Water production control method and device, electronic equipment and storage medium

Abstract

The present disclosure provides a water production control method, device, electronic device and storage medium, which relate to the field of artificial intelligence technology, especially to the field of industrial scheduling technology and industrial Internet technology. The specific implementation scheme is: obtaining the water production time range within the current target time; determining the available water information of the water production system corresponding to at least one expected water production time within the water production time range; determining the target water production time required for water production from the at least one expected water production time based on the water consumption within the current target time and the available water information; controlling the water production system to produce water within the target water production time. According to the present disclosure, the accurate determination of the target water production time and the accurate control of the water production of the water production system can be achieved.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, in particular to industrial scheduling technology and industrial Internet technology, and specifically to a water production control method and device, electronic equipment and storage medium. Background Art

[0002] In a waterworks, a water treatment system draws water from the source and processes it through multiple layers of filtration, impurity precipitation, and disinfection to produce usable water for residents. Currently, the timing of water production in this system is manually controlled based on experience. In practice, this control lacks precision, resulting in either excessive or insufficient water production. Summary of the Invention

[0003] The present disclosure provides a water production control method, a water production control device, an electronic device, and a storage medium.

[0004] According to one aspect of the present disclosure, a water production control method is provided, comprising:

[0005] Get the water production time range within the current target time;

[0006] Determining available water information of the water production system corresponding to at least one expected water production time within the water production time range;

[0007] Determining a target water production time for required water production from the at least one expected water production time according to the water consumption within the current target time and the available water information;

[0008] The water production system is controlled to produce water within the target water production time.

[0009] According to another aspect of the present disclosure, there is provided a water production control device, comprising:

[0010] The first acquisition unit is used to obtain the water production time range within the current target time;

[0011] a first determining unit, configured to determine available water information of the water production system corresponding to at least one expected water production time within the water production time range;

[0012] a second determining unit, configured to determine a target water production time for required water production from the at least one expected water production time according to the water consumption within the current target time and the available water information;

[0013] A control unit is used to control the water production system to produce water within the target water production time.

[0014] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein,

[0015] The memory stores instructions that can be executed by the at least one processor. The instructions are executed by the at least one processor to enable the at least one processor to perform the method in any embodiment of the present disclosure.

[0016] According to yet another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided. The computer instructions are used to cause a computer to execute the method in any embodiment of the present disclosure.

[0017] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, which implements the method in any embodiment of the present disclosure when executed by a processor.

[0018] According to the present disclosure, based on the water consumption within the current target time and the available water information of the water production system corresponding to at least one expected water production time, the required water production time is determined from the at least one expected water production time, thereby accurately determining the water production time in smaller time slices relative to the current target time, and achieving automatic and accurate determination of the target water production time required for water production. This solution for accurately determining the target water production time facilitates precise control of water production in the water production system, significantly avoiding the problems caused by manually determining water production times based on experience.

[0019] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings are provided to facilitate a better understanding of the present invention and do not constitute a limitation of the present disclosure.

[0021] Figure 1 It is a schematic diagram of the composition structure of the water production system disclosed in the present invention;

[0022] Figure 2 1 is a schematic diagram of an implementation flow of a water production control method embodiment disclosed herein;

[0023] Figure 3 is a schematic diagram of the water production parameters monitored by the present disclosure;

[0024] Figure 4 is a schematic diagram of the time delay generated in the water production system of the present disclosure;

[0025] Figure 5 is a schematic diagram comparing the working capacities of multiple alternative water pumps disclosed herein;

[0026] Figure 6 The composition structure of the water control device embodiment disclosed in the present invention Figure 1 ;

[0027] Figure 7 The composition structure of the water control device embodiment disclosed in the present invention Figure 2 ;

[0028] Figure 8 4 is a block diagram of an electronic device used to implement the water production control method embodiment of the present disclosure. DETAILED DESCRIPTION

[0029] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0030] Before introducing the technical solution of the embodiment of the present disclosure, a water production process of the water production system of the water plant is generally described. Figure 1 FIG. 1 is a structural diagram of the water production system of the waterworks disclosed herein. Figure 1 As shown, the water production system includes:

[0031] The water intake pumphouse, also known as the source pumphouse or primary pumphouse, draws water from sources such as rivers and groundwater systems, delivering it to water purification facilities or directly to surface water intake pumphouses serving users. The water intake pumphouse in a water production system requires water from the source to produce water. The intake pumps control the water source and supply the system with the necessary water. If the intake pumps are not drawing water, water production cannot proceed normally.

[0032] In municipal water supply, distribution wells distribute source water. Adding substances such as ozone and sodium hypochlorite to the folded plate flocculation tank purifies the source water.

