Intelligent water conveying and distribution device based on multi-parameter optimization and system thereof

Abstract

The invention discloses an intelligent water transmission and distribution device and system based on multi-parameter optimization, and the device comprises a data collection and preprocessing module which is used for collecting the operation data of the intelligent water transmission and distribution device, and executing the preprocessing; the four-dimensional coupling dynamic transmission and distribution modeling module is used for constructing a four-dimensional coupling dynamic transmission and distribution model and executing parameter initialization; the coupling state building module is used for building the relation among water pressure disturbance, mechanical response, aperture adjustment and flow output in the intelligent water conveying and distribution process; the dynamic energy field constraint module is used for establishing an energy field function; the parameter self-adaptive regulation and control module is used for generating a control parameter set; and the steady flow solving module is used for carrying out iterative solving through the four-dimensional coupling dynamic transmission and distribution model to obtain the final aperture adjusting quantity and the outflow quantity. The four-dimensional coupling dynamic transmission and distribution model and the energy field constraint mechanism are constructed based on multi-parameter optimization, low-voltage current stabilization and energy balance control are achieved, and the method has the advantages of being high in precision, self-adaptive and capable of saving energy.

Description

Technical Field

[0001] This invention relates to the field of modern water conservancy and irrigation and fluid automation control, and in particular to an intelligent water conveyance and distribution device and system based on multi-parameter optimization. Background Technology

[0002] Existing water distribution devices mostly use mechanical throttling valves, float valves, or constant flow devices for flow control. Some introduce siphon flow limiting structures to achieve automatic water intake under low pressure conditions. However, these devices generally rely on fixed geometric parameters or single pressure feedback for regulation, making it difficult to achieve dynamic response to instantaneous water pressure fluctuations in complex water supply environments. Traditional steady flow control methods often suffer from unstable flow, lag response, and increased energy loss when faced with changes in water supply pressure, pipeline vibration, and fluctuations in outlet resistance, affecting the overall efficiency and stability of water distribution.

[0003] Meanwhile, existing water transmission and distribution systems lack unified modeling and coordinated control of multiple energy sources such as water pressure potential energy, spring potential energy, and flow deviation energy, making it impossible to establish a precise energy balance relationship. This results in frequent switching between steady-state and disturbance states, insufficient flow regulation accuracy, and especially under low-pressure or non-constant-pressure transmission and distribution conditions, it is impossible to achieve adaptive steady flow regulation and dynamic energy field balance. Summary of the Invention

[0004] One objective of this invention is to propose an intelligent water distribution device and system based on multi-parameter optimization. This invention constructs a four-dimensional coupled dynamic distribution model and energy field constraint mechanism based on multi-parameter optimization to achieve low-pressure stable flow and energy balance control, and has the advantages of high precision, self-adaptation and energy saving.

[0005] To achieve the aforementioned objective, the technical solution of the present invention is as follows: A smart water distribution device based on multi-parameter optimization includes a siphon flow limiting device and an outlet pipe, wherein the outlet pipe is connected to the upper end of the siphon flow limiting device.

[0006] A multi-parameter optimized intelligent water transmission and distribution system based on the aforementioned intelligent water transmission and distribution device includes: The data acquisition and preprocessing module is used to collect the operating data of the intelligent water transmission and distribution device, and perform data preprocessing to generate a standardized set of operating parameters; The four-dimensional coupled dynamic transport and distribution modeling module is used to construct a four-dimensional coupled dynamic transport and distribution model based on a standardized set of operating parameters and to perform parameter initialization. The coupled state construction module is used to establish the relationship between water pressure disturbance, mechanical response, orifice regulation and flow output in the process of intelligent water transmission and distribution, forming a continuous time-series coupled state data sequence; The dynamic energy field constraint module is used to establish a dynamic energy field constraint model based on the coupled state data sequence, and to uniformly describe the water pressure potential energy, spring potential energy and flow deviation energy as an energy field function that changes with time. The parameter adaptive control module is used to calculate the energy fluctuation rate of the energy field function, extract the energy deviation value, and adjust the aperture control parameters, spring preload parameters, and energy weight parameters to form a set of control parameters. The steady flow solution module is used to input the set of control parameters into the four-dimensional coupled dynamic transport and distribution model for iterative solution to obtain the final orifice adjustment amount and outflow rate.

[0007] The solution further involves establishing a dynamic energy field constraint model based on the coupled state data sequence during the intelligent water transmission and distribution process. This model unifies the water pressure potential energy, spring potential energy, and flow deviation energy as time-varying energy field functions. The energy fluctuation rate of the energy field function is calculated, and the energy fluctuation rate is compared with the energy stability range to extract the energy deviation value. Based on the energy deviation value, the aperture control parameters, spring preload parameters, and energy weight parameters are dynamically adjusted to form a set of control parameters, thereby realizing adaptive steady flow regulation based on energy field constraints. The set of control parameters is input into a four-dimensional coupled dynamic transport and distribution model for iterative solution to obtain the final orifice adjustment amount and outflow rate, thereby realizing dynamic steady flow control and energy field balance maintenance under water pressure disturbance.

[0008] The solution further includes: the operating data includes instantaneous water pressure, flow rate, spring deformation and orifice displacement in the pipeline; and the preprocessing includes time synchronization of the acquired data, noise filtering and data standardization.

[0009] The solution further includes the following specific steps for initializing the execution parameters: Extract instantaneous water pressure, flow rate, spring deformation and orifice displacement from the standardized operating parameter set to construct the parameter space of a four-dimensional coupled dynamic transport and distribution model; Initialize each parameter in the four-dimensional coupled dynamic transportation and distribution model to form an initial running state set, which serves as the benchmark input for solving the four-dimensional coupled dynamic transportation and distribution model; Based on the parameter range in the standardized operating parameter set, the parameter boundaries of the four-dimensional coupled dynamic transport and distribution model are limited, and the range of values ​​for instantaneous water pressure, outflow, spring deformation and orifice displacement in the model iteration is constrained. The standardized set of operating parameters is input into the four-dimensional coupled dynamic transportation model. Combined with the initial set of operating states and parameter boundary conditions, the initialization and parameter calibration of the four-dimensional coupled dynamic transportation model are completed.

