Water supply scheduling method driven by real-time water regimen

Abstract

The invention relates to the technical field of urban water supply operation scheduling, in particular to a real-time water regimen-driven water supply scheduling method, which comprises the following steps of S1, synchronously acquiring water quality parameters of a water source, pressure data of a main pipe network and instantaneous flow of a user side; s2, generating a dynamic water quality safety margin based on the water quality parameters; s3, calculating a regional pressure flow unbalance factor according to the pressure data of the main pipe network and the instantaneous flow of the user side; s4, the dynamic water quality safety margin and the pressure flow unbalance factor are fused, and a real-time water supply toughness index is generated; and S5, mapping the water supply toughness index into a pressure regulation and control instruction. According to the method, the water supply toughness index is constructed by fusing the water quality and the hydraulic state, the graded pressure regulation and control strategy is executed accordingly, and dynamic guarantee of the stability and safety of the water supply system under the complex water regimen is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of urban water supply operation scheduling, and in particular to a water supply scheduling method driven by real-time water conditions. Background Art

[0002] With the continuous expansion of urban water supply systems and the development of zoning control technology, the traditional water supply scheduling method based on static water pressure setting and regular water quality sampling has become difficult to meet the complex and changing water demand and the response requirements of sudden water quality incidents.

[0003] Most current water supply scheduling schemes still focus on regulating a single parameter, such as maintaining constant pressure by controlling the frequency of main pumps or adjusting regional pressure through terminal pressure boosters. However, these schemes often lack the collaborative analysis of multiple data sources, such as water quality, water pressure, and flow. This leads to delayed scheduling or rigid strategies, making it difficult to balance water supply security and scheduling flexibility. Therefore, a real-time water condition-driven water supply scheduling method is urgently needed to address these issues. Summary of the Invention

[0004] Based on the above objectives, the present invention provides a water supply scheduling method driven by real-time water conditions.

[0005] A real-time water condition driven water supply scheduling method comprises the following steps: S1: Synchronously obtain water quality parameters at the water source, main pipe network pressure data and instantaneous flow at the user end; S2: Generate dynamic water quality safety margin based on water quality parameters; S3: Calculate the regional pressure-flow imbalance factor based on the main pipeline network pressure data and the instantaneous flow at the user end; S4: Integrate the dynamic water quality safety margin and pressure-flow imbalance factor to generate a real-time water supply resilience index; S5: Map the water supply resilience index into pressure control instructions, including maintaining pressure, reducing pressure in stages, or activating emergency low-pressure mode.

[0006] Optionally, the S1 specifically includes: S11: obtaining real-time water quality parameters, including turbidity and residual chlorine concentration, through an online water quality sensor installed at the water outlet of the water source; S12: Install piezoresistive pressure transmitters at the nodes of the hydraulic zones of the pipe network and record pressure data at a sampling frequency of 100 Hz; S13: Collect instantaneous flow data through the remote flow meter installed at the user end; S14: Align the data acquired from S11 to S13 according to a unified timestamp to form a standardized time series data set.

[0007] Optionally, the S2 specifically includes: S21: extract the turbidity and residual chlorine concentration data obtained in S1, and compare the two water quality parameters with the corresponding water quality safety thresholds to determine whether the current water quality meets the safety standards; S22: Assign corresponding risk levels based on the degree of turbidity exceeding the standard or the degree of residual chlorine concentration deficiency. The risk levels are divided into five levels: very low, low, medium, high, and very high. S23: Match the corresponding water quality safety margin coefficient based on the risk level determined in S22.

[0008] Optionally, the S22 specifically includes: S221: Compare the turbidity value obtained in S1 with the preset maximum safety limit and calculate the turbidity deviation rate ,when When When the deviation is low, medium, high or very high, the S222: Compare the residual chlorine concentration value obtained in S1 with the preset minimum safety limit to calculate the residual chlorine deficiency rate ,when It is judged as very low risk when When the risk level is low, medium, high or very high, the risk level is divided into five levels according to the degree of deficiency. S223: Record the two risk levels obtained from S221 and S222 respectively, and use the higher risk level as the final risk level of the current water quality parameter.

[0009] Optionally, the S23 specifically includes: S231: Receive the water quality risk level output in S22, recorded as , with values ​​ranging from 1 to 5, corresponding to very low, low, moderate, high, and very high water quality risks, respectively; S232: According to the risk level , matching the corresponding water quality safety margin coefficient, the safety margin coefficient is The interval is assigned according to a fixed function, and the expression of the function is: ,in, is the water quality safety margin coefficient, The current water quality risk level.