[0033] The function of the horizontal flow sedimentation tank is to precipitate and remove the flocs in the water passing through the folded plate flocculation tank. The generated wastewater is recycled by the recovery pool, and the remaining water is filtered by the V-type filter, extracted from the lift pump room, and filtered by the carbon filter to reach the clear water tank.

[0034] The water production process in a water system begins with the water being drawn from the source by a water pump and processed through a series of steps, resulting in water ready for injection into the clean water tank. In municipal water supply, usable water from the clean water tank is drawn into a suction well, from which the water pumphouse draws water to provide water to residents.

[0035] As you can understand, a clean water tank typically contains water for residents' use. In practice, the clean water tank is set with lower and upper limits, with the water level in the clean water tank positioned between these limits to prevent problems with water supply to residents due to insufficient storage. The water in the clean water tank is obtained by the water production system through the aforementioned water production process.

[0036] In the related solutions, the control of when to start the water production system is done manually, such as manually relying on experience to decide when to start the water production system to produce water, and to produce water in time to avoid the occurrence of failure to provide normal water supply to residents. The intelligence of the water production system cannot be reflected based on manual experience, and there may be errors based on manual experience. The technical solution of the embodiment of the present disclosure can be considered as a technical solution for the water production system to intelligently and accurately determine the time when water production is required (target water production time), and can also be considered as a solution for automatically controlling the water production system based on the target water production time. Among them, obtaining the water production time range is equivalent to obtaining a reasonable time range for staff to stay in the water plant, so as to avoid the problem of no staff on site for maintenance during the process of automatic water production problems.

[0037] The technical solutions of the embodiments of the present disclosure are described below.

[0038] Figure 2 FIG. 1 is a schematic diagram of the implementation flow of the water production control method embodiment disclosed in the present invention. Figure 2 As shown, the method is applied to a water production control device, and the method includes:

[0039] S201: Acquire a water production time range within a current target time based on historical data.

[0040] In this step, the current target time may be the current water production cycle of the periodic water production cycle. For example, taking the water production cycle as 1 day as an example, the current target time may be the current day.

[0041] The water supply time range can be a randomly selected time period within the current target time, or it can be a time period derived from historical data. For example, the water supply time range can be determined based on historical water supply times that meet water demand. For example, the current target time (e.g., the same time period as yesterday's historical water supply time, e.g., 9:00-14:00) can be used as the water supply time range within the current target time. The water supply time range can also be determined based on the specific controlled time of the water supply system and the historical water supply time that meets water demand. For example, the specific controlled time of the water supply system includes the duty hours of the water supply system staff, or the time when the duty staff of the water supply system meets preset requirements. Combining historical data can determine historical water supply times that meet residential and / or commercial water use requirements. The water supply time range can be obtained by intersecting the specific controlled time and the historical water supply time. Of course, this is merely an example of determining the water supply time range, and the specific implementation is not limited to this.

[0042] For example, the water production time range is a time period obtained based on historical data, such as 9:00-14:00 or 10:00-19:00 of the current day.

[0043] With this water production timeframe, water plant staff can work within it, rather than being bound by fixed hours. This effectively avoids issues caused by unattended water production. During periods outside the target timeframe, the water production system can be stopped or uncontrolled, saving energy. The water production timeframe is based on historical data, ensuring accuracy.

[0044] It is understood that, taking a month as an example, the water supply time range for each day within that month can be the same or different. Furthermore, the water supply time range can be the same for some days and different for others. In practical applications, water supply time range information for the current target time can be obtained and saved based on historical data prior to the current target time. The saved information can then be retrieved when the current target time arrives.

[0045] S202: Determine available water information of the water production system corresponding to at least one expected water production time within the water production time range.

[0046] In this step, the expected water supply time can be any one, two, or more times within the water supply time range. The expected water supply time can be a random time selected from the water supply time range, or it can be a time obtained by dividing the water supply time range into time intervals, such as every five minutes or every one minute within the water supply time range. The available water information corresponding to the expected water supply time can be the liquid level value of the clear water tank in the water supply system at the expected water supply time. The available water information corresponding to each expected water supply time can be obtained by reading the monitored value of the clear water tank liquid level in the water supply system.

[0047] S203: Determine a target water production time for required water production from at least one expected water production time according to the water consumption and available water information within the current target time.

[0048] Available water information can be: water quantity information reflecting that the water production system has been fully produced and meets the water quality requirements for residential or commercial water. Exemplarily, available water information includes, but is not limited to, liquid level information of the clear liquid tank in the water production system that meets the residential water requirements. Knowing the liquid level information of the clear liquid tank, combined with the capacity of the clear liquid tank, can determine the current water consumption that meets the residential water requirements. Thus, by combining the water consumption within the current target time with the available water information, the amount of water to be produced can be determined, and then the amount of water to be produced can be allocated to each expected water production time, so that the target water production time required for water production can be determined from at least one expected water production time.