[0010] The solution further includes the following specific steps for generating the coupled state data sequence: In the process of intelligent water transmission and distribution, instantaneous water pressure, flow rate, spring deformation and orifice displacement are collected in real time according to a unified sampling cycle to construct a continuous time series dataset; Compare adjacent time-series data in a continuous time series dataset to calculate instantaneous water pressure changes, flow rate changes, spring deformation changes, and orifice displacement changes; Calculate the mechanical response value caused by water pressure disturbance based on the correspondence between the instantaneous water pressure change and the spring deformation change; The change in spring deformation is matched with the change in orifice displacement to calculate the orifice adjustment caused by the mechanical response, which is used to characterize the transmission effect of the spring response to the change in orifice geometric opening. The orifice displacement change and the outflow rate change are correlated and calculated to obtain the outflow rate response value caused by orifice adjustment, which is used to describe the real-time impact of orifice geometry change on fluid output. The mechanical response value caused by water pressure disturbance, the orifice adjustment amount caused by mechanical response, and the outflow response value caused by orifice adjustment are integrated in time to form a multi-parameter coupled response set. The multi-parameter coupled response set is sorted and paired according to the sampling time order to form a coupled state data sequence, which is used to reflect the multi-parameter balance characteristics of intelligent water transmission and distribution during the operation cycle.

[0011] The scheme further includes the following specific steps for generating the energy field function: Based on the coupled state data sequence, the dynamic change information of the mechanical response value caused by water pressure disturbance, the orifice adjustment amount caused by mechanical response, and the outflow response value caused by orifice adjustment in each sampling period is extracted and aligned with a unified time index to generate a response input sequence. Based on the response input sequence, the spring potential energy corresponding to the mechanical response value, the water pressure potential energy corresponding to the water pressure disturbance, and the flow deviation energy corresponding to the outflow response value are calculated to form an energy feature set; Based on the energy characteristic set, a dynamic energy field constraint model is established, which uniformly describes the water pressure potential energy, spring potential energy and flow deviation energy as energy field functions that change with time, and constructs a continuous time-series structure of the energy field function with the sampling time as the index.

[0012] The solution further includes: the energy field function is constructed from a sequence of comprehensive energy values, which describes the comprehensive distribution of water pressure potential energy, spring potential energy, and flow deviation energy over a continuous sampling time dimension. Each sampling moment corresponds to the comprehensive energy value of the system. The dynamic energy field constraint model takes the energy field function as its core and achieves dynamic coordination and energy balance control among multiple energy elements by constraining the continuity and balance of the comprehensive energy value in the time series, thereby maintaining the steady flow operation of the intelligent water distribution device.

[0013] The solution further includes the following specific steps for generating the control parameter set: The energy composite value sequence is extracted from the dynamic energy field constraint model, and the energy change sequence is calculated based on the continuous sampling time index. Based on the energy change sequence, the energy change amplitude is extracted, the average change amplitude of the energy change sequence is calculated, and the energy volatility is generated based on the average change amplitude. The energy volatility is compared with the preset upper and lower limits of the energy stability range to calculate the energy deviation value, and the changing trend of the energy deviation value in the time series is recorded to generate an energy deviation feature sequence. The energy deviation correction coefficient is calculated based on the energy deviation characteristic sequence and the average energy change amplitude. The aperture control parameters, spring preload parameters, and energy weight parameters are adjusted based on the energy deviation correction coefficient to generate a set of control parameters.

[0014] The solution further includes the following specific steps for generating the final orifice adjustment amount and outflow rate: After the energy field-constrained steady-flow regulation is completed, the set of control parameters is matched with the energy state parameters; The energy state parameters include water pressure potential energy, spring potential energy, and flow deviation energy; The set of control parameters is input into the dynamic energy field constraint model. Using the energy state parameters as initial conditions, the first time-series solution is performed to obtain the corresponding preliminary aperture adjustment amount and outflow rate. Based on the initial aperture adjustment amount and outflow rate, the energy state parameters are corrected, and an energy field balance judgment is performed. If the total energy deviation is less than or equal to the energy balance threshold, the current energy field is determined to be in balance. If the total energy deviation is greater than the energy balance threshold, the next round of time series solution is executed. After determining that the energy field has reached equilibrium, the final aperture adjustment amount and outflow rate are output.

[0015] The beneficial effects of this invention are: This invention constructs an intelligent water distribution system based on multi-parameter optimization, achieving coupled modeling and dynamic control of multi-dimensional elements such as water pressure disturbance, mechanical response, orifice regulation, and flow output. It overcomes the shortcomings of traditional mechanical throttling and fixed-aperture flow limiting devices, such as slow response, low regulation accuracy, and low energy utilization. By collecting operational data such as instantaneous water pressure, outflow, spring deformation, and orifice displacement, the system establishes a four-dimensional coupled dynamic distribution model. It can capture multi-parameter changes in the system's operating state in real time under non-constant pressure distribution environments, realizing the transformation from single-variable control to multi-parameter collaborative control. This enables the distribution process to have self-learning and self-adaptive capabilities, thereby improving the accuracy and response speed of flow regulation.

[0016] At the energy control level, this invention introduces a dynamic energy field constraint model, which unifies the water pressure potential energy, spring potential energy, and flow deviation energy into a time-continuous energy field function. This enables dynamic monitoring and coordinated correction of the energy state. By comparing the energy fluctuation rate with the stable range, the system can extract the energy deviation in real time and generate correction coefficients. It then adaptively adjusts the orifice control parameters, spring preload parameters, and energy weight parameters to maintain a dynamic balance between the outflow and the energy field. This fundamentally eliminates the disturbance effect of water pressure fluctuations on the flow output. This closed-loop energy mechanism not only effectively reduces flow oscillations caused by mechanical inertia and pressure fluctuations but also improves the device's flow stabilization capability and energy efficiency in low-pressure water supply environments.

