A pressurized water storage method suitable for rural water supply

Abstract

The application discloses a kind of pressurized water storage methods suitable for rural water supply, it is related to pressurized water storage technical field, comprising the following steps: first, establish a comprehensive real-time monitoring system, to obtain the current water usage data of reservoir;Real-time water usage data collected is stored and managed, a structured data set is established, and the key features reflecting the continuous and rapid consumption of water in the reservoir are extracted from the established data set.The application analyzes the water consumption of the reservoir through intelligent monitoring and deep learning, assesses the water trend in real time, and quickly identifies demand surge.The system starts the water pump in advance and adjusts the pressure when consumption accelerates, ensuring timely replenishment of water sources.Introducing machine learning improves the flexibility of the water supply system, optimizes the traditional minimum water level starting method, effectively responds to high demand periods, and stabilizes the supply of agricultural irrigation and residential water demand.

Description

Technical Field

[0001] This invention relates to the field of pressurized water storage technology, and specifically to a pressurized water storage method suitable for rural water supply. Background Technology

[0002] A booster-storage water system typically refers to a device or facility that combines water pressure boosting and water storage functions, and is widely used in rural water supply systems. The basic function of this system is to increase the pressure of water from low-pressure or long-distance water sources to the required pressure, ensuring that water can be smoothly delivered to the point of use. Simultaneously, the system also has a water storage function, storing water when water demand is low for use during peak periods, thus maintaining the stability and reliability of the water supply. In rural areas, due to geographical conditions and pipeline network layout, water pressure is often low. Booster-storage water systems can effectively solve this problem, ensuring that farmers' daily water needs are not affected, especially in irrigation, domestic water, and drinking water.

[0003] Floating ball switches are a common method for identifying water levels in reservoirs, especially in simple and economical applications. The working principle of a floating ball switch is based on buoyancy; the float rises and falls with changes in water level. When the water level rises, the float rises; when the water level falls, the float falls. When the water level reaches a preset minimum or maximum level, the float triggers the switch, thereby starting or stopping the water pump or issuing an alarm signal. This technology is simple, low-cost, and highly reliable, and therefore widely used in homes, farmland irrigation, and water storage tanks.

[0004] The existing technology has the following shortcomings:

[0005] During peak farming seasons, farmers typically employ alternating irrigation methods to ensure each plot of land receives sufficient water, maximizing water resource utilization efficiency and reducing pressure on water sources. Although crops may not be sown at the same time (e.g., rice), variety differences can lead to a large number of crops germinating simultaneously, necessitating timely irrigation to ensure healthy seedling growth. When a large number of fields are irrigated concurrently, the water in reservoirs is rapidly depleted. Furthermore, these reservoirs, in addition to supplying irrigation water, also need to provide water to water plants and residential areas, increasing the pressure on water supply. Continuing to rely on pumps to replenish water when the reservoir level reaches its lowest point may result in insufficient water supply. After the pumps start, the water level in the reservoirs has already dropped to a low level, and the replenishment speed often cannot keep up with demand, especially during periods of high demand when multiple fields are irrigated simultaneously, causing the reservoir level to drop too quickly and resulting in delayed water replenishment. The limited water supply rate of the water pump cannot quickly meet the water needs of multiple farmlands and residents, resulting in periodic instability in water supply. The irrigation system cannot complete the irrigation task within the scheduled time, affecting the overall irrigation efficiency and potentially extending the irrigation cycle. It may also affect the daily water supply of residents.

[0006] The information disclosed in the background section is only intended to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0007] The purpose of this invention is to provide a pressurized water storage method suitable for rural water supply. Through intelligent water consumption monitoring and precise allocation, combined with real-time monitoring and deep learning models, the system can analyze key characteristics of water consumption in reservoirs and intelligently assess water consumption trends. When water consumption increases sharply, the system proactively activates water pumps and dynamically adjusts pressure to ensure timely water replenishment and prevent water supply delays from affecting irrigation tasks. Furthermore, by introducing a machine learning model, the flexibility and response speed of the water supply system are improved, optimizing the traditional minimum water level activation method and ensuring stable water supply during periods of high demand. This effectively meets the dual needs of agricultural irrigation and residential water use, thus solving the problems mentioned in the background section.

[0008] To achieve the above objectives, the present invention provides the following technical solution: a pressurized water storage method suitable for rural water supply, comprising the following steps:

[0009] First, establish a comprehensive real-time monitoring system to obtain current water usage data for the reservoir.

[0010] The collected real-time water volume is stored and managed to establish a structured data set, from which key features reflecting the continuous and rapid consumption of water in the reservoir are extracted.

[0011] Under the detection window, the extracted key features are analyzed in depth, and the analyzed key features are input into a pre-trained deep learning model to perform intelligent water consumption assessment.

[0012] Based on the evaluation results of the deep learning model, the water consumption in the reservoir is divided into two categories: normal consumption and rapid consumption.

[0013] For cases classified as normal consumption, the traditional method of starting the water pump based on the lowest water level in the reservoir will continue to be used to replenish the water source.

[0014] For cases classified as rapidly depleted, the water pumps are started in advance to supply water to the reservoir based on the evaluation results of the deep learning model, and the pressure of the water pumps is adjusted in real time according to the dynamic changes in water consumption.

[0015] Preferably, key features reflecting the continuous and rapid consumption of water in the reservoir are extracted from the established dataset. The extracted features include the fluctuation of water demand and water usage in a short period of time. Under the detection window, the extracted key features are analyzed to generate a demand surge rate factor and a water resource use disturbance factor. The demand surge rate factor quantifies the degree of sharp increase in water demand in the reservoir. By assessing the change in water consumption rate, it reflects the trend of a sharp increase in water demand caused by the simultaneous irrigation of multiple farmlands during periods of high demand. The water resource use disturbance factor quantifies the volatility and instability that occur during water use. By analyzing the fluctuation of water flow, it assesses whether there are drastic fluctuations in water resource consumption during irrigation, reflecting the stability of water supply.