[0049] The target water supply time is the time at which water supply is required. The target water supply time is determined, for example, by selecting the desired water supply time from at least one expected water supply time. Thus, one or more target water supply times may exist within a water supply time range. If there are multiple target water supply times, they can be distributed continuously or discretely in the time domain.

[0050] S204: Control the water production system to produce water within the target water production time.

[0051] In this step, a command for controlling the water production system to produce water may be sent to the water production system at the target water production time, so as to control the water production system to produce water within the target water production time.

[0052] In S201-S204, based on the water consumption within the current target time and the available water information of the water system corresponding to at least one desired water production time, a target water production time is determined from the at least one desired water production time. This allows for precise determination of water production times in smaller time slices within the current target time. This enables automatic and accurate determination of the target water production time. This intelligent and precise solution for determining target water production times significantly avoids the problems associated with manually determining water production times based on experience.

[0053] This automatic and precise determination of the target water production time enables automatic and precise control of the water production system, such as ensuring that the system produces water within the target water production time. Furthermore, the obtained water production time range acts as a benchmark time from which the target water production time is precisely determined, allowing the water production system to automatically produce water at a more precise time. This avoids unnecessary water production when the system is still producing water when it doesn't need it, or when the system isn't producing water when it should.

[0054] For example, for a day's water production time range of 8:00-17:00, assume that two desired times, such as Time 1 and Time 2, are selected within this time range. When Time 1 arrives, if the liquid level in the clear water tank at Time 1 is lower than the day's water consumption, indicating that the water in the clear water tank at Time 1 cannot meet the day's water consumption, Time 1 can be determined as a time when water production is required, and a command to control water production is sent to the water production system at Time 1. When Time 2 arrives, if the liquid level in the clear water tank at Time 2 is higher than or equal to the day's water consumption, indicating that the day's water consumption can be met, Time 2 is determined to be a time when water production is not required, and a command to control water production is sent to the water production system at Time 2 to stop water production, or no command to control water production is sent to the water production system.

[0055] In an embodiment of the present disclosure, a first target model is provided. Water consumption within a current target time and available water information for any one of at least one expected water supply time, such as the nth expected water supply time, are input into the first target model. Based on the input data, the first target model can output indication information indicating whether the nth expected water supply time is the target water supply time or not.

[0056] For example, the first target model receives as input the daily water consumption of residents and the clear water tank level at the fifth expected water supply time. It processes the input using an artificial intelligence (AI) algorithm according to the set constraints and outputs an indication indicating whether the water supply system should be controlled to produce water at the fifth expected water supply time or whether it is not necessary to control the water supply system to produce water. If the indication indicates that the water supply system should be controlled to produce water at the fifth expected water supply time, then the fifth expected water supply time is the target water supply time at which water supply is required, and a command to control the water supply system to produce water at the fifth expected water supply time is sent. If the indication indicates that the water supply system should not be controlled to produce water at the fifth expected water supply time, then the fifth expected water supply time is the target water supply time at which water supply is not required, and there is no need to send a command to control the water supply system to produce water or a command to stop the water supply system at the fifth expected water supply time. The AI algorithm can be any reasonable algorithm, such as the eXtreme Gradient Boosting (XGboost) algorithm.

[0057] Based on the water consumption within the current target time, the available water information of the nth expected water production time, and the indication information output by the first target model, the water production time in smaller time slices for the current target time is automatically and accurately determined, which can ensure the precise control of the water production system.

[0058] In addition, since the first target model is a trained AI model, and since the trained AI model has good stability and robustness, the determined target water production time can be made more accurate, and accurate control of the water production system can be achieved.

[0059] The disclosed embodiments involve a second target model used to determine a water production time range. Specifically, water consumption data within a historical target time is obtained, such as reading data; at least one alternative water production time within the historical target time is obtained, such as selecting data; the water consumption data within the historical target time and the at least one alternative water production time are input into the second target model, and the second target model outputs reference water production data obtained by the water production system within the at least one alternative water production time; and the water production time range is determined from the at least one alternative water production time based on the reference water production data and the water consumption data within the historical target time.

[0060] The historical target time is a historical periodic water supply schedule. For example, if water supply was required every day in the past, the historical target time is every day in the past. Water consumption within the historical target time is the actual residential and / or commercial water consumption for each day in the past. Compared to the current target time, water consumption within the historical target time is the actual water consumption within the historical target time, such as the actual residential water consumption yesterday or the day before yesterday. Alternative water supply schedules within the historical target time can be one or more pre-selected times within the historical target time at which water supply is desired to be controlled, such as 9:00-14:00 or 10:00-15:00 every day for the past 365 days.

