional data acquisition module is used to collect water supply-related data from the secondary water supply pumping station in real time and construct a water supply-related data set S; The local disturbance analysis module is used to obtain the disturbance residual factor Dk based on the water supply related data set S, in order to determine the water supply status of the secondary water supply pumping station, and to trigger the misalignment feature analysis module to identify the misalignment sliding sampling window. The misalignment feature analysis module is used to extract features based on the water supply-related data set S to obtain a feature data set, mark water hammer triggering candidate segments, and construct a candidate time segment set G; The risk assessment module is used to construct a time interval sequence based on the candidate time interval set G, and perform autocorrelation analysis to obtain the periodic fluctuation risk index Fx in order to assess the risk level of micro water hammer phenomenon. The adaptive adjustment module is used to generate strategy adjustment parameters from the disturbance countermeasure library when the risk level of micro water hammer phenomenon is the third risk level, and to perform adaptive adjustment of the secondary water supply pumping station.

[0023] In this embodiment, a five-level closed-loop mechanism of "collection-analysis-identification-evaluation-adjustment" effectively solves the problem of difficulty in identifying, evaluating, and intervening in "micro water hammer" in the prior art. The system uses multi-dimensional signal analysis to analyze the water supply status and combines the disturbance residual factor Dk and the misalignment coherence coefficient Ck to identify the dynamic coupling misalignment behavior of electrical control, load, and hydraulic response. Furthermore, it extracts periodic disturbance characteristics through autocorrelation analysis of time interval sequences and constructs a periodic fluctuation risk index Fx, which solves the problem that micro water hammer behavior is difficult to archive in time and difficult to quantify in period. After the periodic fluctuation risk index Fx reaches the third risk level, the adaptive adjustment module outputs control commands in conjunction with the disturbance countermeasure library, and links the main control system to perform precise intervention and correction, realizing automatic identification and closed-loop adjustment of structural water hammer risk, significantly improving the operational stability of the pumping station and the intelligent response capability of the control system.

[0024] Example 2 Please refer to Figure 1 and Figure 3 Specifically: The multi-dimensional data acquisition module is used to set up data acquisition nodes in the secondary water supply pumping station, and to install intelligent sensor groups on the data acquisition nodes. A multi-channel high-precision synchronous ADC interface board is used to connect each sensor, and a sliding sampling window is set. ], and in the sliding sampling window [ The system collects water supply-related data from secondary water supply pumping stations to obtain water supply-related data from several sliding sampling windows, and constructs a water supply-related data set S. This water supply-related data includes current signals I... Voltage signal U Input power at the motor end and the mechanical impedance M at the load end ; Current signal I Acquired via a Hall current sensor; voltage signal U Obtained through a strain gauge pressure sensor; Input power at the motor end Obtained through a multi-functional energy meter; Mechanical resistance M at the load end Obtained via a torque sensor; In the sliding sampling window [ ]Inside, Indicates the start time point of the sliding sampling window. Indicates the end time point of the sliding sampling window. Indicates the duration of the sliding sampling window; For the acquired current signal I and voltage signal U Using Fast Fourier Transform to identify the dominant frequency point and the collected current signal I and voltage signal U The frequency spectrum is transformed into a complex spectrum in the frequency domain through DFT transformation, and the dominant frequency point is obtained from the complex spectrum in the frequency domain. The complex spectrum value is used to calculate the phase difference between the current and voltage signals, and further obtain the phase synchronization factor Tb. The specific method for obtaining the phase synchronization factor Tb is as follows: ; In the formula, This indicates the voltage signal at the dominant frequency point. Complex spectral values ​​on This indicates the current signal at the dominant frequency point. Complex spectral values ​​on Indicates the dominant frequency point. Represents a complex phase angle function. This represents the phase angle of the voltage signal at the dominant frequency. denoted by , cos represents the phase angle of the current signal at the main frequency point, and cos represents the cosine function.

[0025] Complex phase angle function The phase angle used to extract the negative complex spectral value of a signal in the frequency domain; The phase synchronization factor Tb represents the voltage signal and the current signal at the dominant frequency point. The phase difference cosine value is used to determine the phase difference between voltage and current signals when the system experiences disturbances, abnormal loads, or nonlinear responses. If Tb is close to 1, it indicates that the voltage and current are in phase, the system is operating stably, and the load changes linearly. If Tb approaches 0, it indicates that the phase asynchrony between voltage and current is higher, and the system is more likely to have structural, electrical, or hydraulic abnormalities. The phase synchronization factor Tb can be used to judge the pump's working efficiency and power factor trend. At the main frequency point, it is highly correlated with the instantaneous power factor and participates in the calculation of the instantaneous load divergence index Fk, reflecting whether the system coupling state is coordinated and whether the operating state is stable. Here, DFT refers to Discrete Fourier Transform, a mathematical method for converting discrete-time signals from the time domain to the frequency domain. It is used to extract the complex spectrum values ​​of frequency points, by transforming the current signal I... and voltage signal U By transforming the data using the DFT, the data is converted into a complex spectrum in the frequency domain, allowing us to obtain the complex spectral values ​​at each discrete frequency point. The complex spectrum in the frequency domain refers to a dataset containing the complex spectral values ​​at all discrete frequency points.