[0017] Furthermore, this invention structurally combines a siphon flow limiting device and an outlet pipe to form a closed water intake unit, enabling low-pressure stable flow and balanced water intake without external force, thus reducing system energy consumption and maintenance costs. This is achieved through a multi-layered collaborative mechanism involving energy constraints, parameter adaptation, and time-series solution. Attached Figure Description

[0018] Figure 1 This is a schematic diagram of the intelligent water supply and distribution device based on multi-parameter optimization according to the present invention; Figure 2 This is a schematic diagram of the intelligent water transmission and distribution system based on multi-parameter optimization according to the present invention; Figure 3 This is a schematic diagram of the energy field constraint model of the present invention.

[0019] Attached reference numerals: 1. Siphon flow limiting device; 2. Water outlet pipe. Detailed Implementation

[0020] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, illustrating only the basic structure of the invention, and therefore only show the components relevant to the invention. Example 1:

[0021] refer to Figure 1 A smart water distribution device based on multi-parameter optimization includes a siphon flow limiting device 1 and an outlet pipe 2, wherein the outlet pipe 2 is connected to the upper end of the siphon flow limiting device 1. The outlet pipe 2 is used to discharge the fluid taken out by the siphon flow limiting device 1, so as to realize constant flow output and stable pressure distribution. The siphon flow limiting device 1 and the outlet pipe 2 together constitute a closed water intake unit, which is used to replace the traditional open channel water intake structure, realize multi-point graded water intake under low pressure flow conditions and reduce land occupation. Implementation: 2:

[0022] refer to Figure 2 and Figure 3A smart water distribution system based on multi-parameter optimization, comprising the smart water distribution device based on multi-parameter optimization described in Example 1, wherein the water distribution system includes: The data acquisition and preprocessing module is used to collect the operating data of the intelligent water transmission and distribution device, and perform data preprocessing to generate a standardized set of operating parameters; The four-dimensional coupled dynamic transport and distribution modeling module is used to construct a four-dimensional coupled dynamic transport and distribution model based on a standardized set of operating parameters and to perform parameter initialization. The coupled state construction module is used to establish the relationship between water pressure disturbance, mechanical response, orifice regulation and flow output in the process of intelligent water transmission and distribution, forming a continuous time-series coupled state data sequence; The dynamic energy field constraint module is used to establish a dynamic energy field constraint model based on the coupled state data sequence, and to uniformly describe the water pressure potential energy, spring potential energy and flow deviation energy as an energy field function that changes with time. The parameter adaptive control module is used to calculate the energy fluctuation rate of the energy field function, extract the energy deviation value, and adjust the aperture control parameters, spring preload parameters, and energy weight parameters to form a set of control parameters. The steady flow solution module is used to input the set of control parameters into the four-dimensional coupled dynamic transport and distribution model for iterative solution to obtain the final orifice adjustment amount and outflow rate.

[0023] In the process of intelligent water transmission and distribution, the relationship between water pressure disturbance, mechanical response, orifice regulation and flow output is established to form a continuous time-series coupled state data sequence; based on the coupled state data sequence, a dynamic energy field constraint model is established, and water pressure potential energy, spring potential energy and flow deviation energy are uniformly described as energy field functions that change with time. The energy fluctuation rate of the energy field function is calculated, and the energy fluctuation rate is compared with the energy stability range to extract the energy deviation value. Based on the energy deviation value, the aperture control parameters, spring preload parameters, and energy weight parameters are dynamically adjusted to form a set of control parameters, thereby realizing adaptive steady flow regulation based on energy field constraints. The set of control parameters is input into a four-dimensional coupled dynamic transport and distribution model for iterative solution to obtain the final orifice adjustment amount and outflow rate, thereby realizing dynamic steady flow control and energy field balance maintenance under water pressure disturbance.

[0024] In this embodiment, the operating data includes instantaneous water pressure, flow rate, spring deformation, and orifice displacement within the pipeline. The preprocessing includes time synchronization of the acquired data, noise filtering, and data standardization. Specifically: the instantaneous water pressure represents the change in water pressure within the pipeline per unit time, reflecting real-time fluctuations in the water supply pressure; the flow rate represents the actual fluid volume at the device outlet within the same time interval, measuring instantaneous water supply capacity; the spring deformation represents the axial compression or tension displacement of the spring unit inside the device under water pressure, reflecting the mechanical structure's response to pressure disturbances; and the orifice displacement represents the change in the opening of the outlet orifice under the combined action of water pressure and spring force, characterizing the real-time adjustment state of the outlet channel. These four types of parameters together constitute the operating status parameters of the intelligent water distribution device, comprehensively describing the fluid pressure changes, mechanical response, and orifice adjustment process under non-constant pressure conditions.

[0025] In this embodiment, the execution parameter initialization includes the following specific steps: Instantaneous water pressure, flow rate, spring deformation and orifice displacement are extracted from the standardized operating parameter set to construct the parameter space of a four-dimensional coupled dynamic transmission and distribution model, which is used to describe the multi-parameter coupling state of the intelligent water transmission and distribution device during operation. The four-dimensional coupled dynamic transmission and distribution model is used to describe the mathematical model of the dynamic correlation between water pressure change, flow rate change, spring deformation change and orifice displacement change during the operation of the intelligent water transmission and distribution device. The model takes instantaneous water pressure, flow rate, spring deformation and orifice displacement as four core dimensions. By establishing the coupling and time series response relationship between multiple parameters, it forms a multi-dimensional dynamic structure that reflects mechanical behavior and fluid flow characteristics. Initialize each parameter in the four-dimensional coupled dynamic transportation and distribution model to form an initial running state set, which serves as the benchmark input for solving the four-dimensional coupled dynamic transportation and distribution model; Based on the parameter range in the standardized operating parameter set, the parameter boundaries of the four-dimensional coupled dynamic transport and distribution model are limited, and the range of values ​​for instantaneous water pressure, outflow, spring deformation and orifice displacement in the model iteration is constrained. The standardized set of operating parameters is input into the four-dimensional coupled dynamic transportation model. Combined with the initial set of operating states and parameter boundary conditions, the initialization and parameter calibration of the four-dimensional coupled dynamic transportation model are completed, so that the four-dimensional coupled dynamic transportation model has a unified parameter scale, boundary constraints and time consistency.