[0061] For example, the actual water consumption data of residents for the past 365 days is read, and 9:00-14:00 of each day in the past 365 days is selected as an alternative water supply time. The actual water consumption data of residents on the first day of the 365 days and the alternative water supply time of 9:00-14:00 on the first day are input into the second target model. The second target model outputs the water production volume produced by the water production system for the first day within the alternative water supply time. The water production volume can be used as the reference water production data obtained for the first day of the past 365 days. The actual water consumption data of residents on the second day of the 365 days and the alternative water supply time of 9:00-14:00 on the second day are input into the second target model. The second target model outputs the water production volume produced by the water production system for the second day within the alternative water supply time. The water production volume can be used as the reference water production data obtained for the second day of the past 365 days. Similarly, for the past 365 days, if the reference water production data generated daily by the water production system meets the requirements (e.g., the reference water production data generated by the water production system for 360 days meets the residential water demand for the corresponding day), then the water produced by the water production system during the alternative water production time of 9:00-14:00 each day can meet the residential water demand for the entire day. In this case, the alternative water production time of 9:00-14:00 is used as the water production time range within the current target time. If the reference water production data generated daily by the water production system does not meet the requirements, a new alternative water production time, such as 10:00-17:00, is set to see if the water produced during the new alternative water production time during the past 365 days meets the requirements. If so, the new alternative water production time is used as the water production time range within the current target time. The second objective model can be implemented using a reasonable AI algorithm such as the XGboost algorithm.

[0062] Based on the water consumption data within the historical target time, at least one alternative water production time within the historical target time and the second target model, the water production time range is intelligently and accurately determined, thereby ensuring a more accurate target water production time within the water production time range.

[0063] Among them, since the trained second target model usually has strong stability and robustness, the second target model can be used to accurately obtain the water production time range, and then accurately determine the target water production time and accurately control the water production system.

[0064] In the aforementioned solution, the water consumption within the current target time can be obtained using the first prediction model. That is, the water consumption within the current target time is obtained using the first prediction model based on the first target data. Specifically, the solution is as follows: obtaining the first target data, where the first target data includes at least one of the current target time, weather information within the current target time, and information related to the water consumption within the current target time.

[0065] The first target data is input into the first prediction model, and the first prediction model predicts the water consumption within the current target time based on the first target data; the prediction result of the first prediction model is obtained to obtain the water consumption within the current target time.

[0066] The first prediction model in the disclosed embodiments is a water consumption prediction model. This model is implemented using the XGboost algorithm. Its input is the time information to be predicted, such as the current day, for example, November 25th. The weather information within the time information to be predicted primarily includes at least one of humidity, temperature, and air temperature.

[0067] The water consumption information in a time period close to the time information to be predicted includes the water consumption information in a time period before the time information to be predicted, such as the actual water consumption on November 23 and 24.

[0068] These data are input into the water consumption prediction model, which uses the XGboost algorithm to calculate the amount of water that may be used by residents within the time information to be predicted (the water consumption within the time information to be predicted).

[0069] Based on the first target data and the first prediction model, water consumption within the current target time is predicted, achieving automatic water consumption prediction. Furthermore, because the trained first prediction model is highly robust and stable, using the first prediction model to predict water consumption within the predicted time ensures accurate water consumption, providing a reliable basis for determining the target water production time.

[0070] The above scheme is a scheme for applying the water consumption prediction model. Before it is applied, the model needs to be trained. The data used for model training are all historical data, which are divided into three parts: the first part is historical time information, or historical time information and holiday information of the historical time. The second part is the weather information of the historical time, such as temperature, humidity, weather, etc. at the historical time. The third part is autoregressive feature information. Considering that water consumption is related to seasonal weather and time, the morning peak when getting up and the evening peak before going to bed lead to a surge in water consumption. Autoregressive feature information includes water consumption information at times close to historical times. The following content is an exemplary reference for the above three parts:

[0071] Historical time information includes:

[0072] date: the date of the historical time;

[0073] if_holiday: whether it is a holiday,

[0074] holiday_name: name of the holiday;

[0075] is_workday: whether it is a working day;

[0076] weekday: day of the week;

[0077] hour: historical time.

[0078] Weather information during historical time periods includes:

[0079] temp: temperature at historical time;

[0080] humi: Humidity in historical time.

[0081] The autoregressive feature information in historical time includes:

[0082] The water output at the previous moment in the historical time, the water output at the previous two moments...the water output at the previous 12 points, etc.;

[0083] The water output at the same time one day, two days, three days ago in historical time, etc.