[0026] In this embodiment, by deploying multi-dimensional data acquisition nodes at the secondary water supply pumping station and integrating high-precision synchronous ADCs and intelligent sensor groups, high-frequency and high-synchronous-precision sampling of pumping station operating parameters is achieved, providing a basic guarantee for subsequent feature extraction and risk identification. By real-time acquisition of key signals such as pump current, voltage, input power, and mechanical resistance, and combined with fast Fourier transform and DFT frequency domain analysis methods, the phase difference between electrical and power characteristics is accurately identified, thereby constructing a "phase synchronization factor Tb". This effectively captures the weak phase misalignment characteristics between control, load, and hydraulic pressure, and constructs a water supply data set S, providing a stable data foundation for subsequent disturbance identification and misalignment assessment. Overall, this improves the ability to perceive early abnormal signs of "micro water hammer", helps to break the blind zone limitation of water hammer cycle in traditional monitoring methods, and enhances the system's early perception and response capability to micro-disturbance dynamics.

[0027] Example 3 Please refer to Figure 1 Specifically: the local disturbance analysis module includes a pressure trajectory fitting unit and a residual disturbance identification unit; The pressure trajectory fitting unit is used based on the sliding sampling window. Voltage signal U acquired within and main frequency Construct a periodic fitting pressure curve Among them, the periodically fitted pressure curve The specific manifestations are as follows: ; In the formula, This represents the constant term, namely the mean pressure value. This represents the amplitude coefficient of the nth harmonic. Indicates the main frequency point The corresponding dominant angular frequency, , where n represents the harmonic order index. This represents the phase shift angle of the nth harmonic. The total harmonic order is represented by t, and the sliding sampling window is represented by t. The time variable within ], t∈[ ].

[0028] The reconstructed term representing the periodic perturbation component of the pressure signal is defined within the sliding sampling window. ], use A series of sinusoidal waves of different frequencies, i.e., the dominant frequency and its harmonics, are used to fit the voltage signal U. The part related to cyclical fluctuations; Total Harmonic Order The amplitude coefficient of the nth harmonic is set by the customer based on historical experience. By adjusting the sliding sampling window [ The voltage signal within [ ] is subjected to Fast Fourier Transform (FFT) to extract the amplitude spectrum components at the dominant frequency and its harmonic frequencies, and the amplitude value corresponding to the nth harmonic frequency is used as the amplitude coefficient. Obtain; Among them, the constant term By adjusting the sliding sampling window [ Voltage signal U within ] Obtain the arithmetic mean by performing calculation. Amplitude coefficient of the nth harmonic Used to reflect the amplitude intensity of the nth harmonic in pressure fluctuations. The larger the value, the higher the energy percentage of that frequency component; Phase shift angle of the nth harmonic This refers to the time offset of the nth harmonic relative to the fundamental frequency. It is a key phase factor that affects the waveform trend and is obtained through FFT identification. Harmonics refer to the integer multiples of frequencies in a periodic signal, excluding the dominant frequency. The harmonic order n refers to the ratio of a certain harmonic to the fundamental frequency. Periodic fitting pressure curve Within a sliding sampling window, a periodic estimation curve is constructed based on the dominant frequency and combined with the superposition of multiple harmonics. This curve is primarily used to construct an approximate model of the actual pressure signal, serving as a baseline for disturbance identification. It effectively isolates structural fluctuations and non-periodic interference, laying the foundation for subsequent calculation of the residual disturbance factor Dk. This fitting method has the advantages of strong interpretability and strong energy concentration description ability, significantly improving the robustness and accuracy of perturbation identification. In a specific example, such as in a secondary water supply system, pressure sensors continuously collect pressure signals from the pump output. Due to periodic changes in motor speed, network load disturbances, and users' rhythmic water usage behavior, the pressure signal often contains multiple harmonics and fluctuation components. In this case, constructing a periodic fitting pressure curve is crucial. It can determine whether there are periodic pressure fluctuations in the water pump system and periodically fit the pressure curve. Removing noise components such as electromagnetic interference and transient changes facilitates the subsequent calculation of the disturbance residual factor Dk.