[0016] Preferably, the specific steps for analyzing water demand over a short period of time and generating a demand surge rate factor within the detection window are as follows:

[0017] Within the detection window, the demand fluctuation range is identified based on real-time water demand data. The expression for calculating water demand fluctuation is as follows:

[0018]

[0019] In the formula, D(t) is the water demand at time t, T is the time interval, and D(tT) is the water demand at the time point preceding t. window It is the total duration of the detection window, and ΔD(t) is the fluctuation in water demand at time point t;

[0020] After identifying the fluctuations in water demand, the next step is to calculate the rate of demand surge, as shown in the following expression:

[0021]

[0022] ΔD(t-1) is the fluctuation of water demand at time t-1, γ is the demand change index, α is the time decay correction coefficient, and A(t) is the rate of increase of water demand, that is, the rate of increase of water demand at time t.

[0023] After obtaining the rate of increase in water demand A(t), a nonlinear correction factor is introduced to further adjust the rate of increase in demand. The calculation expression is as follows:

[0024]

[0025] In the formula, β is the demand acceleration correction coefficient, δ is the nonlinear adjustment exponent, ζ is the adjustment constant, exp(-λt) is the time decay factor, λ is the decay rate parameter, and F rate (t) is the corrected rate of increase in water demand;

[0026] Based on the corrected acceleration of the water demand surge rate, the final demand surge rate factor is comprehensively evaluated and calculated as follows:

[0027]

[0028] In the formula, S increase η is the demand surge rate factor, ρ is the dynamic adjustment coefficient, and ρ is the influence coefficient of demand.

[0029] Preferably, the specific steps for analyzing the fluctuation of water usage within the detection window and generating water resource usage disturbance factors are as follows:

[0030] Within the detection window, water usage data is collected from the real-time monitoring system. The acquired data is preprocessed, and features reflecting fluctuations in water usage are extracted from the preprocessed dataset. Rate analysis of changes in water usage is then performed to calculate the rate of change in water consumption. The calculation expression is as follows:

[0031]

[0032] In the formula, W(t) is the amount of water used at time t, W(t-1) is the amount of water used at time t-1, that is, the amount of water used at the previous time, and R(t) is the water consumption rate at time t.

[0033] By calculating the water consumption rate R(t) at each time point, the fluctuation of water consumption is obtained. Based on the consumption rate, a water usage fluctuation index is generated, and the calculation expression is as follows:

[0034]

[0035] In the formula, WI(t) is the water use fluctuation index, N is the total number of time points, i is the time point index, and σ is the standard deviation of the weighting factor, which determines the degree of influence of the time point interval on the fluctuation index.

[0036] After obtaining the water use fluctuation index WI(t), the water use disturbance is then quantified and transformed into a water resource use disturbance factor, calculated as follows:

[0037]

[0038] In the formula, WRUDF is the water resource use disturbance factor, W(ti) is the water resource usage at time ti, W(ti-1) is the water resource usage at the time before time ti, and p is the weighted index of the fluctuation amplitude.

[0039] Preferably, after obtaining the demand surge rate factor and water resource use disturbance factor generated by analyzing and processing the extracted key features, the demand surge rate factor and water resource use disturbance factor are input into a pre-learned deep learning model. The deep learning model generates a water consumption index, and the water consumption index is used to intelligently assess the water consumption in the reservoir.

[0040] Preferably, the generated water consumption index is compared and analyzed with a pre-set water consumption index reference threshold to classify the water consumption in the reservoir. The specific classification steps are as follows:

[0041] If the water consumption index is greater than or equal to the preset reference threshold for water consumption index, the water consumption in the reservoir will be classified as rapid consumption.

[0042] If the water consumption index is less than the preset reference threshold for water consumption index, the water consumption in the reservoir will be classified as normal consumption.

[0043] Preferably, for cases classified as rapidly depleted, based on the evaluation results of the deep learning model, the water pump is started in advance to supply water to the reservoir, and the water pump pressure is adjusted in real time according to the dynamic changes in water consumption. The specific steps are as follows:

[0044] When it is determined that water consumption is in a state of rapid depletion, based on machine learning evaluation results, water pumps are started in advance to replenish the water in the reservoir. The purpose of starting the water pumps in advance is to prevent the water level in the reservoir from continuing to drop to a low point, which would prevent the irrigation needs of farmland from being met. The expression is as follows:

[0045]

[0046] In the formula, Start Time is the startup time. These are the input parameters used to solve for the minimum value of the objective function. WSCI(t) is the water consumption index at time point t. ref It is the reference threshold for the water consumption index;

[0047] After the water pump starts, the pump pressure is dynamically adjusted based on real-time water consumption. The specific adjustment method is based on the dynamic changes of the Water Consumption Index (WSCI), assessing the current consumption rate and automatically adjusting the pump output according to demand. The calculation is expressed as follows:

[0048] Pressure regulation (t) = k·(WSCI(t) - WSCI) ref )

[0049] In the formula, pressure regulation (t) is the amount of pressure adjustment on the pump output at time t, and k is an adjustment coefficient that represents the sensitivity of adjusting the pump pressure according to the change in the water consumption rate.

[0050] While the water pump starts and begins to adjust the pressure, it is also necessary to monitor the water consumption in real time to determine whether to continue adjusting the pump pressure. The expression is as follows:

[0051]

[0052] In the formula, the feedback pressure (t) is the pump pressure adjusted at time t based on the dynamic changes in current water consumption. It is the feedback correction coefficient.