[0084] It can be understood that in the training phase of the water consumption prediction model, the input data used is historical data. Historical data is data that has actually occurred, and historical data can be obtained by reading the recorded data. For example, the autoregressive features of a certain time in history, the weather at that time, and other times earlier than that time can be used as inputs in the training phase. These data are input into the water consumption prediction model, which uses the XGboost algorithm for calculation to obtain an output value. The difference between the output value and the actual water consumption at that time is used to calculate the value of the model's loss function. When the value of the loss function is less than or equal to the preset loss threshold, the model is trained. The trained model can then be used to predict water consumption within a certain period of time.

[0085] Figure 3 This is a schematic diagram for monitoring the water production parameters involved in the water production process in a water plant. Figure 3 As shown, the water production parameters include the liquid level of the clean water tank, the active power of the water intake pump, and the quality parameters of the source water (the water taken by the water intake pump). Among them, the quality parameters of the source water include the chemical oxygen demand (COD), the pH value (pH) and the turbidity of the source water.

[0086] like Figure 3 As shown in the figure, as the water pump is turned on, the liquid level in the clean water tank slowly rises until the water pump is turned off to stop the water intake. It can be understood that there are other processing steps between the water pump taking water and the start of water filling into the clean water tank, so there is a time delay between the time the water pump is turned on and the time the liquid level in the clean water tank starts to rise, as shown in the figure. Figure 4 The rectangular box shown in the figure shows the difference between the moment the water pump is turned on (the water intake starts and there is water inflow) and the moment the clear water tank level starts to rise. This difference can be regarded as the time delay generated by the water production system during the water production process. This time delay will affect the water production efficiency. In addition, if Figure 3 As shown, the pH value, turbidity and COD of the source water are different at different times, and these quality parameters will affect the water yield. The worse the quality parameters, the lower the water yield and the longer the time delay. Because wastewater is generated in the water production process, the water yield can be regarded as the proportion of the produced usable water to the source water taken by the water pump. Under normal circumstances, the time delay and the water yield can be used as capacity index parameters for evaluating the water production system. When executing the water production control scheme in the embodiment of the present disclosure, it is also necessary to obtain the capacity index parameters of the water production system; based on the water consumption within the target time, the available water information corresponding to the nth expected water production time and the capacity index parameters, determine whether the nth expected water production time is the target water production time or not. Taking into account the impact of the water yield and time delay on the water production of the water production system, the target water production time can be determined more accurately.

[0087] For example, let's assume that the water production time range for the day is 8:00-17:00. Assume that two desired times are selected within this time range: Time 1 and Time 2, which is the time after Time 1. Without considering water production capacity parameters, there is a certain delay between the water supply pump in the water production system drawing water and the start of filling the clear water tank. This delay is exacerbated by poor water quality, and this delay may cause the required water production time to be postponed from Time 1 to Time 2. Alternatively, if the water quality is very poor that day, the water production system may slow down due to the poor water quality, causing the liquid level in the clear water tank to rise slowly, potentially delaying the target water production time from Time 1 to Time 2.

[0088] The disclosed embodiments involve a second prediction model, which is used to predict the capacity index parameters of the water production system at a certain moment. Furthermore, water quality information is obtained at the nth expected water production time, such as reading at least one of the source water COD, source water turbidity, and source water pH value monitored at the 5th expected time. The water quality information at the n=5th expected time is input into the second prediction model, and the second prediction model outputs the capacity index parameters of the water production system at the nth expected time based on the water quality information at the n=5th expected time, such as at least one of the water yield and water production delay at the n=5th expected time. The second prediction model can be regarded as a capacity index parameter prediction model and is implemented using the XGboost algorithm. Automatic prediction of the capacity index parameters of the water production system is achieved based on the water quality information and the second prediction model. In addition, because the trained second prediction model has strong robustness and stability, using the second prediction model to predict the capacity index parameters of the water production system at a certain moment can ensure the accuracy of the acquisition of the capacity index parameters, thereby providing a reliable basis for determining the target water production time.

[0089] The above-mentioned scheme is a scheme in which the capability index parameter prediction model is applied. Before it is applied, the model needs to be trained. The data used for model training is historical data, which includes water quality information at historical time, such as water quality information at 8 o'clock every day in the past 30 days and actual water yield and delay information at historical time. The water quality information at historical time is used as input in the model training phase and input into the capability index parameter prediction model. The capability index parameter prediction model uses the XGboost algorithm for calculation to obtain an output value. The difference between the output value and at least one of the actual water yield and actual delay at the historical time is used to calculate the value of the model's loss function. When the value of the loss function is less than or equal to the preset loss threshold, the model is trained. The trained model can be used to predict the water yield and delay information within a certain period of time.