[0026] In this embodiment, the generation of the coupling state data sequence includes the following specific steps: In the process of intelligent water transmission and distribution, instantaneous water pressure, flow rate, spring deformation and orifice displacement are collected in real time according to a unified sampling cycle to construct a continuous time series dataset; By comparing data from adjacent moments in a continuous time series dataset, the instantaneous water pressure change, flow rate change, spring deformation change, and orifice displacement change are calculated to characterize the response rate in the time dimension. Based on the correspondence between the instantaneous change in water pressure and the change in spring deformation, the mechanical response value caused by water pressure disturbance is calculated to quantify the immediate impact of water pressure change on the spring structure. The mechanical response value is the dynamic response of the deformation of the spring structure in the water supply and distribution device under the action of instantaneous water pressure disturbance. It is used to characterize the mechanical displacement change caused by unit water pressure change and reflect the instantaneous response characteristics of water pressure disturbance to mechanical structure. The change in spring deformation is matched with the change in orifice displacement to calculate the orifice adjustment caused by the mechanical response, which is used to characterize the transmission effect of the spring response to the change in orifice geometric opening. The orifice displacement change and the outflow rate change are correlated and calculated to obtain the outflow rate response value caused by orifice adjustment, which is used to describe the real-time impact of orifice geometry change on fluid output. The mechanical response value caused by water pressure disturbance, the orifice adjustment amount caused by mechanical response, and the outflow response value caused by orifice adjustment are integrated in time to form a multi-parameter coupled response set, which is used to characterize the dynamic interaction relationship between the four core parameters. The mechanical response value caused by water pressure disturbance, the orifice adjustment amount caused by mechanical response, and the outflow response value caused by orifice adjustment are dynamic response values ​​calculated based on the causal mapping relationship between four operating parameters. They are used to characterize the transmission effect and coupling relationship between multiple internal parameters. The instantaneous water pressure change, outflow change, spring deformation change, and orifice displacement change are physical change values ​​collected in real time by sensors. They are used to reflect the actual physical state changes in continuous operating cycles. The former is a derived response value used to characterize the dynamic action chain of water pressure disturbance between mechanical structure and fluid output. The latter is a measured observation value used to provide model input and state monitoring basis. The two form a closed loop relationship of "observation-calculation-feedback" in logic, which jointly supports the four-dimensional coupled dynamic control process. The multi-parameter coupled response set is sorted and paired according to the sampling time order to form a coupled state data sequence, which is used to reflect the multi-parameter balance characteristics of intelligent water transmission and distribution during the operation cycle.

[0027] In this embodiment, the generation of the energy field function includes the following specific steps: Based on the coupled state data sequence, the dynamic change information of the mechanical response value caused by water pressure disturbance, the orifice adjustment amount caused by mechanical response, and the outflow response value caused by orifice adjustment in each sampling period is extracted and aligned with a unified time index to generate a response input sequence. Based on the response input sequence, the spring potential energy corresponding to the mechanical response value, the water pressure potential energy corresponding to the water pressure disturbance, and the flow deviation energy corresponding to the outflow response value are calculated to form an energy feature set, which is used to reflect the energy distribution characteristics under multi-parameter coupling conditions. The generation of the flow deviation energy specifically includes: obtaining the rated outflow rate as the target steady flow reference value, and extracting the outflow response value of the current sampling period from the coupled state data sequence, and recording the two values ​​respectively; calculating the difference between the current outflow response value and the rated outflow rate to obtain the outflow deviation amount, which is used to quantify the degree of flow deviation at the output end in this period; and calculating the energy change value corresponding to the flow deviation based on the outflow deviation amount and the fluid density and pipe cross-sectional area in the current sampling period, as the flow deviation energy of this sampling period. Based on the energy feature set, a dynamic energy field constraint model is established. Water pressure potential energy, spring potential energy, and flow deviation energy are uniformly described as time-varying energy field functions. A continuous time-series structure of the energy field function is constructed using the sampling time as an index. Specifically, this includes: recording the numerical change sequences of each parameter within a continuous sampling period based on the water pressure potential energy, spring potential energy, and flow deviation energy extracted from the energy feature set, generating energy parameter sequences corresponding to the time index; synchronizing and aligning each energy parameter sequence according to the sampling time to form an energy time-series matrix with the same time step, reflecting the dynamic distribution of the three types of energy in the time dimension; calculating the weighted sum of water pressure potential energy, spring potential energy, and flow deviation energy within each sampling period to obtain the comprehensive energy value for that sampling period, characterizing the overall energy level of the system at that moment; constructing the comprehensive energy value sequence as an energy field function using the sampling time as an index, and performing smoothing processing on the energy field function to eliminate abnormal energy abrupt changes, generating a continuous and analytical energy field function, thus obtaining a dynamic energy field constraint model reflecting the time-varying laws of water pressure potential energy, spring potential energy, and flow deviation energy.

[0028] In this embodiment, the energy field function is constructed from a sequence of comprehensive energy values ​​to describe the comprehensive distribution of water pressure potential energy, spring potential energy, and flow deviation energy over a continuous sampling time dimension. Each sampling moment corresponds to the comprehensive energy value of the system. The dynamic energy field constraint model takes the energy field function as its core and achieves dynamic coordination and energy balance control among multiple energy elements by constraining the continuity and balance of the comprehensive energy values ​​in the time series, thereby maintaining the steady flow operation of the intelligent water distribution device.