[0029] The residual disturbance identification unit is used to fit the pressure curve based on the period. and voltage signal U By comparing and analyzing the residual energy density per unit time, the perturbation residual factor Dk is obtained. The specific method for obtaining the perturbation residual factor Dk is as follows: ; In the formula, This represents the pressure value at time point t. This represents the pressure value at time point t in the periodically fitted pressure curve. Indicates the sliding sampling window [ The duration of the duration; The disturbance residual factor Dk is a quantitative indicator used to represent the degree of difference between the water supply pressure signal and its periodic fitting curve. It reflects the degree of deviation between the actual operating state of the water supply system and the ideal periodic fluctuation state per unit time. It can effectively identify abnormal pressure deviations in the water supply system caused by water hammer disturbances, mechanical feedback misalignment or other minor disturbances. It provides key basis for subsequent water hammer triggering judgment, structural misalignment identification and risk level assessment, and improves the system's perception accuracy and diagnostic capability for the latent behavior of "micro water hammer". A preset residual judgment threshold Pd is established, and the residual judgment threshold Pd and the disturbance residual factor Dk are compared and analyzed to evaluate the water supply status of the secondary water supply pumping station. The specific evaluation content is as follows: If the disturbance residual factor Dk is less than or equal to the residual judgment threshold Pd, i.e. Dk≤Pd, then the water supply status of the secondary water supply pump station is determined to be normal. The secondary water supply pump system can maintain stability through self-regulation and does not pose a threat to system safety and water supply stability. At this time, the current operation strategy is maintained and water supply-related data are continuously monitored. If the disturbance residual factor Dk > the residual judgment threshold Pd, that is, Dk > Pd, then the water supply state of the secondary water supply pump station is determined to be a structural disturbance state. The secondary water supply pump system is difficult to maintain stability through self-adjustment and has exceeded the system self-balancing capability boundary. At this time, the misalignment feature analysis module is immediately triggered to perform structural fault analysis.

[0030] In this embodiment, a periodically fitted pressure curve is constructed. With voltage signal U By comparing the data, the system can effectively identify minute and non-abrupt disturbances in the water supply system. Using frequency domain dominant frequency extraction and harmonic reconstruction methods, a periodic theoretical pressure model is dynamically constructed. The disturbance intensity is evaluated by combining the residual energy density per unit time, thereby obtaining the disturbance residual factor Dk and performing quantitative analysis. This mechanism improves the sensitivity to early characteristics of structural disturbances. By setting the residual judgment threshold Pd, the system can automatically distinguish between micro-disturbances and structural anomalies, thereby enabling early warning of abnormal water supply conditions. This provides accurate and controllable triggering conditions for subsequent misalignment analysis and risk identification, and significantly enhances the system's intelligent response and forward-looking regulation.

[0031] Example 4 Please refer to Figure 1 and Figure 3 Specifically: the misalignment feature analysis module includes a feature extraction unit and a misalignment evaluation unit; The feature extraction unit is used to extract features based on the water supply-related data set S, and to construct a feature data set H based on the extracted feature indicators; The maximum instantaneous rate of change of the sum of current and torque response is quantified to obtain the instantaneous load divergence index Fk. The specific method for obtaining the instantaneous load divergence index Fk is as follows: ; In the formula, This represents the input power at the motor terminals at time point t. This represents the mechanical impedance at the load end at time point t. Indicates the gain coefficient. Represents the phase synchronization factor. This indicates the phase synchronization factor of the equipment under rated conditions. Indicates the sliding sampling window The maximum derivative value within; in, This represents the phase synchronization offset correction term, which measures the deviation between the phase synchronization capability of the system in the current state and the synchronization reference in the rated state, thereby realizing the dynamic amplification or suppression correction of the impact of load disturbances. Gain coefficient It is a modulation parameter used to establish a dimensional mapping relationship between different physical quantities, used to map mechanical impedance to the input power at the motor end. Comparable equivalent power perturbation forms, gain coefficient The specific values ​​were obtained through experimental calibration. This involved applying load disturbances of varying amplitudes to the equipment under steady-state load conditions, simultaneously recording changes in input power and load impedance, and constructing a disturbance response sample set. Subsequently, the least squares method was used to fit the linear relationship between the disturbance pairs, and the gain coefficient was extracted. ; Phase synchronization factor of the equipment under rated conditions Acquired through calibration during equipment commissioning and factory inspection; The instantaneous load divergence index Fk is used to quantify the degree of coupling consistency between the electric control drive side (motor input power) and the execution load side (pump torque response) of a secondary water supply pump station within a sliding sampling window. Specifically, it reflects the degree of uncoordinated motion or short-term power imbalance that occurs during the operation of the water supply pump set. It comprehensively considers the dynamic difference between energy input and mechanical resistance under real-time operating conditions, combined with the offset of the phase synchronization factor, to extract the mechanical divergence characteristics existing in the transient disturbance process of the water supply system. In specific examples, such as in high-load mechanical systems driven by variable frequency motors, like water pump systems, sudden changes in mechanical load, acceleration and deceleration, and impact vibrations can all cause drastic changes in motor power response. If the response is not timely, phenomena such as loss of synchronization, mechanical fatigue, and system shutdown may occur. At this time, the instantaneous load divergence index Fk can identify the peak value of the coordinated fluctuation of power and mechanical resistance through the maximum derivative rate, quantify the dynamic impact intensity that the system is subjected to, and determine whether the current system is facing a high-risk load impact.