[0010] Optionally, the S3 specifically includes: S31: Based on the main pipeline network pressure data obtained in S1, the pressure of each node is aggregated in time series according to the hydraulic partition structure to form a pressure change sequence, and the average pressure change rate and maximum node pressure difference of each partition are extracted; S32: Based on the instantaneous flow data of the user end obtained in S1, the total flow of users in each hydraulic zone is weighted and summarized, and combined with the conventional water load model in the zone, the current instantaneous flow deviation rate is calculated; S33: Correlation analysis is performed on the pressure fluctuation index and flow deviation rate in each hydraulic zone, and a multi-dimensional state combination rule is set to determine whether there is a pressure drop caused by a sudden increase in flow or a backflow caused by pressure imbalance in the zone; S34: According to the determination result of S33, a regional pressure-flow imbalance factor is assigned to each hydraulic zone.

[0011] Optionally, the setting of multi-dimensional state combination rules includes: Rule 1: When the average pressure change rate within a zone is negative, the flow deviation rate is positive, and the pressure difference exceeds the set threshold, it is determined to be a pressure drop caused by a sudden flow increase; Rule 2: When the average pressure change rate within a partition is positive, the flow deviation rate is negative, and the upstream node pressure is higher than the downstream node pressure, it is determined to be a backflow caused by pressure imbalance; Rule 3: When the frequency of pressure fluctuations within a zone increases abnormally and exceeds a preset threshold, and there is no flow change, it is determined to be pipe network oscillation; Rule 4: When both the flow deviation rate and the pressure change rate are negative, it is determined that the stability has decreased due to a low water supply load state.

[0012] Optionally, the S34 specifically includes: S341: For each identified hydraulic zone in S33, extract the corresponding state type label, including pressure drop caused by sudden flow increase, backflow caused by pressure imbalance, pipe network oscillation and stability degradation, and set the corresponding basic imbalance score value for each state type ; S342: Based on the basic imbalance score, the real-time pressure change amplitude factor of each partition is superimposed Deviation factor from flow rate ; S343: Calculate the final regional pressure-flow imbalance factor based on the influence of each factor on the imbalance degree. The expression is: ,in, Indicates the imbalance factor of the current hydraulic zone, and its value range is limited to .

[0013] Optionally, the S4 specifically includes: S41: Obtain the water quality safety margin coefficient calculated in S23 And the regional pressure-flow imbalance factor calculated in S34 , and normalize and check the two indicators to ensure that they are both within the range Inside; S42: Perform weighted fusion on the two parameters to obtain the real-time water supply resilience index, which is: ,in, is the real-time water supply resilience index, and Represent the weight coefficients of water quality dimension and hydraulic dimension respectively.

[0014] Optionally, the S5 specifically includes: S51: Obtaining real-time water supply resilience index and compare it with the preset three-stage toughness threshold range to determine the current regulation state; The threshold interval includes: The first threshold interval [0.7, 1] is determined as stable water supply, corresponding to the pressure maintenance mode; The second threshold interval [0.4, 0.7) is determined to be water supply shortage, corresponding to the graded pressure reduction mode; The third threshold interval [0, 0.4) is determined to be a high risk of water supply, corresponding to the emergency low-pressure mode.

[0015] Beneficial effects of the present invention: The present invention collects multi-source real-time data on water quality at the water source, pipe network pressure, and user flow, constructs a dynamic water quality safety margin and a regional pressure-flow imbalance factor, and integrates them to form a water supply resilience index, thereby achieving a comprehensive quantitative assessment of the stability and safety of the water supply system and providing a basis for the accurate generation of scheduling instructions.

[0016] The present invention, through the graded response mechanism of the resilience index, enables the scheduling system to dynamically match three types of control strategies: maintaining pressure, graded pressure reduction, and emergency low pressure. This improves the system's ability to identify and respond to water quality risks and hydraulic disturbances, and enhances the water supply system's adaptability and fault tolerance under complex water conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 Schematic diagram of a water supply scheduling method according to an embodiment of the present invention; Figure 2 Schematic diagram of a process for generating a regional pressure-flow imbalance factor according to an embodiment of the present invention. DETAILED DESCRIPTION

[0019] The present invention is described in detail below with reference to the accompanying drawings and specific embodiments. It is also noted that, to provide a more detailed description, the following embodiments are best and preferred embodiments, and those skilled in the art may employ alternative methods for implementing certain known technologies. Furthermore, the accompanying drawings are intended only to provide a more detailed description of the embodiments and are not intended to limit the present invention.