[0053] The technical effects and advantages provided by the present invention in the above technical solution are as follows:

[0054] This invention effectively solves the problem of insufficient water supply during periods of high demand by intelligently monitoring and precisely allocating water consumption. Through a combination of a real-time monitoring system and a deep learning model, the system can analyze key characteristics of water consumption in reservoirs, such as the demand surge rate factor and water resource usage disturbance factor, intelligently assess water consumption trends, and automatically identify whether water consumption has entered a "rapid consumption" state. When the rate of water consumption increases sharply, the system can start the water pumps in advance and dynamically adjust the pump pressure according to demand to ensure timely water replenishment, avoiding delays in irrigation tasks and thus improving the stability of the water supply system and the efficiency of water resource utilization.

[0055] This invention optimizes the traditional water supply method based on starting pumps at the lowest water level by improving the flexibility and response speed of the reservoir water supply system. During periods of high demand, such as simultaneous irrigation of multiple farmlands, the traditional method may result in delayed pump startup, failing to meet water demand in a timely manner. By introducing a machine learning model, the system can assess the dynamic changes in water consumption in real time and proactively start pumps and adjust water supply pressure to quickly respond to changing water demands when demand surges. This flexible water supply scheduling mechanism ensures that the reservoir can stably supply water during periods of high demand, avoiding problems of insufficient water supply and uneven water distribution, thereby improving the efficiency and responsiveness of the water supply system and meeting the dual needs of agricultural irrigation and residential water use. Attached Figure Description

[0056] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0057] Figure 1 This is a flowchart of a pressurized water storage method applicable to rural water supply according to the present invention. Detailed Implementation

[0058] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, they are provided so that the description of this disclosure will be more complete and fully convey the concept of the exemplary embodiments to those skilled in the art.

[0059] This invention provides, for example Figure 1 The illustrated method for pressurized water storage suitable for rural water supply includes the following steps:

[0060] First, establish a comprehensive real-time monitoring system to obtain current water usage data for the reservoir.

[0061] To establish a comprehensive real-time monitoring system for acquiring current water usage data from the reservoir, the first step is to select and install appropriate sensors, such as high-precision water level sensors, flow meters, and water quality sensors, to ensure accurate capture of water level changes, flow data, and water quality conditions. Next, a data acquisition system must be built to transmit data from these sensors via wired (e.g., Ethernet) or wireless (e.g., LoRa, NB-IoT) methods to a central control unit or edge computing device. Then, a data transmission network must be configured to ensure stable and real-time data transmission to a data storage and processing platform, potentially including a local server or cloud server, for centralized management and analysis. Data processing software must be developed or deployed to clean, filter, and format the collected raw data, ensuring its accuracy and consistency. Simultaneously, a user-friendly monitoring interface or dashboard should be established to graphically display real-time water levels, flow rates, and other key parameters, allowing managers to promptly understand the reservoir's operational status. To ensure stable system operation and data continuity, a reliable power supply and backup power or batteries are necessary to handle power outages and other emergencies. Furthermore, regular sensor calibration and maintenance are essential to ensure the accuracy and durability of the monitoring equipment and reduce the failure rate. Finally, implement data security measures, including data encryption, access control, and backup policies, to prevent data loss or unauthorized access. Through these steps, a fully functional, reliable, and efficient real-time monitoring system can be established, ensuring that water usage data from the reservoir can be accurately and promptly acquired and managed, thus providing solid data support for subsequent water resource allocation and intelligent management.

[0062] The collected real-time water volume is stored and managed to establish a structured data set, from which key features reflecting the continuous and rapid consumption of water in the reservoir are extracted.

[0063] The collected real-time water usage data is stored and managed to establish a structured dataset. The specific steps are as follows: First, data acquisition: real-time water usage data is acquired through various sensors installed in the reservoir (such as water level sensors and flow meters). Second, data transmission: the collected data is transmitted to a central database or cloud storage platform via wired or wireless networks. Next, data storage: a reasonable table structure is designed in the database, and data is stored in an orderly manner according to dimensions such as time, location, and flow rate to ensure data structure and standardization. Then, data cleaning: the raw data is filtered and processed to remove noise, outliers, and duplicate data, improving data quality. Finally, data organization and standardization: data from different sources and formats are standardized. The process involves several key steps: First, the data is uniformly converted into a consistent format for easier analysis and processing. Next, data indexing and classification are implemented, creating indexes and category labels to improve retrieval and access efficiency. Then, data backup and security are ensured through regular backups and encryption and access control measures. Following this, data management tools are applied, utilizing database management systems or dedicated data management platforms to simplify data maintenance, querying, and updating. Next, data visualization and monitoring are implemented, using dashboards and charts to visually display data, facilitating real-time monitoring of water usage by management personnel. Finally, the dataset is maintained and updated regularly to ensure its up-to-dateness and accuracy. The purpose of establishing such a structured dataset is to provide a high-quality, standardized data foundation for subsequent key feature extraction and deep learning model training, ensuring that intelligent assessments accurately reflect water consumption in reservoirs, thereby supporting effective water resource management and water supply scheduling, and improving the overall efficiency and reliability of the irrigation system.

[0064] Under the detection window, the extracted key features are analyzed in depth, and the analyzed key features are input into a pre-trained deep learning model to perform intelligent water consumption assessment.