[0032] Calculate the degree of deviation of pressure fluctuation within the current sliding sampling window to obtain the pressure stability residual factor Rk. The specific method for obtaining the pressure stability residual factor Rk is as follows: ; In the formula, This represents the pressure value at time point t. This represents the average pressure value across several sampling time points within the sliding sampling window. This represents the standard deviation of pressure within the sliding sampling window.

[0033] The pressure stability residual factor Rk represents the degree to which pressure fluctuations deviate from the pressure mean within the sliding sampling window. It is used to reveal whether local disturbances have exceeded the structural response capability of the pressure regulating system. In the operation of secondary water supply pumping stations, peak water usage periods and water hammer disturbances can both cause pressure increases. However, traditional monitoring methods are generally based on instantaneous pressure values, which can easily misjudge micro water hammer as normal pressure fluctuations, making it difficult to identify micro water hammer phenomena.

[0034] The misalignment evaluation unit is used to perform a summary calculation for each sliding sampling window based on the feature data set H to obtain the misalignment coherence coefficient Ck. The specific method for obtaining the misalignment coherence coefficient Ck is as follows: ; In the formula, Indicates the instantaneous load divergence index. This represents the pressure-stabilized residual factor. Indicates a stress-inhibiting regulatory factor. Indicates the phase difference of the main frequency. This represents the phase lag suppression coefficient, and e represents the base of the natural logarithm, which is a commonly used constant in mathematics, e≈2.71828...; This represents the pressure steady-state compensation term, used to determine whether pressure fluctuations within the sliding sampling window deviate from the pressure equilibrium state. A large value indicates a drastic fluctuation in water pressure; This represents the phase synchronization suppression term, used to measure the synchronicity of the control system response. If there is a significant phase difference between the voltage and current signals, it indicates a command response delay or regulation chain misalignment. If the value is approximately 0, it indicates that the electric drive response and the control input are consistent. A value greater than 0 indicates voltage control misalignment. Among them, pressure inhibition regulatory factors It is a nonlinear gain adjustment index used to amplify or compress the effect of the pressure stabilization residual factor Rk on the misalignment coherence coefficient Ck, and a pressure suppression control factor. The specific values ​​are obtained through an empirical initialization method and are used in the motor-hydraulic coupling system; Phase lag suppression coefficient It is the reliability adjustment coefficient of the electronic control-execution response chain coupling, used to measure the reliability of synchronization between voltage and current, and the phase hysteresis suppression coefficient. The specific values ​​were set by experts based on historical experience; In existing technologies, although secondary water supply pumping stations are monitored through pressure sensors, motor feedback, and PLC control, when low-amplitude and short-duration water hammer disturbances, i.e., "micro-water hammers," occur, the various modules of the system, including pressure monitoring, electrical control feedback, and mechanical response, still operate independently, lacking a unified evaluation logic. This makes it difficult to determine whether there is a misalignment between control, execution, and fluid response in the secondary water supply pumping station system, and it is difficult to identify the misalignment relationship between fluid disturbances and control behavior. The lack of a unified, multi-source fusion identification mechanism leads to the failure to track the key response chain after micro-water hammers are triggered, resulting in hidden structural damage and inducing misjudgments and delayed control. However, using the misalignment coherence coefficient Ck can solve the problems of difficulty in identifying dynamic misalignment states across dimensions, difficulty in calibrating water hammer occurrence nodes, and misjudgment of disturbance causes in traditional systems. It is a key supporting indicator for building an intelligent micro-disturbance monitoring and control mechanism, ensuring the coordination and predictability between the pumping station system's operating logic and physical response. Set a misalignment threshold Ckyz, and for each sliding sampling window, compare the misalignment coherence coefficient Ck of the sliding sampling window with the misalignment threshold Ckyz. If the misalignment coherence coefficient Ck is greater than or equal to the misalignment threshold Ckyz, it is determined that dynamic coupling misalignment behavior of the three sides of the electronic control, load and hydraulic system has occurred in the sliding sampling window. At this time, the sliding sampling window is marked as a water hammer trigger candidate window. If the misalignment coherence coefficient Ck is less than the misalignment threshold Ckyz, it is determined that dynamic coupling misalignment behavior of the three sides of the electronic control, load and hydraulic system has not occurred in the sliding sampling window, and no processing is required. The set of all judgment results is a sliding sampling window of the water hammer triggering candidate window. The center time point of each water hammer triggering candidate window is extracted to construct the candidate time segment set G.