[0020] It should be noted that references in the specification to "one embodiment," "an embodiment," "exemplary embodiments," "some embodiments," etc. indicate that the described embodiments may include specific features, structures, or characteristics, but not necessarily every embodiment will include such specific features, structures, or characteristics. Furthermore, when specific features, structures, or characteristics are described in conjunction with an embodiment, it is within the knowledge of persons skilled in the relevant art to implement such features, structures, or characteristics in conjunction with other embodiments (whether or not explicitly described).

[0021] In general, terms can be understood, at least in part, from their use in context. For example, depending at least in part on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending at least in part on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0022] like Figure 1-Figure 2 As shown, a real-time water condition driven water supply scheduling method includes the following steps: S1: Synchronously obtain water quality parameters at the water source, main pipe network pressure data and instantaneous flow at the user end; S2: Generate dynamic water quality safety margin based on water quality parameters; S3: Calculate the regional pressure-flow imbalance factor based on the main pipeline network pressure data and the instantaneous flow at the user end; S4: Integrate the dynamic water quality safety margin and pressure-flow imbalance factor to generate a real-time water supply resilience index; S5: Map the water supply resilience index into pressure control instructions, including maintaining pressure, reducing pressure in stages, or activating emergency low-pressure mode.

[0023] S1 specifically includes: S11: Real-time water quality parameters, including turbidity and residual chlorine concentration, are obtained through online water quality sensors installed at the water source outlet. Turbidity is collected by a light scattering turbidimeter, and residual chlorine concentration is collected by an electrochemical residual chlorine electrode. The collected data are then uploaded to the dispatching platform in real time. S12: Install piezoresistive pressure transmitters at nodes in the hydraulic zones of the pipe network, record pressure data at a sampling frequency of 100 Hz, and transmit the data in real time to the edge computing gateway via industrial Ethernet. S13: Collect instantaneous flow data through the remote flow meter installed at the user end. The remote flow meter includes an ultrasonic flow sensor and a GPRS communication module, which can upload the instantaneous flow value of each terminal to the central server in a cycle of 1 second; S14: Align the data obtained from S11 to S13 according to a unified timestamp to form a standardized time series data set, which serves as the input basis for subsequent water quality margin assessment and water supply resilience calculation; the above steps can significantly improve the response timeliness and overall perception accuracy of the data-driven water supply scheduling system by synchronously collecting and time-aligning the water quality parameters, pipe network pressure and terminal flow data at the water source within a time scale of seconds, and provide accurate and real-time data support for subsequent water quality margin analysis and resilience decision-making.

[0024] S2 specifically includes: S21: extract the turbidity and residual chlorine concentration data obtained in S1, and compare the two water quality parameters with the corresponding water quality safety thresholds to determine whether the current water quality meets the safety standards; S22: According to the degree of turbidity exceeding the standard or the degree of residual chlorine concentration being insufficient, the corresponding risk level is assigned. The risk level is divided into five levels: very low, low, medium, high and very high, which are used to indicate the current water quality risk level; S23: Based on the risk level determined by S22, the corresponding water quality safety margin coefficient is matched. This coefficient is a quantitative indicator reflecting the current water quality safety margin. The higher the value, the lower the risk. By establishing a water quality parameter mapping mechanism with risk level as the intermediary, the level quantification of the real-time water quality status is achieved, which helps the subsequent scheduling links to dynamically adjust the water supply strategy under the premise of ensuring water supply safety, and improve the water quality adaptability and decision-making accuracy of the overall system.

[0025] S22 specifically includes: S221: The turbidity value obtained in S1 With the preset maximum safety limit Compare and calculate the turbidity deviation rate , whose expression is: , among which, when When When the deviation is classified into low, medium, high or very high, the specific classification standard is: When , it is a lower risk; when When When , it is a higher risk; when When , it is extremely high risk; The turbidity mentioned above is an important parameter that reflects the amount of suspended particles in the water. It usually has a legal maximum allowable value. When the real-time turbidity exceeds this threshold, it means that the water quality has begun to deteriorate. The essence of the deviation rate is to quantify the severity of the exceedance by calculating the ratio of the difference between the actual turbidity value and the safety threshold. The logic is: if the turbidity is lower than or equal to the threshold, the deviation rate is zero, indicating no risk. As the turbidity value gradually exceeds the standard, the deviation rate increases, indicating that the risk level is gradually increasing. This method converts the exceedance range into a dimensionless value so that it can be treated uniformly with other indicators.