[0065] Key features reflecting the continuous and rapid consumption of water in the reservoir were extracted from the established dataset. These features included the fluctuations in water demand and water usage over a short period. Under a detection window, the extracted key features were analyzed to generate a demand surge rate factor and a water resource use disturbance factor. The demand surge rate factor quantifies the degree of rapid increase in water demand in the reservoir. By assessing changes in the water consumption rate, it reflects the trend of a sharp increase in water demand caused by simultaneous irrigation of multiple farmlands during periods of high demand. The water resource use disturbance factor quantifies the volatility and instability that occur during water use. By analyzing water flow fluctuations, it assesses whether there are drastic fluctuations in water resource consumption during irrigation, reflecting the stability of water supply.

[0066] A surge in water demand within a short period typically indicates a rapid and continuous depletion of water in reservoirs. This surge reflects the simultaneous irrigation of multiple fields, especially during peak farming seasons when multiple crops may be irrigated at the same time. In such cases, the water supply from reservoirs cannot keep pace with the demand, leading to a rapid drop in water levels and accelerated water consumption. Particularly during periods of high demand, when multiple fields begin irrigation simultaneously, the pump capacity is often limited, and the reservoir's water supply cannot be replenished promptly, further exacerbating the rate of water consumption. This short-term surge in demand demonstrates a non-linear increase in reservoir water consumption, usually accompanied by a lag in water replenishment. Therefore, a short-term surge in water demand not only serves as a direct signal of water supply pressure but also reflects the continuous and rapid depletion of water in reservoirs, indicating the need for more refined scheduling strategies, such as starting pumps in advance and adjusting supply pressure, to ensure the successful completion of irrigation tasks.

[0067] The specific steps for analyzing water demand over a short period of time and generating a demand surge rate factor within the detection window are as follows:

[0068] Within the detection window, the demand fluctuation range is identified based on real-time water demand data. The goal of this step is to pinpoint periods of rapid changes in water demand, typically manifested as a sudden jump from a low to a high level. The expression for calculating water demand fluctuation is as follows:

[0069]

[0070] In the formula, D(t) is the water demand at time t, T is the time interval, and D(tT) is the water demand at the time point preceding t. window It is the total duration of the detection window, and ΔD(t) is the fluctuation in water demand at time point t;

[0071] The purpose of this step is to calculate the dramatic fluctuations in water demand over a short period of time, laying the foundation for the generation of the index in subsequent steps.

[0072] After identifying the fluctuations in water demand, the next step is to calculate the rate of demand surge. By calculating the acceleration of the change in demand, it is determined whether the increase in demand exhibits characteristics of a surge. The calculation expression is as follows:

[0073]

[0074] ΔD(t-1) is the fluctuation of water demand at time t-1, γ is the demand change index, which is used to represent the exponential effect of the increase in demand, α is the time decay correction coefficient, which reflects the relationship between demand change and time, and adjusts the relationship between the surge rate of water demand and the growth of time. A(t) is the surge rate of water demand, that is, the surge rate of water demand at time t.

[0075] The demand change index γ is an exponentially decaying coefficient used to represent the degree to which the rate of change in water demand decays as demand increases. As water demand increases, the sensitivity to changes in demand gradually weakens, meaning that the rate of water consumption may not continue to grow linearly. Therefore, the role of the demand change index γ is to adjust the non-linear characteristics of water demand growth, making the rate of surge in water demand relatively match the growth in water consumption. A smaller γ value increases sensitivity to changes in water demand, while a larger γ value can reduce overreaction under high demand and avoid excessively amplifying the rate of demand surge.

[0076] The time decay correction factor α is used to adjust for time effects, ensuring that the rate of change in water demand is adjusted reasonably over time. Over time, surges in water demand may be influenced by changes in environmental conditions, climate change, or irrigation patterns, exhibiting different dynamic trends. The role of the time decay correction factor α is to correct for the rate of water demand surges over time, adapting to long-term trends in water demand changes. For example, during periods of high water consumption, the time decay correction factor helps assess the persistence and cyclical fluctuations in demand, avoiding unreasonable demand surge responses over long periods and ensuring more stable and accurate predictions of water consumption.

[0077] After obtaining the rate of increase in water demand A(t), a nonlinear correction factor is introduced to further adjust the rate of increase in demand, especially when dealing with complex water resource supply and demand relationships. The calculation expression is as follows:

[0078]

[0079] In the formula, β is the demand acceleration correction coefficient, used to control the influence of the demand surge rate in nonlinear adjustment, determining the contribution of the demand surge rate A(t) to the final demand surge rate factor; δ is the nonlinear adjustment index, controlling the nonlinear adjustment intensity of the demand surge rate, determining the degree of attenuation of the demand surge rate to the final rate factor; ζ is the adjustment constant, used to fine-tune the amplitude of the nonlinear correction factor, its function being to provide a basic increment value for the correction factor during the demand surge; exp(-λt) is the time decay factor; λ is the decay rate parameter; and F... rate (t) is the corrected rate of increase in water demand;

[0080] Based on the corrected acceleration of the water demand surge rate, the final demand surge rate factor is comprehensively evaluated and calculated as follows:

[0081]

[0082] In the formula, S increase η is the demand surge rate factor, ρ is the dynamic adjustment coefficient, and ρ is the influence coefficient of demand.

[0083] The dynamic adjustment coefficient refers to the parameter of the water pump supply pressure or flow rate that is automatically adjusted according to the actual changes in water consumption during real-time monitoring and evaluation to cope with instantaneous changes in demand. When demand surges or water consumption intensifies, the dynamic adjustment coefficient will change accordingly, allowing the water supply system to flexibly adjust in a short time and avoid imbalances in water supply or insufficient pump output. Its function is to improve the adaptability and response speed of the water supply system, ensuring that the irrigation system can operate smoothly under different loads and ensuring a stable and continuous water supply by rapidly responding to changes in real-time water flow and demand.