[0035] In this embodiment, by fusing three-dimensional information of motor input power, load mechanical resistance, and pressure change, an "instantaneous load divergence index Fk" and a "pressure stability residual factor Rk" are constructed. Then, the "misalignment coherence coefficient Ck" is used to evaluate the dynamic matching status of the pump station on the electrical control, load, and hydraulic sides during operation. This can effectively identify whether misalignment coupling behavior exists within the sliding sampling window, thereby achieving accurate marking of the precursor behavior of "micro water hammer". Compared with existing methods that rely on single water pressure or current changes for early warning, this significantly improves the ability to perceive low-amplitude, short-time lag disturbances, effectively solving the problem of "micro water hammer" being difficult to detect. This provides a basic support for subsequent water hammer periodic reconstruction and risk classification judgment, and comprehensively improves the identification accuracy and response timeliness of the water hammer triggering chain.

[0036] Example 5 Please refer to Figure 1 and Figure 4 Specifically: the risk assessment module includes an autocorrelation analysis unit and a risk determination unit; The autocorrelation analysis unit is used to calculate the time interval between the center time points of each adjacent water hammer triggering candidate window based on the candidate time interval set G, in order to construct a time interval sequence. Based on this time interval sequence, autocorrelation analysis is performed to construct an autocorrelation function, which is specifically expressed as follows: ; In the formula, Indicates the lag step size as The autocorrelation function value at time, This represents the k-th time interval in the time interval sequence. Indicates the average of time intervals. Indicates the lag step size. Indicates the first There are 1 time intervals, where n represents the total number of time intervals; For autocorrelation function Calculate each lag step size Extract the autocorrelation function value, and then extract the maximum autocorrelation function value. And record the maximum autocorrelation function value. Corresponding lag step size ,in, =1, 2, 3, ..., n- , where n- Indicates the lag step size The upper limit calculation range, This indicates the minimum set hysteresis step size; In the formula, This indicates how much the fluctuation in the k-th time interval deviates from the mean. It means that it has passed. The product of the time intervals after each step is positive and negative or both are negative, indicating a positive trend. If one is positive and the other is negative, the trend is opposite. By continuously accumulating such products, it is possible to identify how much the time interval sequence is being shifted. After the next step, will there still be a similar pattern to the original one? The larger the value, the stronger the periodic reproducibility of the disturbance interval, the higher the probability of the micro water hammer phenomenon, and the greater the risk. Autocorrelation analysis is a statistical method used to determine the degree of similarity between a signal or sequence and its "self" at different time intervals, i.e., at "lag". If a system's events recur, such as the micro water hammer phenomenon, it will show high autocorrelation at a certain lag step, thus determining whether the micro water hammer phenomenon has "periodic fluctuations".

[0037] The risk assessment unit is used to set the maximum autocorrelation function value. Let Fx be the cyclical volatility risk index, and let the first cyclical volatility risk threshold be preset. Second-cycle volatility risk threshold The cyclical volatility risk index Fx is compared with the first cyclical volatility risk threshold. Second-cycle volatility risk threshold A comparative analysis was conducted to assess the risk level of micro-water hammer phenomena. The specific assessment content is as follows: If the cyclical volatility risk index Fx is less than or equal to the first cyclical volatility risk threshold That is, Fx≤ If the risk level of the micro water hammer phenomenon is determined to be the first risk level, then the time interval has no stable repeating characteristics and is determined to be a micro-occasional disturbance, not dominated by water hammer. If the cyclical volatility risk index Fx is greater than the first cyclical volatility risk threshold And less than the second cycle volatility risk threshold ,Right now <Fx< If the risk level of the micro water hammer phenomenon is determined to be the second risk level, then there is a potential water hammer hazard in the secondary water supply pumping station. The valve should be shut off with a delayed start and the start rate should be adjusted to 80% of the standard start rate. If the cyclical volatility risk index Fx is greater than or equal to the second cyclical volatility risk threshold That is, Fx≥ If the risk level of the micro water hammer phenomenon is determined to be the third risk level, then the secondary water supply pumping station has a structural water hammer risk, the disturbance period is significant, triggering the main control system of the secondary water supply pumping station to perform adaptive adjustment of the secondary water supply pumping station.

[0038] In this embodiment, by setting up an autocorrelation analysis unit and a risk judgment unit, the periodic risk of micro water hammer phenomena can be accurately identified and quantified. The core lies in constructing a time interval sequence and performing autocorrelation analysis, and then calculating the periodic fluctuation risk index Fx to reflect the periodic recurrence capability of the disturbance. This breaks through the limitations of traditional methods that rely on pressure or electrical signal anomalies for identification. It can identify the low-amplitude, high-repetition disturbance pattern generated by "micro water hammer". With the help of a dual threshold mechanism, differentiated response strategies can be triggered under different risk levels, realizing a step-by-step control link from potential hazard identification to structural water hammer early warning. This significantly improves the system's monitoring sensitivity and proactive response to micro-periodic disturbances, effectively fills the identification gap of the "water hammer period blind zone", and ensures the safe operation and structural stability of the pumping station.

[0039] Example 6 Please refer to Figure 1Specifically: When the risk level of micro water hammer phenomenon is the third risk level, the adaptive adjustment module automatically generates strategy adjustment parameters based on the disturbance countermeasure library in the secondary water supply pumping station, packages the strategy adjustment parameters into strategy control instructions, and sends the strategy control instructions to the PLC control platform through the standard interface protocol to drive the system components of the secondary water supply pumping station to perform adaptive adjustment.