[0029] In this embodiment, the generation of the control parameter set includes the following specific steps: The energy comprehensive value sequence is extracted from the dynamic energy field constraint model, and the energy change sequence is calculated based on the continuous sampling time index to characterize the energy fluctuation characteristics of the intelligent water transmission and distribution device during the operating cycle. Based on the energy change sequence, the energy change amplitude is extracted, the average change amplitude of the energy change sequence is calculated, and the energy volatility is generated based on the average change amplitude. The energy fluctuation rate is a local energy stability parameter calculated within a continuous time window. Each time window corresponds to an energy fluctuation rate. By calculating the energy fluctuation rate in multiple adjacent time windows and arranging the results in chronological order, an energy fluctuation rate sequence is formed. This sequence is used to describe the temporal evolution of energy stability of the intelligent water distribution device during its operating cycle. The energy fluctuation rate sequence reflects the intensity change of system energy fluctuations in different time periods, providing a time-dimensional basis for energy balance determination for the dynamic energy field constraint model. The energy volatility is compared with the preset upper and lower limits of the energy stability range to calculate the energy deviation value, and the changing trend of the energy deviation value in the time series is recorded to generate an energy deviation feature sequence. When calculating the difference between energy volatility and the boundary of the stable interval, the relationship between energy volatility and the stable energy interval is first determined. When the energy volatility is higher than the upper limit of the stable interval, the difference between the energy volatility and the upper limit is calculated as the upper deviation energy value. When the energy volatility is lower than the lower limit of the stable interval, the difference between the lower limit and the energy volatility is calculated as the lower deviation energy value. When the energy volatility is within the stable interval, the energy deviation value is recorded as zero. By recording and arranging the obtained energy deviation values ​​in chronological order, an energy deviation characteristic sequence is formed, which is used to characterize the energy deviation trend and stability change characteristics of the intelligent water distribution device during the operating cycle. When setting the energy stability interval, during the stable operation phase of the system, the energy change amplitude sequence of multiple consecutive sampling periods is statistically calculated to extract the average value and standard deviation of energy volatility under long-term stable operating conditions. The average energy volatility is used as the central benchmark value of the energy stability interval, and the allowable range of energy volatility is set according to the multiplier of the standard deviation. When the multiplier is 1, the generated energy stability interval covers approximately 68% of the stable operating samples, and when the multiplier is 2, it covers approximately 95% of the stable operating samples. The central benchmark value plus the allowable range is used as the upper limit of the energy stability interval, and the central benchmark value minus the allowable range is used as the lower limit of the energy stability interval. The interval is fixed as the stable energy judgment standard of the dynamic energy field constraint model. Based on the energy deviation characteristic sequence and the average energy change amplitude, the energy deviation correction coefficient is calculated. Specifically, this includes: extracting the average deviation of energy deviation from the energy deviation characteristic sequence; reading the corresponding average energy change amplitude; and calculating the ratio between the average deviation of energy deviation and the average energy change amplitude to obtain the energy deviation correction coefficient, which is used to quantify the influence of the current energy deviation of the system on the control parameters. Based on the energy deviation correction coefficient, the aperture control parameters, spring preload parameters, and energy weight parameters are adjusted to generate a set of control parameters for adaptive steady-flow regulation in the dynamic energy field constraint model. The adjustment of the orifice control parameters, spring preload parameters, and energy weight parameters specifically includes: dividing the energy deviation correction coefficient into a fast correction factor, a slow correction factor, and a trend correction factor. The fast correction factor corresponds to the transient adjustment stage, which is used to correct the outflow orifice changes in real time. The slow correction factor corresponds to the mechanical balance stage, which is used to compensate for the stability of the spring reset characteristics. The trend correction factor corresponds to the energy distribution stage, which is used to optimize the energy field weight distribution in the long term. During the segmentation process, differential calculations are performed on the energy deviation characteristic sequence to obtain the energy deviation change rate sequence, which is used to characterize the fluctuation speed and direction of energy state in the time dimension. Based on the absolute value of the energy deviation change rate, a stratification threshold is set to divide the energy deviation change rate sequence into high-change, medium-change, and low-change intervals, corresponding to fast correction factors, slow correction factors, and trend correction factors, respectively. When the corresponding change rate is in the high-change interval, a fast correction factor is generated, and the orifice control parameters are corrected using a real-time proportional method to ensure timely compensation for water pressure disturbances in the outflow response. When the corresponding change rate is in the medium-change interval, a slow correction factor is generated, and the spring preload parameter is corrected using an iterative update method to gradually restore the mechanical balance characteristics over several sampling periods. When the corresponding change rate is in the low-change interval and the duration exceeds a set threshold, a trend correction factor is generated, and the energy weight parameters are corrected using a sliding weighted average method to maintain the long-term stability of the weight distribution of water pressure potential energy, spring potential energy, and flow deviation energy. The correction results are combined to form a control parameter set for the adaptive steady-flow regulation process in the dynamic energy field constraint model. The fast correction factor, slow correction factor, and trend correction factor are all generated by weighting the energy deviation correction coefficient and the energy deviation change rate. The energy deviation correction coefficient is used as the correction benchmark, and the energy deviation change rate is used as the weighting factor to dynamically adjust the correction range of the energy deviation correction coefficient. This is used to perform adaptive correction on the aperture control parameter, spring preload parameter, and energy weight parameter. Based on the rate of change of energy deviation, three types of correction factors—fast, slow, and trend—are dynamically generated and applied to the aperture control parameters, spring preload parameters, and energy weight parameters, respectively. This achieves an independent adaptive correction mechanism across multiple time scales. This structure avoids the global coupling problem caused by a single correction coefficient and improves the response sensitivity and flow stabilization accuracy of energy field control. The orifice control parameter, spring preload parameter, and energy weight parameter are used to describe the adjustable attributes and energy feedback relationship of different control units in the intelligent water distribution device. The orifice control parameter is the execution parameter of the outlet opening adjustment unit, which is used to control the effective flow area between the cone and the piston to achieve fine adjustment of the flow rate. The spring preload parameter is the initial stress setting value of the spring support structure, which is used to adjust the damping strength of the spring on the piston reset, thereby affecting the sensitivity and steady-state position of the mechanical response. The energy weight parameter is the proportional coefficient in the dynamic energy field constraint model, which is used to allocate the weight ratio of water pressure potential energy, spring potential energy, and flow deviation energy in the energy calculation to achieve dynamic coordination between different energy elements. The three types of parameters together constitute the comprehensive control parameter system of the intelligent water distribution device, providing a basic control basis for the system to achieve adaptive steady flow under energy fluctuation conditions. When the intelligent water distribution device is in a static state and the pipeline water pressure is stable, a standardized set of operating parameters, including initial water pressure, flow rate, spring deformation, and orifice displacement, is collected to generate an initial operating characteristic set. Based on the correspondence between flow rate and orifice displacement in the initial operating characteristic set, the target opening degree of the system under steady state is calculated, and the opening degree value is set as the initial value of the orifice control parameter. Based on the static balance relationship between spring deformation and water pressure change, the reset force required to maintain steady state is calculated, and the spring stress value corresponding to the reset force is set as the initial value of the spring preload parameter. Furthermore, the average distribution characteristics of water pressure potential energy, spring potential energy, and flow deviation energy in the energy field are statistically analyzed, the relative proportions of the three types of energy are calculated, and this proportion is set as the initial allocation coefficient of the energy weight parameter.