[0026] S222: The residual chlorine concentration value obtained in S1 Compared with the preset minimum safety limit Compare and calculate the residual chlorine deficiency rate , whose expression is: , among which, when It is judged as very low risk when When the risk is divided into five levels according to the degree of deficiency: low, medium, high or very high. The specific classification standards are: When , it is a lower risk; when When When , it is a higher risk; when When , it is extremely high risk; The above-mentioned residual chlorine is a key factor in sterilizing the water supply system and maintaining water quality safety, and is usually required to be no lower than a certain concentration threshold. When the actual residual chlorine concentration is lower than the threshold, the sterilization protection ability of the water supply is weakened and the risk increases. The principle of the deficiency rate is to reflect the degree of water quality risk by calculating the ratio of the residual chlorine concentration gap to the threshold: when the residual chlorine is higher than the threshold, the deficiency rate is zero, indicating safety; when the residual chlorine is lower than the threshold, the deficiency rate increases with the increase of the gap, which intuitively reflects the degree to which the water supply safety margin is weakened. Through this dimensionless description, a symmetrical risk quantification framework can be formed with the turbidity index.

[0027] S223: Record the two risk levels obtained from S221 and S222 respectively, and take the higher-level one as the final risk level of the current water quality parameter, which will be used as the basis for determining the water quality safety margin in subsequent steps. The above steps quantify the deviation rate and the deficiency rate, and set segmented thresholds to achieve clear classification of risk levels, so that the system can accurately identify the degree of water quality abnormality, thereby ensuring that the subsequent scheduling process has a clear basis for judging the risk level.

[0028] S23 specifically includes: S231: Receive the water quality risk level output in S22, recorded as , with values ​​ranging from 1 to 5, corresponding to very low, low, moderate, high, and very high water quality risks, respectively; S232: According to risk level , matching the corresponding water quality safety margin coefficient, the safety margin coefficient is The interval is assigned according to a fixed function, and the expression of the function is: ,in, is the water quality safety margin coefficient, is the current water quality risk level. According to this functional relationship, the margin coefficient is negatively correlated with the risk level, that is, the higher the risk level, the lower the safety margin. The above steps realize the structured conversion of water quality risk information to the input parameters of the scheduling model by constructing a mathematical functional relationship between the water quality risk level and the safety margin coefficient, so that the system can generate numerical margin evaluation indicators in real time when the water quality deviates, providing high-efficiency and high-stability basic parameter support for subsequent resilient scheduling.

[0029] S3 specifically includes: S31: Based on the main pipeline network pressure data obtained in S1, the pressure of each node is aggregated in time series according to the hydraulic partition structure to form a pressure change sequence, and the average pressure change rate and maximum node pressure difference of each partition are extracted to characterize the local water supply stability; S32: Based on the instantaneous flow data of the user end obtained in S1, the total flow of users in each hydraulic zone is weighted and summarized, and combined with the conventional water load model in the zone, the current instantaneous flow deviation rate is calculated to identify whether the user end flow fluctuates abnormally; S33: Correlation analysis is performed on the pressure fluctuation index and flow deviation rate in each hydraulic zone, and a multi-dimensional state combination rule is set to determine whether there is a pressure drop caused by a sudden increase in flow or a backflow caused by pressure imbalance in the zone; S34: Based on the judgment result of S33, a regional pressure-flow imbalance factor is assigned to each hydraulic zone. This factor comprehensively considers the pressure stability, flow deviation degree and its time-series coupling characteristics, and reflects the degree of abnormal operation of the current regional hydraulic system. The value range is 0 to 1, and the larger the value, the higher the degree of imbalance. The above steps integrate the spatial fluctuation characteristics of the pipeline network pressure and the instantaneous deviation characteristics of the user flow, and establish a multi-dimensional state judgment mechanism, thereby achieving highly sensitive identification of non-steady-state hydraulic behavior in the region, effectively capturing potential anomalies in the system operation, and improving the scheduling system's active response capability and identification accuracy to local imbalance states.