[0040] Among them, the disturbance countermeasure library refers to a set of preset control strategy combinations embedded in the system for different water hammer risk levels, periodic characteristics and disturbance patterns, which generate strategy adjustment parameters by calling predefined control strategy templates or rules.

[0041] A PLC platform refers to an automation control platform with a programmable logic controller as its core. It is widely used in industrial control systems for real-time monitoring and logic control of industrial components such as machinery, motors, pumps, and valves.

[0042] In this embodiment, by introducing a disturbance countermeasure library, the system can quickly link system components to execute targeted response control strategies after identifying structural micro-water hammer risks. Compared with traditional static control logic, the system dynamically calls preset control templates based on the risk level of periodic fluctuations to generate strategy adjustment parameters that match the current disturbance characteristics. This greatly improves the system's sensitivity to water hammer disturbances and its responsiveness. The strategy adjustment parameters are also encapsulated into standardized instructions in real time and sent to the PLC platform, realizing adaptive operation and adjustment of the closed-loop control chain and improving the overall operational safety and intelligence level of the pumping station.

[0043] Example 7 Please refer to Figure 2 Specifically, a method for remote operation and maintenance of a secondary water supply pumping station based on the Internet of Things includes the following steps: Step 1: Collect water supply-related data from the secondary water supply pumping station in real time and construct a water supply-related data set S; Step 2: Based on the water supply-related data set S, obtain the disturbance residual factor Dk to determine the water supply status of the secondary water supply pumping station and trigger the misalignment feature analysis module to identify the misalignment sliding sampling window. Step 3: Based on the water supply-related data set S, perform feature extraction to obtain the feature data set, mark the candidate segments for water hammer triggering, and construct the candidate time segment set G; Step 4: Based on the candidate time interval set G, construct a time interval sequence and perform autocorrelation analysis to obtain the periodic fluctuation risk index Fx, so as to assess the risk level of the micro water hammer phenomenon. Step 5: When the risk level of micro-water hammer phenomenon is the third risk level, use the disturbance countermeasure library to generate strategy adjustment parameters and carry out adaptive adjustment of the secondary water supply pumping station.

[0044] In this embodiment, by collecting water supply-related data, a disturbance residual factor Dk and a misalignment characteristic index are constructed to accurately identify the latent disturbance of "micro-water hammer". This makes up for the problem of traditional methods missing short-term and low-amplitude misalignment behavior. Furthermore, by using autocorrelation analysis of time interval sequences, periodic risk fluctuations are quantified to solve the technical shortcoming of the difficulty in identifying the blind zone of water hammer cycle. Finally, in conjunction with the disturbance countermeasure library, adjustment strategies are generated in real time and distributed to the main control system to achieve closed-loop control and adaptive correction of structural water hammer risk, effectively improving the system's steady-state operation capability and adjustment response time.

[0045] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A remote operation and maintenance system for secondary water supply pumping stations based on the Internet of Things, characterized in that: It includes a multi-dimensional data acquisition module, a local disturbance analysis module, a misalignment feature analysis module, a risk assessment module, and an adaptive adjustment module; The multidimensional data acquisition module is used to collect water supply-related data from the secondary water supply pumping station in real time and construct a water supply-related data set S; The local disturbance analysis module is used to obtain the disturbance residual factor Dk based on the water supply related data set S, in order to determine the water supply status of the secondary water supply pumping station, and trigger the misalignment feature analysis module to identify the misalignment sliding sampling window; The misalignment feature analysis module is used to extract features based on the water supply-related data set S to obtain a feature data set, mark water hammer triggering candidate segments, and construct a candidate time segment set G; The risk assessment module is used to construct a time interval sequence based on the candidate time interval set G, and perform autocorrelation analysis to obtain the periodic fluctuation risk index Fx in order to assess the risk level of micro water hammer phenomenon. The adaptive adjustment module is used to generate strategy adjustment parameters from the disturbance countermeasure library to perform adaptive adjustment of the secondary water supply pumping station when the risk level of micro water hammer phenomenon is the third risk level.