[0030] In this embodiment, the generation of the final orifice diameter adjustment amount and the outflow rate includes the following specific steps: After the energy field-constrained steady-flow regulation is completed, the set of control parameters is matched with the energy state parameters; The energy state parameters include water pressure potential energy, spring potential energy, and flow deviation energy; The set of control parameters is input into the dynamic energy field constraint model. Using the energy state parameters as initial conditions, the first time-series solution is performed to obtain the corresponding preliminary aperture adjustment amount and outflow rate. The generation of the preliminary orifice adjustment amount and outflow rate specifically includes: inputting the control parameter set into the dynamic energy field constraint model, using the energy state parameters of the previous cycle as initial conditions, and calculating the target orifice opening for the current cycle based on the orifice control parameters in the control parameter set; weighting the water pressure potential energy, spring potential energy, and flow deviation energy according to the energy weight parameters to obtain the energy distribution value; under the action of the energy distribution value, using the spring preload parameter to obtain the change in spring deformation, and calculating the orifice displacement adjustment amount from the change to generate the preliminary orifice adjustment amount; and calculating the flow rate based on the preliminary orifice adjustment amount. Based on the initial aperture adjustment amount and outflow rate, the energy state parameters are corrected, and an energy field balance judgment is performed. If the total energy deviation is less than or equal to the energy balance threshold, the current energy field is determined to be in balance. If the total energy deviation is greater than the energy balance threshold, the next round of time series solution is executed. When performing energy field balance judgment, based on the preliminary orifice adjustment amount and outflow response value of the current cycle, the water pressure potential energy, spring potential energy, and flow deviation energy in the energy state parameters are synchronously corrected to obtain the corrected water pressure potential energy value, spring potential energy value, and flow deviation energy value, respectively. These three types of energy values ​​are then combined to form an energy update vector. The energy update vector is compared item by item with the energy state parameters of the previous cycle, and the difference between each energy component is calculated to obtain the water pressure energy deviation, spring energy deviation, and flow energy deviation. The three deviations are then summed to obtain the total energy deviation. Finally, the total energy deviation is compared with a preset... The system compares the energy balance threshold to determine whether the current energy field is in equilibrium. If the total energy deviation is less than or equal to the energy balance threshold, the current energy field is determined to be in equilibrium. If the total energy deviation is greater than the energy balance threshold, the energy field is determined to be in an unequilibrium state. The total energy deviation is then input into the control parameter set to update the aperture control parameters, spring preload parameters, and energy weight parameters, generating a corrected control parameter set. The dynamic energy field constraint model is then called again to perform the next round of time-series solution, forming a new aperture adjustment amount and outflow rate, thus achieving periodic dynamic balance control of the energy field. After determining that the energy field has reached equilibrium, the final aperture adjustment amount and outflow rate are output.

[0031] To verify the feasibility of this embodiment in practice, it was applied to a newly built intelligent water supply and distribution network system in a coastal city. This region has significant topographical variations and a complex water supply network distribution. Traditional open channel or constant pressure pump control methods are prone to localized high pressure and low pressure at the end of the supply chain during multi-node parallel water supply, leading to significant fluctuations in outflow in some areas, especially during peak morning and evening water usage periods. Delayed flow regulation and pressure feedback significantly reduce the stability and energy efficiency of the water supply system. To improve these fluctuations and energy imbalances under non-constant pressure conditions, the intelligent water supply and distribution system based on multi-parameter optimization proposed in this invention was deployed on-site.

[0032] In practical applications, the system in this embodiment acquires real-time signals of instantaneous water pressure, flow rate, spring deformation, and orifice displacement inside the pipeline through a data acquisition and preprocessing module. These signals are then input into a four-dimensional coupled dynamic distribution modeling module to form a complete multi-parameter operational data stream. The system establishes a dynamic mapping relationship between water pressure disturbance, mechanical response, orifice adjustment, and flow output, constructing a coupled state data sequence to achieve continuous modeling from physical measurement to dynamic response. Subsequently, the dynamic energy field constraint module performs unified calculations on water pressure potential energy, spring potential energy, and flow deviation energy to form a time-series energy field function, thereby constraining the energy distribution balance of the entire distribution process. The parameter adaptive control module dynamically adjusts the orifice control parameters, spring preload parameters, and energy weight parameters based on the energy fluctuation rate and energy deviation value, enabling the system to automatically perform flow stabilization correction according to different water loads and water pressure disturbances. Finally, the flow stabilization solution module performs multi-cycle iterative calculations on the corrected parameter set to obtain a stable orifice adjustment amount and balanced flow rate, achieving automatic energy balance and flow stabilization distribution under complex terrain conditions.