[0030] Setting multi-dimensional state combination rules includes: Rule 1: When the average pressure change rate within a zone is negative, the flow deviation rate is positive, and the pressure difference exceeds the set threshold, it is determined to be a pressure drop caused by a sudden flow increase; Rule 2: When the average pressure change rate within a partition is positive, the flow deviation rate is negative, and the upstream node pressure is higher than the downstream node pressure, it is determined to be a backflow caused by pressure imbalance; Rule 3: When the frequency of pressure fluctuations within a zone increases abnormally and exceeds a preset threshold, and there is no flow change, it is determined to be pipe network oscillation; Rule 4: When both the flow deviation rate and the pressure change rate are negative, it is determined that the stability has decreased due to a low water supply load state. By constructing three-dimensional state judgment rules covering pressure change trends, pressure difference extremes, and flow deviation degrees, and defining typical combination scenarios, structured recognition of complex imbalance behaviors within hydraulic zones is achieved, effectively improving the scheduling system's ability to classify and judge abnormal patterns and the accuracy of hydraulic diagnosis.

[0031] S34 specifically includes: S341: For each identified hydraulic zone in S33, extract the corresponding state type label, including pressure drop caused by sudden flow increase, backflow caused by pressure imbalance, pipe network oscillation and stability degradation, and set the corresponding basic imbalance score value for each state type , set to 0.6, 0.7, 0.5, 0.4 respectively; S342: Based on the basic imbalance score, the real-time pressure change amplitude factor of each partition is superimposed Deviation factor from flow rate ; The two factors are calculated as follows: Pressure variation factor: ;in, is the average pressure change rate of the partition, is the reference pressure value; Flow deviation degree factor: ,in, is the partition flow deviation rate, is the benchmark deviation value under the standard load model; S343: Calculate the final regional pressure-flow imbalance factor based on the influence of each factor on the imbalance degree. The expression is: ,in, Indicates the imbalance factor of the current hydraulic zone, and its value range is limited to , and perform upper and lower limit truncation when exceeding the boundary; the above steps effectively realize the quantitative characterization of regional hydraulic abnormality status by numerically fusing the state identification label with the multi-source deviation factor and constructing a standardized scoring calculation model, thereby improving the system's perception and parameterized expression ability of local imbalance risks, and providing a stable and comparable input basis for subsequent scheduling decisions.

[0032] S4 specifically includes: S41: Obtain the water quality safety margin coefficient calculated in S23 And the regional pressure-flow imbalance factor calculated in S34 , and normalize and check the two indicators to ensure that they are both within the range As the input variable of the subsequent fusion model; S42: Perform weighted fusion on the two parameters to obtain the real-time water supply resilience index, which is: ,in, is the real-time water supply resilience index, and Represent the weight coefficients of water quality dimension and hydraulic dimension respectively, satisfying , weights can be preset in the scheduling model according to regional characteristics; the above steps calculate the water supply resilience index by integrating water quality and hydraulic status indicators in a fixed-weight manner, and establish a unified quantitative evaluation index system based on multi-dimensional water emotion perception, which provides the scheduling system with a real-time judgment basis for the current stability and carrying capacity of the water supply system.

[0033] The above basic imbalance scores are preset risk level initial values ​​for different imbalance types (such as pressure drop, backflow, pipe network oscillation, etc.); their design logic is: Different types of imbalances pose different levels of threat to system stability, so different initial scores are set for them based on expert experience or historical big data. This score is equivalent to a baseline risk, which will be subsequently corrected by adding pressure change factors and flow deviation factors. The principle of this method is to first use qualitative knowledge to establish a basic distinction, and then achieve quantitative adjustment through dynamic parameter calculation, thereby maintaining clear classification and flexible adaptability.

[0034] S5 specifically includes: S51: Obtaining real-time water supply resilience index and compare it with the preset three-stage toughness threshold range to determine the current regulation state; The threshold intervals include: The first threshold interval [0.7, 1] is determined as stable water supply, corresponding to the pressure maintenance mode; The second threshold interval [0.4, 0.7) is determined to be water supply shortage, corresponding to the graded pressure reduction mode; The third threshold interval [0, 0.4) is determined to be a high risk of water supply, corresponding to the emergency low-pressure mode.