[0084] The demand impact coefficient represents the degree to which changes in farmland water demand affect water consumption in reservoirs under different irrigation conditions. This coefficient considers multiple factors, such as climate change, farmland type, and crop growth stage, to assess the impact of sudden or persistent demand on the rate of water consumption. Its purpose is to quantify the actual impact of demand changes on water consumption, ensuring that the water supply system can accurately adjust its output when water demand increases, thus avoiding the risks of insufficient or excessive water supply. The demand impact coefficient helps to more accurately predict fluctuations in water demand, thereby providing data support for water allocation and management and optimizing the execution of irrigation tasks.

[0085] Within the detection window, a higher value for the demand surge rate factor, generated after analyzing water demand over a short period, indicates a sustained and rapid depletion of water in the reservoir. A large demand surge rate factor signifies a significant increase in the rate of water consumption, a rapid decline in reservoir water levels, and a delayed recovery of water resources, failing to meet the increasing demand in a timely manner. Conversely, a smaller value indicates a more stable increase in water demand, a more consistent rate of water consumption, and no rapid depletion of water in the reservoir.

[0086] Drastic fluctuations in water usage typically indicate a rapid and continuous depletion of water in reservoirs. This is primarily because the fluctuations reflect the instability of water consumption and the drastic changes in instantaneous demand. In farmland irrigation, such dramatic fluctuations often occur when multiple farmers are irrigating simultaneously, especially during peak seasons. When multiple fields are irrigated concurrently, water consumption often surges instantaneously, causing a rapid drop in reservoir levels. If irrigation demand is high and the water supply system fails to adjust in time, water consumption will exhibit a drastic fluctuation trend. This fluctuation indicates that the pump's capacity is not effectively keeping up with demand changes, making the water supply process unstable and potentially leading to water shortages. Drastic fluctuations not only signify rapid water consumption but may also lead to delayed replenishment of reservoirs, causing water levels to drop too quickly and disrupting the stable operation of the water supply system. In short, drastic fluctuations in water usage are a significant signal of continuous and rapid depletion of water in reservoirs, usually indicating a potential risk to the water supply and necessitating optimized water supply scheduling to alleviate this pressure.

[0087] Under the detection window, the specific steps for analyzing the fluctuation of water usage and generating water resource usage disturbance factors are as follows:

[0088] Within the detection window, water usage data is collected from the real-time monitoring system. The acquired data is preprocessed, and features reflecting fluctuations in water usage are extracted from the preprocessed dataset. Key features of these fluctuations typically include instantaneous rate of change, frequency of change, and amplitude of change. Rate analysis is performed on the changes in water usage to calculate the rate of change in water consumption. The calculation expression is as follows:

[0089]

[0090] In the formula, W(t) is the amount of water used at time t, W(t-1) is the amount of water used at time t-1, that is, the amount of water used at the previous time, and R(t) is the water consumption rate at time t.

[0091] By calculating the water consumption rate R(t) at each time point, the fluctuation of water consumption is obtained. If the rate value is large in a certain period, it means that the water consumption fluctuates drastically and is consumed rapidly. Based on the consumption rate, a water consumption fluctuation index is generated, and the calculation expression is as follows:

[0092]

[0093] In the formula, WI(t) is the water use fluctuation index, N is the total number of time points, i is the time point index, and σ is the standard deviation of the weighting factor, which determines the degree of influence of the time point interval on the fluctuation index.

[0094] The above steps can effectively highlight the impact of recent changes on fluctuations in water use and avoid interference from long-term changes.

[0095] After obtaining the water use fluctuation index WI(t), the water use disturbance is then quantified and transformed into a water resource use disturbance factor, calculated as follows:

[0096]

[0097] In the formula, WRUDF is the water resource use disturbance factor, W(ti) is the water consumption at time ti, W(ti-1) is the water consumption at the time before time ti, and p is the weighted index of the fluctuation amplitude, reflecting the degree of increase in the water consumption rate.

[0098] The fluctuation amplitude weighted index is a comprehensive indicator used to quantify the intensity and magnitude of fluctuations in water usage. Through weighted analysis of changes in water consumption, it reflects the degree of water volume fluctuation and its impact on the stability of the water supply system. This index assigns different weights to fluctuations in different time periods to more accurately reflect the impact of fluctuations during certain critical periods on the entire water supply system. For example, if the fluctuation in a certain period has a greater impact on the system, it can be given a higher weight, thereby enhancing the contribution of that period's fluctuation to the fluctuation amplitude weighted index. Its function is to help monitor the stability of water supply in real time, identify fluctuation patterns that may lead to uneven or insufficient water supply, and thus provide decision support for adjusting water supply strategies and optimizing irrigation plans, ensuring the balance and stability of water consumption in reservoirs, and avoiding instability in the water supply system due to excessive fluctuations.

[0099] Within the detection window, a higher value for the water resource use disturbance factor, generated after analyzing the fluctuations in water usage, generally indicates that the water in the reservoir is being consumed rapidly and continuously. This is because the water resource use disturbance factor reflects the volatility and instability in the water use process. When multiple farmlands are irrigated simultaneously, drastic fluctuations in water flow indicate a sharp increase in demand and rapid changes in water consumption. Conversely, when water usage fluctuations are small, water flow is stable, and the disturbance index value is low, it indicates that the rate of water consumption is relatively stable, and the water resource is not being consumed rapidly.

[0100] After obtaining the demand surge rate factor and water resource use disturbance factor generated by analyzing and processing the extracted key features, the demand surge rate factor and water resource use disturbance factor are input into a pre-learned deep learning model. The deep learning model generates a water consumption index, and the water consumption index is used to intelligently assess the water consumption in the reservoir.