[0033] From the perspective of the entire operation cycle, this embodiment significantly reduces the flow deviation caused by pressure fluctuations during the dynamic process of pipeline operation, improves the energy distribution efficiency of the system, and enhances the water flow continuity in the low-pressure water supply area. After continuous operation for a period of time, it was found that the overall system operation is more stable, the control response time is significantly shortened, and the water supply pressure distribution is more uniform.

[0034] To verify the performance of this embodiment in practice, it was compared with a traditional constant voltage and constant current system.

[0035] Table 1. Performance Comparison between Multi-Parameter Optimized Intelligent Water Distribution System and Traditional Constant Pressure Flow Stabilization System Compared with traditional constant voltage and constant current systems, the performance variation of this invention is... Average steady-state response time (s) 5.8 2.1 ↓63.8% Traffic fluctuation rate (%) 6.7 2.3 ↓65.7% Water supply pressure deviation range (kPa): 22.4 7.6 ↓66.1% Outflow stability coefficient (0~1): 0.72, 0.94, ↑30.6% Overall energy utilization efficiency (%) 82.3 93.6 ↑13.7% Overall system energy consumption (kWh / day): 184 153 ↓16.8% Percentage of low-pressure points in the pipeline network (%) 14.5 4.1 ↓71.7% Fault alarm rate (times / month): 5.2 1.6 ↓69.2% As can be seen from the data comparison in Table 1, the intelligent water transmission and distribution system proposed in this embodiment has better overall performance indicators than the traditional constant pressure and steady flow system under the constraints of dynamic energy field and the multi-parameter adaptive control mechanism.

[0036] In terms of response speed, traditional methods rely on pressure sensor feedback and pump speed control, resulting in significant response lag. In contrast, this invention achieves rapid correction through the coupling calculation of water pressure potential energy, spring potential energy, and flow deviation energy, reducing the average steady flow response time by approximately 64% and improving flow regulation efficiency.

[0037] Regarding the performance of flow fluctuation and pressure balance, this invention utilizes a four-dimensional coupled dynamic transmission and distribution model to achieve continuous correction of the energy field, thereby reducing the flow fluctuation rate by nearly two-thirds and narrowing the water supply pressure deviation range from 22.4 kPa to 7.6 kPa, thus enhancing pressure stability under complex terrain conditions.

[0038] From an energy consumption perspective, the overall energy utilization efficiency of the system is improved by about 13.7%, mainly due to the effect of the dynamic energy field constraint mechanism. By adaptively adjusting the aperture control parameters and spring preload parameters through the energy deviation correction coefficient, the mechanical damping loss and energy redundancy distribution are effectively reduced. At the same time, the overall energy consumption of the system is reduced by about 17% compared with the traditional method, and the proportion of low-pressure area is reduced by more than 70%, indicating that the present invention can achieve efficient energy distribution and rebalancing under the premise of ensuring stable flow.

[0039] In terms of stability, the outflow stability coefficient of the intelligent system has been improved to 0.94, indicating that its fluid output fluctuation is minimal. During long-term operation, the wear of mechanical units in the pipeline network has been reduced, and the fault alarm rate has been reduced from 5.2 times / month to 1.6 times / month. The safety and reliability of the system have been significantly improved.

[0040] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A smart water distribution device based on multi-parameter optimization, characterized in that, It includes a siphon flow limiting device (1) and a water outlet pipe (2), wherein the water outlet pipe (2) is connected to the upper end of the siphon flow limiting device (1).

2. A smart water transmission and distribution system based on multi-parameter optimization, using the smart water transmission and distribution device described in claim 1, characterized in that, include: The data acquisition and preprocessing module is used to collect the operating data of the intelligent water transmission and distribution device, and perform data preprocessing to generate a standardized set of operating parameters; The four-dimensional coupled dynamic transport and distribution modeling module is used to construct a four-dimensional coupled dynamic transport and distribution model based on a standardized set of operating parameters and to perform parameter initialization. The coupled state construction module is used to establish the relationship between water pressure disturbance, mechanical response, orifice regulation and flow output in the process of intelligent water transmission and distribution, forming a continuous time-series coupled state data sequence; The dynamic energy field constraint module is used to establish a dynamic energy field constraint model based on the coupled state data sequence, and to uniformly describe the water pressure potential energy, spring potential energy and flow deviation energy as an energy field function that changes with time. The parameter adaptive control module is used to calculate the energy fluctuation rate of the energy field function, extract the energy deviation value, and adjust the aperture control parameters, spring preload parameters, and energy weight parameters to form a set of control parameters. The steady flow solution module is used to input the set of control parameters into the four-dimensional coupled dynamic transport and distribution model for iterative solution to obtain the final orifice adjustment amount and outflow rate.

3. The intelligent water transmission and distribution system based on multi-parameter optimization according to claim 2, characterized in that, In the process of intelligent water transmission and distribution, a dynamic energy field constraint model is established based on the coupled state data sequence, and the water pressure potential energy, spring potential energy and flow deviation energy are uniformly described as energy field functions that change with time. The energy fluctuation rate of the energy field function is calculated, and the energy fluctuation rate is compared with the energy stability range to extract the energy deviation value. Based on the energy deviation value, the aperture control parameters, spring preload parameters, and energy weight parameters are dynamically adjusted to form a set of control parameters, thereby realizing adaptive steady flow regulation based on energy field constraints. The set of control parameters is input into a four-dimensional coupled dynamic transport and distribution model for iterative solution to obtain the final orifice adjustment amount and outflow rate, thereby realizing dynamic steady flow control and energy field balance maintenance under water pressure disturbance.