[0035] The above-mentioned resilience threshold range is used to map the water supply resilience index to the control instructions, which is a graded response mechanism; its design principles include: when the resilience index is close to 1, it means that the water quality is safe, the pressure is balanced, the system is in a stable state, and the pressure can be maintained unchanged; when the resilience index is in the medium range, it means that some risks exist and active mitigation measures need to be taken, so a graded pressure reduction strategy is set; when the resilience index is very low, it means that the water supply security is seriously insufficient and it is necessary to enter the emergency mode to reduce the overall pressure to ensure the water supply safety of key areas; by dividing the resilience index into different intervals, continuous quantitative indicators can be converted into discrete decision-making actions, thereby improving the operability and controllability of scheduling execution.

[0036] If it is determined to be in pressure maintenance mode, the scheduling system will maintain the existing pressure regulating valve opening and water supply pump frequency unchanged, and only conduct slight pressure monitoring on the boundary nodes to avoid excessive intervention; If the staged pressure reduction mode is determined, the pressure regulation priority is assigned in descending order according to the pressure-flow imbalance factor of each hydraulic zone. The dispatching system gradually reduces the pressure setting value of the high imbalance area according to the set ratio. The typical pressure reduction range is 5% to 15%. If it is determined to be an emergency low-pressure mode, the emergency water supply strategy for the corresponding area will be immediately activated, including reducing the operating frequency of the main pump, closing some terminal branches, locking the water supply protection range of key areas, and simultaneously sending a scheduling alarm signal to the monitoring platform; by dividing the water supply resilience index into three threshold intervals and corresponding to different control strategies, a fine-grained graded response of the pressure scheduling logic is achieved, enabling the system to automatically execute adaptive control actions based on the comprehensive water supply status, effectively balancing water supply safety and system stability, and improving the intelligence level of scheduling decisions.

[0037] The present invention encompasses any alternatives, modifications, equivalents, and solutions that fall within the spirit and scope of the present invention. To provide a thorough understanding of the present invention, specific details are described in detail below in connection with the preferred embodiments of the present invention, but those skilled in the art will be able to fully understand the present invention without these detailed descriptions. Furthermore, to avoid unnecessary confusion regarding the essence of the present invention, well-known methods, processes, procedures, components, and circuits have not been described in detail.

[0038] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.

Claims

1. A water supply scheduling method driven by real-time water conditions, characterized in that: The following steps are involved: S1: Synchronously obtain water quality parameters at the water source, main pipe network pressure data and instantaneous flow at the user end; S2: Generate dynamic water quality safety margin based on water quality parameters; S3: Calculate the regional pressure-flow imbalance factor based on the main pipeline network pressure data and the instantaneous flow at the user end; S4: Integrate the dynamic water quality safety margin and pressure-flow imbalance factor to generate a real-time water supply resilience index; S5: Map the water supply resilience index into pressure control instructions, including maintaining pressure, reducing pressure in stages, or activating emergency low-pressure mode.

2. A real-time water condition driven water supply scheduling method according to claim 1, characterized in that: Said S1 specifically includes: S11: obtaining real-time water quality parameters, including turbidity and residual chlorine concentration, through an online water quality sensor installed at the water outlet of the water source; S12: Install piezoresistive pressure transmitters at the nodes of the hydraulic zones of the pipe network and record pressure data at a sampling frequency of 100 Hz; S13: Collect instantaneous flow data through the remote flow meter installed at the user end; S14: Align the data acquired from S11 to S13 according to a unified timestamp to form a standardized time series data set.

3. A real-time water supply scheduling method driven by water conditions according to claim 2, characterized in that: The S2 specifically includes: S21: extract the turbidity and residual chlorine concentration data obtained in S1, and compare the two water quality parameters with the corresponding water quality safety thresholds to determine whether the current water quality meets the safety standards; S22: Assign corresponding risk levels based on the degree of turbidity exceeding the standard or the degree of residual chlorine concentration deficiency. The risk levels are divided into five levels: very low, low, medium, high, and very high. S23: Match the corresponding water quality safety margin coefficient based on the risk level determined in S22.