[0090] It can be understood that the water yield output by the second prediction model is usually less than 100%. Compared with the ideal situation where the water yield is 100% (there is no wastewater in the water production process), the water production system, specifically the water intake pump, needs to absorb more source water to produce water that meets the residents' needs on that day. The water production system relies on the water intake pump to absorb source water. Usually, the water production system includes at least one water intake pump. For the convenience of description, these water intake pumps are regarded as standby water pumps. Each standby water pump has certain working capacity parameters, such as working frequency, tonnage of water pumped at different pumping heights and / or active pumping power, etc. Figure 5 The figure shows a comparison of the working capacity parameters of several alternative water intake pumps. The horizontal axis Q represents the flow rate in the water intake pump, and the vertical axis represents the pumping height H. Figure 5 Figure 4 shows the operating capacity curves of different alternative water pumps, each with a different operating frequency. For example, the operating frequency of the alternative water pump shown in curve 4 is 30 MHz, while the operating frequency of the alternative water pump shown in curve 3 is 50 MHz. Assuming the same pumping height, the pump with an operating frequency of 30 MHz shown in curve 4 can pump a maximum of 55 tons of water at a pumping height of 20 meters. The pump with an operating frequency of 50 MHz shown in curve 3 can pump a maximum of 80 tons of water at a pumping height of 20 meters. Based on the different operating capacity characteristics of the alternative water pumps, in the disclosed embodiment, the operating capacity parameters of each alternative water pump can be obtained, such as by reading them. Based on the water consumption within the current target time, the available water information at the target water production time, and the operating capacity parameters of the alternative water pumps, a target water pump to be activated within the target water production time is determined from among the alternative water pumps. This enables precise determination and control of the target water pump, thereby ensuring automatic and accurate control of water production in the water production system.

[0091] By controlling the target water pump to be in the on state to obtain the water required for water production within the target water production time, the problem of excessive power consumption caused by other water pumps still being turned on can be avoided.

[0092] In terms of specific implementation, Figure 5The content shown can be considered a water pump simulation model used to simulate the operating capacity of each water pump. For example, if the predicted residential water demand for a particular day is 200 tons and there is 100 tons of available water in the clean water tank, an additional 100 tons of water must be produced to meet the residents' water demand. Without considering the water yield, the water pumps with the operating capacity characteristics of curve 3 and curve 4 can be controlled to be turned on. Commands to control these two target water pumps to start drawing water can be sent to control them to produce water to meet the residents' water demand. The water pumps with the operating capacity characteristics of curves 1 and 2 can be controlled to be turned off. If the water yield is 80%, then producing 100 tons of water requires pumping 125 tons of water. Therefore, the pumps with the operating capacity characteristics of curve 3, curve 4, and curve 2 can be controlled to operate, thereby controlling these pumps to draw water to meet residents' water needs. This allows for precise identification and automatic control of target pumps, ensuring automatic and accurate control of the water production system.

[0093] The water production control scheme of the embodiment of the present disclosure is further described in detail below.

[0094] The aforementioned water consumption prediction model is used to predict residents' daily water consumption as the water consumption within the current target time. Historical data indicates that the water supply time range within the current target time is 10:00-14:00. Assume that within the current target time range, an expected water supply time is selected every hour, with 12:00 selected as one of the expected water supply times. When 12:00 arrives, the first target model is invoked, which indicates whether the water supply system should be controlled to supply water at 12:00. It can be understood that the first target model, as an AI model, operates as a function Y = f(X). Here, X represents the model input; Y represents the model output; and f() represents the mapping relationship from input to output, representing a mapping between X and Y. In practical applications, the model inputs include an expected water supply time within the current target time, such as 12:00 on the day, the clear water tank level of the water supply system at that expected water supply time, and the water yield and delay of the water supply system during that expected water supply time. The clear water tank level of the water system at the expected water production time can be obtained by reading monitoring information from the water plant. The water yield and time delay of the water system within the expected water production time are obtained by inputting water quality information within the expected water production time into a second prediction model. The model inputs may also include upper and lower limits for the clear water tank level within the current target time.

[0095] In the embodiment of the present disclosure, f() can be constrained by using constraints. The constraints are: (1) the water level of the clean water tank must be between the upper and lower limits of the clean water tank water level at the input expected water production time; (2) the minimum number of pumps must be turned on to meet the water demand within the current target time; (3) the currently input expected water production time must be within the water production time range; (4) after each water production starts, the water production system will not stop working until the clean water tank is full; (5) after the clean water tank is full, the water intake pump stops taking water; (6) after the water production ends on the day, all water use before the next water production starts will not cause the clean water tank water level to exceed the lower limit; (6) the water yield and time delay at the input expected water production time are taken into account; (7) the water intake pump must be turned on in a fixed frequency mode.