[0101] The deep learning model is not limited here, but it can achieve the effect of increasing the rate of demand surge factor S. increase Both the water resource perturbation factor WRUDF and the deep learning model that generates the water consumption index WSCI can be used for comprehensive analysis of water resources. In order to realize the technical solution of the present invention, the present invention provides a specific implementation method.

[0102] The formula for generating the Water Consumption Index (WSCI) is as follows:

[0103]

[0104] In the formula, p1 and p2 are the demand surge rate factors S. increase The preset proportional coefficients of the water resource disturbance factor WRUDF are used, and p1 and p2 are both greater than 0.

[0105] As can be seen from the water consumption index, under the detection window, the larger the value of the demand surge rate factor generated after analyzing the water demand in a short period of time, and the larger the value of the water resource use disturbance factor generated after analyzing the fluctuation of water usage, the larger the value of the water consumption coefficient generated under the detection window indicates that the current water storage tank is in a state of continuous and rapid consumption. Conversely, it indicates that the current water consumption of the water storage tank is stable and there is no trend of rapid consumption.

[0106] The preset proportional coefficient refers to the weighting coefficient artificially set when calculating the Water Consumption Index (WSCI) to balance the influence of different factors on the results. In the formula, p1 and p2 are the demand surge rate factors S... increase The preset proportional coefficients for the water resource use disturbance factor WRUDF are used to reflect the relative importance of each factor in the water consumption assessment process. Due to the demand surge rate factor S... increase The water resource use disturbance factor (WRUDF) and the water resource use disturbance factor may have different dimensions or different degrees of contribution to water consumption. The preset proportional coefficient adjusts the influence of the two in the calculation of the water resource consumption index (WSCI) by assigning weights, so as to ensure that the results are more reasonable and accurate.

[0107] For example, if the rate of demand surge has a greater impact on water consumption, p1 will be set relatively high; if the fluctuations in water resource use are more significant, p2 will be given a higher weight. This proportional coefficient can be determined through historical data analysis, practical application experience, or the training results of deep learning models, ultimately achieving reasonable quantification and comprehensive analysis of various key factors, ensuring that the calculation results of the Water Consumption Index (WSCI) can truly reflect the actual situation of current water consumption.

[0108] A pre-learned deep learning model refers to a trained and optimized neural network model capable of prediction and evaluation based on historical data, features, and patterns. In this scenario, the deep learning model is trained using a large amount of water consumption data, irrigation demand, and other relevant features (such as water flow fluctuations and reservoir water level changes). This data, after preprocessing steps such as feature extraction, data cleaning, and standardization, is input into the deep learning model, which learns the intrinsic relationship between water consumption and water flow fluctuations. Through multiple iterations and weight adjustments, the model gradually improves its ability to predict water consumption. Once the deep learning model is fully trained, it possesses the ability to identify and predict water consumption trends and recognize abnormal consumption patterns. The model's training process not only relies on input features but also references multi-dimensional data sources such as historical water supply patterns and changes in irrigation demand, thus forming a predictive model tailored to different water use scenarios.

[0109] By inputting demand surge rate factors and water resource use disturbance factors, a pre-learned deep learning model can intelligently generate a water consumption index. This index reflects the specific trend of water consumption in reservoirs. Combined with the input factors, the model intelligently assesses the rate of water consumption, supply-demand balance, and stability of the water supply system based on learned patterns. When reservoir water is rapidly depleted, the deep learning model can promptly detect potential water supply crises and provide decision support for subsequent pump scheduling. Simultaneously, the deep learning model can self-adjust, gradually adapting to the water consumption characteristics of different time periods and identifying potential factors that may lead to unstable water supply. This intelligent assessment method far surpasses traditional rule-based water supply scheduling methods because it can make more accurate predictions and dynamic adjustments with the support of multiple variables and complex relationships, ensuring that farmland irrigation needs are met in a timely manner.

[0110] Based on the evaluation results of the deep learning model, the water consumption in the reservoir is divided into two categories: normal consumption and rapid consumption.

[0111] The generated water consumption index is compared and analyzed with a pre-set reference threshold for water consumption index to classify the water consumption in the reservoir. The specific classification steps are as follows:

[0112] If the water consumption index is greater than or equal to the preset reference threshold for water consumption index, the water consumption in the reservoir will be classified as rapid consumption.

[0113] If the water consumption index is less than the preset reference threshold for water consumption index, the water consumption in the reservoir will be classified as normal consumption.

[0114] Normal consumption refers to water usage within the expected range, meeting current irrigation needs and water replenishment capacity; rapid consumption refers to water usage exceeding expectations, potentially leading to insufficient water supply.

[0115] For cases classified as normal consumption, the traditional method of starting the water pump based on the lowest water level in the reservoir will continue to be used to replenish the water source.

[0116] The continued use of the traditional method of starting water pumps at the lowest water level in the reservoir to replenish the water supply aims to maintain the stability and efficient operation of the water supply system under normal consumption conditions. This method is suitable for situations where water consumption is within the expected range, maintaining a balance between supply and replenishment without requiring additional intervention or complex adjustments, and minimizing system load and resource waste. Furthermore, by maintaining the existing management approach, the pumps only start when the water level drops to its lowest point, which helps save energy, reduce equipment wear, and extend pump lifespan. Simultaneously, the system continuously monitors water level changes during operation. When abnormal water consumption patterns occur (such as entering a rapid consumption state), intelligent management strategies can be triggered in a timely manner for dynamic adjustments, thereby ensuring the reliability and flexibility of the water supply system and guaranteeing the irrigation needs of farmland.