4. A real-time water condition driven water supply scheduling method according to claim 3, characterized in that: The S22 specifically includes: S221: Compare the turbidity value obtained in S1 with the preset maximum safety limit and calculate the turbidity deviation rate ,when When When the deviation is low, medium, high or very high, the S222: Compare the residual chlorine concentration value obtained in S1 with the preset minimum safety limit to calculate the residual chlorine deficiency rate ,when It is judged as very low risk when When the risk level is low, medium, high or very high, the risk level is divided into five levels according to the degree of deficiency. S223: Record the two risk levels obtained from S221 and S222 respectively, and use the higher risk level as the final risk level of the current water quality parameter.

5. A real-time water condition driven water supply scheduling method according to claim 4, characterized in that: The S23 specifically includes: S231: Receive the water quality risk level output in S22, recorded as , with values ​​ranging from 1 to 5, corresponding to very low, low, moderate, high, and very high water quality risks, respectively; S232: According to the risk level , matching the corresponding water quality safety margin coefficient, the safety margin coefficient is The interval is assigned according to a fixed function, and the expression of the function is: ,in, is the water quality safety margin coefficient, The current water quality risk level.

6. A real-time water condition driven water supply scheduling method according to claim 5, characterized in that: The S3 specifically includes: S31: Based on the main pipeline network pressure data obtained in S1, the pressure of each node is aggregated in time series according to the hydraulic partition structure to form a pressure change sequence, and the average pressure change rate and maximum node pressure difference of each partition are extracted; S32: Based on the instantaneous flow data of the user end obtained in S1, the total flow of users in each hydraulic zone is weighted and summarized, and combined with the conventional water load model in the zone, the current instantaneous flow deviation rate is calculated; S33: Correlation analysis is performed on the pressure fluctuation index and flow deviation rate in each hydraulic zone, and a multi-dimensional state combination rule is set to determine whether there is a pressure drop caused by a sudden increase in flow or a backflow caused by pressure imbalance in the zone; S34: According to the determination result of S33, a regional pressure-flow imbalance factor is assigned to each hydraulic zone.

7. A real-time water condition driven water supply scheduling method according to claim 6, characterized in that: The multi-dimensional state combination rule setting includes: Rule 1: When the average pressure change rate within a zone is negative, the flow deviation rate is positive, and the pressure difference exceeds the set threshold, it is determined to be a pressure drop caused by a sudden flow increase; Rule 2: When the average pressure change rate within a partition is positive, the flow deviation rate is negative, and the upstream node pressure is higher than the downstream node pressure, it is determined to be a backflow caused by pressure imbalance; Rule 3: When the frequency of pressure fluctuations within a zone increases abnormally and exceeds a preset threshold, and there is no flow change, it is determined to be pipe network oscillation; Rule 4: When both the flow deviation rate and the pressure change rate are negative, it is determined that the stability has decreased due to a low water supply load state.

8. A real-time water condition driven water supply scheduling method according to claim 7, characterized in that: The S34 specifically includes: S341: For each identified hydraulic zone in S33, extract the corresponding state type label, including pressure drop caused by sudden flow increase, backflow caused by pressure imbalance, pipe network oscillation and stability degradation, and set the corresponding basic imbalance score value for each state type ; S342: Based on the basic imbalance score, the real-time pressure change amplitude factor of each partition is superimposed Deviation factor from flow rate ; S343: Calculate the final regional pressure-flow imbalance factor based on the influence of each factor on the imbalance degree. The expression is: ,in, Indicates the imbalance factor of the current hydraulic zone, and its value range is limited to .

9. A real-time water condition driven water supply scheduling method according to claim 8, characterized in that: The S4 specifically includes: S41: Obtain the water quality safety margin coefficient calculated in S23 And the regional pressure-flow imbalance factor calculated in S34 , and normalize and check the two indicators to ensure that they are both within the range Inside; S42: Perform weighted fusion on the two parameters to obtain the real-time water supply resilience index, which is: ,in, is the real-time water supply resilience index, and Represent the weight coefficients of water quality dimension and hydraulic dimension respectively.

10. A real-time water condition driven water supply scheduling method according to claim 9, characterized in that: The S5 specifically includes: S51: Obtaining real-time water supply resilience index and compare it with the preset three-stage toughness threshold range to determine the current regulation state; The threshold interval includes: The first threshold interval [0.7, 1] is determined as stable water supply, corresponding to the pressure maintenance mode; The second threshold interval [0.4, 0.7) is determined to be water supply shortage, corresponding to the graded pressure reduction mode; The third threshold interval [0, 0.4) is determined to be a high risk of water supply, corresponding to the emergency low-pressure mode.

Images