[0096] The first objective model processes the received input using an AI algorithm based on the constraints to generate and output instruction information. This instruction information indicates which of the multiple candidate water pumps in the water system should be turned on and which should be turned off. If the instruction information indicates that a water pump is turned on, it indicates that the selected desired water supply time, such as 12:00, is the desired water supply time. At this time, a control command is sent to the water pump that needs to be turned on, causing it to start drawing water from the source. Only when the water pump draws water from the source can other components in the water supply system perform filtering, purification, and other processes to produce water for residents. If the instruction information only indicates that a water pump is turned off, it indicates that the selected desired water supply time, such as 12:00, is not the desired water supply time, and no control command is sent to the water pump to turn it on or off. In the aforementioned scheme, the first objective model can be considered a water pump optimization control model, which implements the turning on and off of which water pumps at a specific desired time. In the aforementioned solution, daily resident water consumption, water availability information corresponding to each desired water supply time in the water supply system, and the first target model are used to automatically and accurately determine the water supply time in smaller time slices relative to the current target time. This intelligent and precise solution for determining target water supply times significantly avoids the problems associated with manually determining water supply times based on experience. Furthermore, the determined target water supply time enables automatic control of water supply in the water supply system, avoiding the problems associated with manual control of water supply.

[0097] Among them, the fixed frequency mode of the water intake pump is relative to the variable frequency mode of the water intake pump. In the fixed frequency mode of the water intake pump, the water intake pump will have the following Figure 5 The curve shown, using Figure 5 The curve shown is convenient for screening out the target water intake pump within the target water production time from multiple water intake pumps.

[0098] In the above scheme, the target water production time is automatically determined based on the indication information output by the first target model, without the need to manually determine the time required for water production, and automatic control of water production is achieved at the target water production time, which reflects the intelligence of water production, saves time and effort, and can avoid errors caused by manual control.

[0099] It can be understood that if the water consumption data within the historical target time, such as the actual water consumption of any day in the past 365 days, one of the alternative water production times within the historical target time, such as a pre-selected time period, and one or more expected water production times selected within the alternative water production time, such as one or more time points selected within the time period, are input into the first target model, or together with the above information, together with information such as the water yield and time delay of the water production system at the selected one or more time points, the first target model will provide indication information on which water intake pumps to control on and off at the one or more time points, determine whether the one or more time points are the time when water production is required within the alternative water production time based on the indication information, and send corresponding control commands to the water intake pumps to achieve water production or not. Based on the above scheme, the first target model can be used to simulate the control conditions of the water intake pumps at each expected water production time within a certain alternative water production time for each day in the past 365 days. During the simulation process, the water production system will generate a water production data, which will be used as the reference water production data obtained within the alternative water production time for each day in the past 365 days. Determine whether the number of days of reference water production data that meet the actual water consumption meets the requirement. If the number of days of reference water production data that meet the actual water consumption reaches a preset number of days, the requirement is considered to be met. For example, determine whether the reference water production data for each day in the past meets the actual water consumption for the corresponding day. If the reference water production data for 360 days out of 365 days meets the actual water consumption for the corresponding day, the requirement is considered to be met, indicating that the alternative water production time can be used as the water production time range within the current target time. If the reference water production data for 180 days out of 365 days cannot meet the actual water consumption for the corresponding day, then select the next alternative water production time. Similar to the above, obtain the reference water production data generated for each day in the past 365 days within the next alternative water production time, and determine whether the reference water production data for each day in the past meets the actual water consumption for the corresponding day. If the reference water production data for 360 days out of 365 days meets the actual water consumption for the corresponding day, then the next alternative water production time can be used as the water production time range within the current target time. Similarly, based on the reference water production data, an available water production time range can be filtered out from one or two or more alternative water production time ranges.In the above simulation scheme, the constraints of the first objective model should be: (1) the water level of the clean water tank must be between the upper and lower limits of the clean water tank water level at the input expected water production time; (2) the minimum number of water pumps must be turned on to meet the daily water demand in the past 365 days; (3) the currently input expected water production time must be within the alternative water production time; (4) after each water production starts, the water production system will not stop working before the clean water tank is full; (5) after the clean water tank is full, the water intake pump stops taking water; (6) after the water production ends on the day, all water use before the next water production starts will not cause the clean water tank water level to exceed the lower limit; (6) the water yield and time delay at the input expected water production time are considered; (7) the water intake pump needs to be turned on in a fixed frequency mode.