4. The intelligent water transmission and distribution system based on multi-parameter optimization according to claim 2, characterized in that, The operational data includes instantaneous water pressure, flow rate, spring deformation, and orifice displacement within the pipeline. The preprocessing includes time synchronization of the acquired data, noise filtering, and data standardization.

5. The intelligent water transmission and distribution system based on multi-parameter optimization according to claim 2, characterized in that, The execution parameter initialization includes the following specific steps: Extract instantaneous water pressure, flow rate, spring deformation and orifice displacement from the standardized operating parameter set to construct the parameter space of a four-dimensional coupled dynamic transport and distribution model; Initialize each parameter in the four-dimensional coupled dynamic transportation and distribution model to form an initial running state set, which serves as the benchmark input for solving the four-dimensional coupled dynamic transportation and distribution model; Based on the parameter range in the standardized operating parameter set, the parameter boundaries of the four-dimensional coupled dynamic transport and distribution model are limited, and the range of values ​​for instantaneous water pressure, outflow, spring deformation and orifice displacement in the model iteration is constrained. The standardized set of operating parameters is input into the four-dimensional coupled dynamic transportation model. Combined with the initial set of operating states and parameter boundary conditions, the initialization and parameter calibration of the four-dimensional coupled dynamic transportation model are completed.

6. The intelligent water transmission and distribution system based on multi-parameter optimization according to claim 2, characterized in that, The generation of the coupled state data sequence includes the following specific steps: In the process of intelligent water transmission and distribution, instantaneous water pressure, flow rate, spring deformation and orifice displacement are collected in real time according to a unified sampling cycle to construct a continuous time series dataset; By comparing data from adjacent moments in a continuous time series dataset, the instantaneous water pressure change, flow rate change, spring deformation change, and orifice displacement change are calculated. Calculate the mechanical response value caused by water pressure disturbance based on the correspondence between the instantaneous water pressure change and the spring deformation change; The change in spring deformation is matched with the change in orifice displacement to calculate the orifice adjustment caused by the mechanical response, which is used to characterize the transmission effect of the spring response to the change in orifice geometric opening. The orifice displacement change and the outflow rate change are correlated and calculated to obtain the outflow rate response value caused by orifice adjustment, which is used to describe the real-time impact of orifice geometry change on fluid output. The mechanical response value caused by water pressure disturbance, the orifice adjustment amount caused by mechanical response, and the outflow response value caused by orifice adjustment are integrated in time to form a multi-parameter coupled response set. The multi-parameter coupled response set is sorted and paired according to the sampling time order to form a coupled state data sequence, which is used to reflect the multi-parameter balance characteristics of intelligent water transmission and distribution during the operation cycle.

7. The intelligent water transmission and distribution system based on multi-parameter optimization according to claim 2, characterized in that, The generation of the energy field function includes the following specific steps: Based on the coupled state data sequence, the dynamic change information of the mechanical response value caused by water pressure disturbance, the orifice adjustment amount caused by mechanical response, and the outflow response value caused by orifice adjustment in each sampling period is extracted and aligned with a unified time index to generate a response input sequence. Based on the response input sequence, the spring potential energy corresponding to the mechanical response value, the water pressure potential energy corresponding to the water pressure disturbance, and the flow deviation energy corresponding to the outflow response value are calculated to form an energy feature set; Based on the energy characteristic set, a dynamic energy field constraint model is established, which uniformly describes the water pressure potential energy, spring potential energy and flow deviation energy as energy field functions that change with time, and constructs a continuous time-series structure of the energy field function with the sampling time as the index.

8. The intelligent water transmission and distribution system based on multi-parameter optimization according to claim 7, characterized in that, The energy field function is constructed from a sequence of comprehensive energy values ​​to describe the comprehensive distribution of water pressure potential energy, spring potential energy, and flow deviation energy over a continuous sampling time dimension. Each sampling moment corresponds to the comprehensive energy value of the system. The dynamic energy field constraint model takes the energy field function as its core and achieves dynamic coordination and energy balance control among multiple energy elements by constraining the continuity and balance of the comprehensive energy value in the time series, thereby maintaining the steady flow operation of the intelligent water distribution device.

9. The intelligent water transmission and distribution system based on multi-parameter optimization according to claim 2, characterized in that, The generation of the control parameter set includes the following specific steps: The energy composite value sequence is extracted from the dynamic energy field constraint model, and the energy change sequence is calculated based on the continuous sampling time index. Based on the energy change sequence, the energy change amplitude is extracted, the average change amplitude of the energy change sequence is calculated, and the energy volatility is generated based on the average change amplitude. The energy volatility is compared with the preset upper and lower limits of the energy stability range to calculate the energy deviation value, and the changing trend of the energy deviation value in the time series is recorded to generate an energy deviation feature sequence. The energy deviation correction coefficient is calculated based on the energy deviation characteristic sequence and the average energy change amplitude. The aperture control parameters, spring preload parameters, and energy weight parameters are adjusted based on the energy deviation correction coefficient to generate a set of control parameters.

10. The intelligent water transmission and distribution system based on multi-parameter optimization according to claim 2, characterized in that, The generation of the final orifice adjustment amount and outflow rate includes the following specific steps: After the energy field-constrained steady-flow regulation is completed, the set of control parameters is matched with the energy state parameters; The energy state parameters include water pressure potential energy, spring potential energy, and flow deviation energy; The set of control parameters is input into the dynamic energy field constraint model. Using the energy state parameters as initial conditions, the first time-series solution is performed to obtain the corresponding preliminary aperture adjustment amount and outflow rate. Based on the initial aperture adjustment amount and outflow rate, the energy state parameters are corrected, and an energy field balance judgment is performed. If the total energy deviation is less than or equal to the energy balance threshold, the current energy field is determined to be in balance. If the total energy deviation is greater than the energy balance threshold, the next round of time series solution is executed. After determining that the energy field has reached equilibrium, the final aperture adjustment amount and outflow rate are output.

Images