2. The remote operation and maintenance system for a secondary water supply pumping station based on the Internet of Things as described in claim 1, characterized in that: The multi-dimensional data acquisition module is used to set up data acquisition nodes in the secondary water supply pumping station, and to install intelligent sensor groups on the data acquisition nodes. A multi-channel high-precision synchronous ADC interface board is used to connect each sensor, and a sliding sampling window is set. ], and in the sliding sampling window [ The system collects water supply-related data from secondary water supply pumping stations to obtain water supply-related data from several sliding sampling windows, and constructs a water supply-related data set S, which includes current signals I. Voltage signal U Input power at the motor end and the mechanical impedance M at the load end ; For the acquired current signal I and voltage signal U Using Fast Fourier Transform to identify the dominant frequency point and the collected current signal I and voltage signal U The frequency spectrum is transformed into a complex spectrum in the frequency domain through DFT transformation, and the dominant frequency point is obtained from the complex spectrum in the frequency domain. The complex spectrum value is used to calculate the phase difference between the current and voltage signals, and further obtain the phase synchronization factor Tb. The specific method for obtaining the phase synchronization factor Tb is as follows: ； In the formula, This indicates the voltage signal at the dominant frequency point. Complex spectral values ​​on This indicates the current signal at the dominant frequency point. Complex spectral values ​​on Indicates the dominant frequency point. Represents a complex phase angle function. This represents the phase angle of the voltage signal at the dominant frequency. denoted by , cos represents the phase angle of the current signal at the main frequency point, and cos represents the cosine function.

3. The remote operation and maintenance system for a secondary water supply pumping station based on the Internet of Things as described in claim 2, characterized in that: The local disturbance analysis module includes a pressure trajectory fitting unit and a residual disturbance identification unit; The pressure trajectory fitting unit is used based on the sliding sampling window. Voltage signal U acquired within and main frequency Construct a periodic fitting pressure curve Among them, the periodically fitted pressure curve The specific manifestations are as follows: ； In the formula, This represents the constant term, which is the average pressure value of the fitted pressure trajectory curve. This represents the amplitude coefficient of the nth harmonic. Indicates the main frequency point The corresponding dominant angular frequency, , where n represents the harmonic order index. This represents the phase shift angle of the nth harmonic. The total harmonic order is represented by t, and the sliding sampling window is represented by t. The time variable within ], t∈[ ].

4. The remote operation and maintenance system for a secondary water supply pumping station based on the Internet of Things as described in claim 3, characterized in that: The residual disturbance identification unit is used to fit the pressure curve based on the period. and voltage signal U By comparing and analyzing the residual energy density per unit time, the perturbation residual factor Dk is obtained. The specific method for obtaining the perturbation residual factor Dk is as follows: ； In the formula, This represents the pressure value at time point t. This represents the pressure value at time point t in the periodically fitted pressure curve. Indicates the sliding sampling window [ The duration of the [unclear]; A preset residual judgment threshold Pd is established, and the residual judgment threshold Pd and the disturbance residual factor Dk are compared and analyzed to evaluate the water supply status of the secondary water supply pumping station. The specific evaluation content is as follows: If the disturbance residual factor Dk is less than or equal to the residual judgment threshold Pd, i.e., Dk≤Pd, then the water supply status of the secondary water supply pumping station is determined to be normal. At this time, the current operation strategy is maintained and water supply-related data is continuously monitored. If the disturbance residual factor Dk > the residual judgment threshold Pd, that is, Dk > Pd, then the water supply state of the secondary water supply pumping station is determined to be a structural disturbance state. At this time, the misalignment feature analysis module is immediately triggered to perform structural fault analysis.

5. The remote operation and maintenance system for a secondary water supply pumping station based on the Internet of Things as described in claim 4, characterized in that: The misalignment feature analysis module includes a feature extraction unit and a misalignment evaluation unit; The feature extraction unit is used to extract features based on the water supply-related data set S, and to construct a feature data set H based on the extracted feature indicators; The maximum instantaneous rate of change of the sum of current and torque response is quantified to obtain the instantaneous load divergence index Fk. The specific method for obtaining the instantaneous load divergence index Fk is as follows: ； In the formula, This represents the input power at the motor terminals at time point t. This represents the mechanical impedance at the load end at time point t. Indicates the gain coefficient. Represents the phase synchronization factor. This indicates the phase synchronization factor of the equipment under rated conditions. Indicates the sliding sampling window The maximum derivative value within; Calculate the degree of deviation of pressure fluctuation within the current sliding sampling window to obtain the pressure stability residual factor Rk. The specific method for obtaining the pressure stability residual factor Rk is as follows: ； In the formula, This represents the pressure value at time point t. This represents the average pressure value across several sampling time points within the sliding sampling window. This represents the standard deviation of pressure within the sliding sampling window.

6. The remote operation and maintenance system for a secondary water supply pumping station based on the Internet of Things as described in claim 5, characterized in that: The misalignment evaluation unit is used to perform a summary calculation for each sliding sampling window based on the feature data set H to obtain the misalignment coherence coefficient Ck. The specific method for obtaining the misalignment coherence coefficient Ck is as follows: ； In the formula, Indicates the instantaneous load divergence index. This represents the pressure-stabilized residual factor. Indicates a stress-inhibiting regulatory factor. Indicates the phase difference of the main frequency. This represents the phase lag suppression coefficient, and e represents the base of the natural logarithm. Set a misalignment threshold Ckyz, and for each sliding sampling window, compare the misalignment coherence coefficient Ck of the sliding sampling window with the misalignment threshold Ckyz. If the misalignment coherence coefficient Ck is greater than or equal to the misalignment threshold Ckyz, it is determined that dynamic coupling misalignment behavior of the three sides of the electronic control, load and hydraulic system has occurred in the sliding sampling window. At this time, the sliding sampling window is marked as a water hammer trigger candidate window. If the misalignment coherence coefficient Ck is less than the misalignment threshold Ckyz, it is determined that dynamic coupling misalignment behavior of the three sides of the electronic control, load and hydraulic system has not occurred in the sliding sampling window, and no processing is required. The set of all judgment results is a sliding sampling window of the water hammer triggering candidate window. The center time point of each water hammer triggering candidate window is extracted to construct the candidate time segment set G.