[0117] For cases classified as rapidly depleted, the water pumps are started in advance to supply water to the reservoir based on the evaluation results of the deep learning model, and the pressure of the water pumps is adjusted in real time according to the dynamic changes in water consumption.

[0118] For cases classified as rapidly depleted, based on the evaluation results of the deep learning model, the water pumps are started in advance to supply water to the reservoir, and the water pump pressure is adjusted in real time according to the dynamic changes in water consumption. The specific steps are as follows:

[0119] When it is determined that water consumption is in a state of rapid depletion, based on machine learning evaluation results, water pumps are activated in advance to replenish the water in the reservoir. During this stage, it is necessary to ensure that the water pumps can respond promptly and to dynamically adjust the water supply strategy according to the specific needs of the reservoir. The purpose of activating the water pumps in advance is to prevent the water level in the reservoir from continuing to drop to a low point, thus failing to meet the irrigation needs of farmland. The expression is as follows:

[0120]

[0121] In the formula, Start Time is the start-up time, referring to the timing of starting the water pump. These are the input parameters used to find the minimum value of the objective function. Here, they represent finding the most suitable time point t within the time range Δt. WSCI(t) is the water consumption index at time point t. ref It is the reference threshold for the water consumption index;

[0122] After the water pump starts, its pressure is dynamically adjusted based on real-time water consumption. This pressure adjustment ensures a stable and continuous water supply to meet the needs of farmland. The specific adjustment method is based on the dynamic changes of the Water Consumption Index (WSCI), assessing the current consumption rate and automatically adjusting the pump output according to demand. The calculation is as follows:

[0123] Pressure regulation (t) = k·(WSCI(t) - WSCI) ref )

[0124] In the formula, pressure regulation (t) is the amount of pressure adjustment on the pump output at time t. It determines whether the pump output pressure increases or decreases to ensure that the water source can be replenished in time. k is an adjustment coefficient, which represents the sensitivity of adjusting the pump pressure according to the change in the water consumption rate.

[0125] This step indicates that as the rate of water consumption increases, the pressure of the water pump increases accordingly to ensure that the water source can be replenished in a timely manner.

[0126] When the water consumption index WSCI ≥ WSCI ref When the water level drops further, the pump's output pressure will increase appropriately to quickly replenish the water supply. If the WSCI value gradually returns to the normal range, the pump pressure will decrease accordingly to avoid over-supply and energy waste.

[0127] While the water pump starts and begins to regulate pressure, it is also necessary to monitor water consumption in real time to determine whether to continue adjusting the pump pressure. This process includes continuous evaluation of the water pump's supply status and dynamic optimization of the pump's pressure regulation strategy through a feedback mechanism to ensure the stability and efficiency of the water supply. The expression is as follows:

[0128]

[0129] In the formula, the feedback pressure (t) is the pump pressure adjusted at time t based on the dynamic changes in current water consumption. It is the feedback correction coefficient, which represents the responsiveness to real-time monitoring results.

[0130] The feedback mechanism continuously optimizes the water supply strategy by comparing the actual water consumption with the expected results in real time, ensuring that the water pump always operates at its optimal efficiency point.

[0131] By precisely controlling the start-up timing and operating pressure of the water pumps, the system ensures that the reservoir can be replenished promptly and maintain a stable water supply even when water is rapidly depleted. During farmland irrigation, especially during periods of high demand, simultaneous irrigation of multiple fields can cause a rapid drop in the reservoir's water level. Relying solely on traditional pump start-up mechanisms (starting the pumps only after the water level reaches its lowest point) may result in delayed water recovery, affecting irrigation efficiency and potentially leading to water shortages. Through intelligent evaluation using a deep learning model, the system can monitor and analyze the Water Consumption Index (WSCI) in real time, predict changes in water demand, and thus start the pumps in advance to replenish the reservoir.

[0132] Furthermore, the dynamic changes in water consumption require real-time adjustment during pump operation to adapt to varying water consumption levels. When water consumption accelerates, the system automatically adjusts the pump's operating pressure based on predictions to increase the water supply rate and ensure timely fulfillment of water demands. This dynamic adjustment mechanism not only effectively prevents water supply instability but also guarantees that the reservoir maintains a sufficient water supply even during rapid consumption, thereby ensuring the smooth completion of irrigation tasks, improving water resource utilization efficiency, reducing waste, and ensuring that the normal irrigation needs of farmland are met.

[0133] This invention effectively solves the problem of insufficient water supply during periods of high demand by intelligently monitoring and precisely allocating water consumption. Through a combination of a real-time monitoring system and a deep learning model, the system can analyze key characteristics of water consumption in reservoirs, such as the demand surge rate factor and water resource usage disturbance factor, intelligently assess water consumption trends, and automatically identify whether water consumption has entered a "rapid consumption" state. When the rate of water consumption increases sharply, the system can start the water pumps in advance and dynamically adjust the pump pressure according to demand to ensure timely water replenishment, avoiding delays in irrigation tasks and thus improving the stability of the water supply system and the efficiency of water resource utilization.

[0134] This invention optimizes the traditional water supply method based on starting pumps at the lowest water level by improving the flexibility and response speed of the reservoir water supply system. During periods of high demand, such as simultaneous irrigation of multiple farmlands, the traditional method may result in delayed pump startup, failing to meet water demand in a timely manner. By introducing a machine learning model, the system can assess the dynamic changes in water consumption in real time and proactively start pumps and adjust water supply pressure to quickly respond to changing water demands when demand surges. This flexible water supply scheduling mechanism ensures that the reservoir can stably supply water during periods of high demand, avoiding problems of insufficient water supply and uneven water distribution, thereby improving the efficiency and responsiveness of the water supply system and meeting the dual needs of agricultural irrigation and residential water use.