7. A remote operation and maintenance system for a secondary water supply pumping station based on the Internet of Things as described in claim 6, characterized in that: The risk assessment module includes an autocorrelation analysis unit and a risk determination unit; The autocorrelation analysis unit is used to calculate the time interval between the center time points of each adjacent water hammer triggering candidate window based on the candidate time interval set G, in order to construct a time interval sequence. Based on this time interval sequence, autocorrelation analysis is performed to construct an autocorrelation function, which is specifically expressed as follows: ； In the formula, Indicates the lag step size as The autocorrelation function value at time, This represents the k-th time interval in the time interval sequence. Indicates the average of time intervals. Indicates the lag step size. Indicates the first There are 1 time intervals, where n represents the total number of time intervals; For autocorrelation function Calculate each lag step. Extract the autocorrelation function value, and then extract the maximum autocorrelation function value. And record the maximum autocorrelation function value. Corresponding lag step size ,in, =1, 2, 3, ..., n- .

8. The remote operation and maintenance system for a secondary water supply pumping station based on the Internet of Things as described in claim 7, characterized in that: The risk assessment unit is used to set the maximum autocorrelation function value. Let Fx be the cyclical volatility risk index, and let the first cyclical volatility risk threshold be preset. Second-cycle volatility risk threshold The cyclical volatility risk index Fx is compared with the first cyclical volatility risk threshold. Second-cycle volatility risk threshold A comparative analysis was conducted to assess the risk level of micro-water hammer phenomena. The specific assessment content is as follows: If the cyclical volatility risk index Fx is less than or equal to the first cyclical volatility risk threshold That is, Fx≤ If the risk level of the micro water hammer phenomenon is determined to be the first risk level, then the time interval has no stable repeating characteristics and is determined to be a micro-occasional disturbance, not dominated by water hammer. If the cyclical volatility risk index Fx is greater than the first cyclical volatility risk threshold And less than the second cycle volatility risk threshold ,Right now <Fx< If the water hammer phenomenon is detected, the risk level is determined to be the second risk level. At this time, there is a potential water hammer hazard in the secondary water supply pumping station. The valve should be shut off with a delayed start and the start rate should be adjusted to 80% of the standard start rate. If the cyclical volatility risk index Fx is greater than or equal to the second cyclical volatility risk threshold That is, Fx≥ If the risk level of the micro water hammer phenomenon is determined to be the third risk level, then the secondary water supply pumping station has a structural water hammer risk, the disturbance period is significant, triggering the main control system of the secondary water supply pumping station to perform adaptive adjustment of the secondary water supply pumping station.

9. A remote operation and maintenance system for a secondary water supply pumping station based on the Internet of Things as described in claim 8, characterized in that: The adaptive adjustment module is used to automatically generate strategy adjustment parameters based on the disturbance countermeasure library in the secondary water supply pumping station when the risk level of micro water hammer phenomenon is the third risk level. The strategy adjustment parameters are packaged into strategy control instructions and sent to the PLC control platform through the standard interface protocol to drive the system components of the secondary water supply pumping station to perform adaptive adjustment.

10. A method for a remote operation and maintenance system for a secondary water supply pumping station based on the Internet of Things (IoT), used to implement the remote operation and maintenance system for a secondary water supply pumping station based on the IoT as described in any one of claims 1 to 9, characterized in that: Includes the following steps, Step 1: Collect water supply-related data from the secondary water supply pumping station in real time and construct a water supply-related data set S; Step 2: Based on the water supply-related data set S, obtain the disturbance residual factor Dk to determine the water supply status of the secondary water supply pumping station and trigger the misalignment feature analysis module to identify the misalignment sliding sampling window. Step 3: Based on the water supply-related data set S, perform feature extraction to obtain the feature data set, mark the candidate segments for water hammer triggering, and construct the candidate time segment set G; Step 4: Based on the candidate time interval set G, construct a time interval sequence and perform autocorrelation analysis to obtain the periodic fluctuation risk index Fx, so as to assess the risk level of the micro water hammer phenomenon. Step 5: When the risk level of micro-water hammer phenomenon is the third risk level, use the disturbance countermeasure library to generate strategy adjustment parameters and carry out adaptive adjustment of the secondary water supply pumping station.

Images