[0135] The foregoing has only described certain exemplary embodiments of the present invention by way of illustration. Undoubtedly, those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the foregoing drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. A pressurized water storage method suitable for rural water supply, characterized in that, Includes the following steps: Establish a comprehensive real-time monitoring system to obtain current water usage data for the reservoir; The collected real-time water volume is stored and managed to establish a structured dataset. Key features reflecting the continuous and rapid consumption of water in the reservoir are extracted from the dataset, including the fluctuation of water demand and water usage in a short period of time. Under the detection window, the extracted key features are analyzed in depth to generate demand surge rate factor and water resource use disturbance factor, which are then input into a pre-trained deep learning model for intelligent water consumption assessment. Based on the evaluation results of the deep learning model, it is determined whether to start the water pump in advance to supply water to the reservoir. The specific steps for generating the demand surge rate factor are as follows: After identifying the fluctuations in water demand, the rate of increase in water demand is calculated using the following expression: , It is a point in time. Fluctuations in water demand over time It is a demand change index. It is the time decay correction factor. It is a point in time. The demand for water is increasing rapidly at all times. It is a point in time. Water demand at any given time; By further adjusting the formula by introducing a nonlinear correction factor, the calculation expression is as follows: In the formula, It is the demand acceleration correction factor. It is a non-linear adjustment index. It is the adjustment constant. It is the time decay factor. It is the decay rate parameter. This is the revised rate of increase in water demand; Based on the revised rate of increase in water demand, the final demand surge rate factor is comprehensively evaluated and calculated as follows: In the formula, It is the rate of demand surge factor. It is a dynamic adjustment coefficient. It is the influence coefficient of demand; The specific steps for generating water resource use disturbance factors are as follows: A rate analysis of the change in water usage is performed to calculate the water consumption rate, and the calculation expression is as follows: In the formula, It is a point in time. Water usage at any time It is a point in time. Water usage at any time It is time The rate of water consumption at any given time; Based on the consumption rate, a water resource usage fluctuation index is generated, calculated as follows: In the formula, It is a water source usage fluctuation index. It is the total number of time points. It is a time point index. The standard deviation of the weighting factor determines the degree of influence of the time interval on the volatility index. Then, the disturbance caused by water use is quantified and transformed into a water resource use disturbance factor, calculated as follows: In the formula, It is a disturbance factor in water resource use. It is a point in time. Water usage at any time It is a point in time. Water usage at the previous moment It is a weighted index of volatility.

2. The pressurized water storage method for rural water supply according to claim 1, characterized in that, Within the detection window, the demand fluctuation range is identified based on real-time water demand data. The expression for calculating water demand fluctuation is as follows: In the formula, It is a point in time. Water demand at any given time It is a time interval. It is a point in time. The water demand at the previous moment, It is the total duration of the detection window. It is a point in time. Fluctuations in water demand at any given time.

3. The pressurized water storage method for rural water supply according to claim 1, characterized in that, After obtaining the demand surge rate factor and water resource use disturbance factor generated by analyzing and processing the extracted key features, the demand surge rate factor and water resource use disturbance factor are input into a pre-learned deep learning model. The deep learning model generates a water consumption index, and the water consumption index is used to intelligently assess the water consumption in the reservoir.

4. A pressurized water storage method suitable for rural water supply according to claim 3, characterized in that, The generated water consumption index is compared and analyzed with a pre-set reference threshold for water consumption index to classify the water consumption in the reservoir. The specific classification steps are as follows: If the water consumption index is greater than or equal to the preset reference threshold for water consumption index, the water consumption in the reservoir will be classified as rapid consumption. If the water consumption index is less than the preset reference threshold for water consumption index, the water consumption in the reservoir will be classified as normal consumption. For cases classified as normal consumption, the traditional method of starting the water pump based on the lowest water level in the reservoir will continue to be used to replenish the water source. For cases classified as rapidly depleted, the water pumps are started in advance to supply water to the reservoir based on the evaluation results of the deep learning model, and the pressure of the water pumps is adjusted in real time according to the dynamic changes in water consumption.

5. A pressurized water storage method suitable for rural water supply according to claim 4, characterized in that, For cases classified as rapidly depleted, based on the evaluation results of the deep learning model, the water pumps are started in advance to supply water to the reservoir, and the water pump pressure is adjusted in real time according to the dynamic changes in water consumption. The specific steps are as follows: When it is determined that water consumption is in a state of rapid depletion, based on machine learning evaluation results, water pumps are started in advance to replenish the water in the reservoir. The purpose of starting the water pumps in advance is to prevent the water level in the reservoir from continuing to drop to a low point, which would prevent the irrigation needs of farmland from being met. The expression is as follows: In the formula, It is the start-up time. These are the input parameters used to find the minimum value of the objective function. It is a point in time. Water consumption index at that time It is the reference threshold for the water consumption index; After the water pump starts, the pump pressure is dynamically adjusted based on real-time water consumption. The specific adjustment method is based on the water consumption index. The dynamic changes automatically adjust the water pump output, and the calculation expression is as follows: In the formula, At a certain point in time The pressure output of the water pump is adjusted in real time. It is an adjustment coefficient, representing the sensitivity of adjusting the water pump pressure according to changes in the water consumption index; While the water pump starts and begins to adjust the pressure, it is also necessary to monitor the water consumption in real time to determine whether to continue adjusting the pump pressure. The expression is as follows: In the formula, At a certain point in time The water pump pressure is adjusted constantly based on the dynamic changes in current water consumption. It is the feedback correction coefficient.

Images