[0100] If the reference water production data generated by the water production system during the simulation process is obtained by monitoring the monitoring module, and the solution for determining whether the number of days of the reference water production data that meets the actual water consumption meets the requirements is implemented by the determination module, then the second target model in the embodiment of the present disclosure includes the first target model, the monitoring module and the determination module, that is, the implementation function of the second target model is implemented by the first target model, the monitoring module and the determination module, etc.

[0101] It can be understood that the first target model and the second target model can be trained models, and the specific training process will not be elaborated in this solution.

[0102] In this embodiment, the water production time range within the current target time, derived from historical data, provides a baseline time for water production within the current target time. This baseline time provides a basis for accurately determining the target water production time. Furthermore, the first target model enables automated control of the water production system, freeing up manpower.

[0103] The present disclosure also provides an embodiment of a water production control device, such as Figure 6 As shown, the device includes:

[0104] The first acquisition unit 601 is used to obtain the water production time range within the current target time;

[0105] The first determining unit 602 is configured to determine available water information of the water production system corresponding to at least one expected water production time within the water production time range;

[0106] The second determining unit 603 is configured to determine a target water production time for required water production from the at least one expected water production time according to the water consumption within the current target time and the available water information;

[0107] The control unit 604 is configured to control the water production system to produce water within the target water production time.

[0108] The second determining unit 603 is configured to:

[0109] The water consumption and the available water information of the nth expected water production time are input into the first target model, and the first target model outputs indication information based on the water consumption and the available water information, wherein the indication information is used to indicate whether the nth expected water production time is the target water production time or not; n is a positive integer.

[0110] The first acquisition unit 601 is configured to acquire a water production time range within a current target time obtained based on historical data.

[0111] Furthermore, the first acquiring unit 601 is used to

[0112] Obtain water consumption data within the historical target time period;

[0113] Inputting the water consumption data within the historical target time and at least one alternative water production time within the historical target time into a second target model, and the second target model outputting reference water production data obtained by the water production system within the at least one alternative water production time;

[0114] The water production time range is determined from the at least one candidate water production time based on the reference water production data and the water consumption data within the historical target time.

[0115] Among them, the first acquisition unit 601 is also used to obtain the water consumption within the current target time based on the first target data through the first prediction model; the first target data includes: the current target time, weather information within the current target time, and at least one of the information related to the water consumption at the current target time.

[0116] Figure 7 In another embodiment of the water production control device, the device further includes a second obtaining unit 703, configured to obtain a capacity indicator parameter of the water production system at the nth expected water production time;

[0117] The second determination unit 704 is used to determine whether the nth expected water production time is the target water production time or not based on the water consumption within the target time, the available water information corresponding to the nth expected water production time, and the capacity indicator parameter.

[0118] The second acquiring unit 703 is used to

[0119] Acquiring water quality information at the nth expected water production time;

[0120] The water quality information is input into a second prediction model, and the second prediction model outputs the capability index parameter according to the water quality information.

[0121] The water production system includes at least one standby water collection pump; the standby water collection pump is used to control a water source to provide the water required for water production to the water production system; the device also includes a third acquisition unit and a third determination unit;

[0122] The third acquisition unit is used to obtain the working capacity parameter of the standby water pump;

[0123] The third determination unit is used to determine a target water intake pump that will be turned on within the target water production time from the alternative water intake pumps based on the water consumption within the current target time, the available water information within the target water production time, and the working capacity parameters of the alternative water intake pumps.

[0124] The control unit 604 is configured to obtain the water required for water production by controlling the target water pump to be in an on state within the target water production time.

[0125] It should be noted that Figure 7 For details on the functions of the first acquisition unit 701, the first determination unit 702, the second determination unit 704 and the control unit 705, see Figure 6 The first acquisition unit 601, the first determination unit 602, the second determination unit 603 and the control unit 604 in the embodiment will not be described in detail.

[0126] The third acquisition unit and the third determination unit are Figure 6 and Figure 7 Not shown in the figure.

[0127] It should be noted that the water production control device disclosed in the present invention has a similar principle for solving the problem as the aforementioned water production control method. Therefore, the implementation process and implementation principle of the water production control device can refer to the description of the implementation process and implementation principle of the aforementioned method, and the repeated parts will not be repeated.

[0128] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0129] The readable storage medium stores computer commands that cause the computer to execute the water production control method according to the embodiment of the present disclosure. The readable storage medium includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, and portable compact disc read-only memory (CD-ROM). The computer program product includes a computer program that, when executed by a processor, implements the water production control method according to the embodiment of the present disclosure.

[0130] The electronic device includes: at least one processor; and a memory in communication with the at least one processor; wherein the memory stores commands that can be executed by the at least one processor, and the commands are executed by the at least one processor to enable the at least one processor to perform the aforementioned gesture method. The processor includes but is not limited to a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc.

[0131] Figure 8 A schematic block diagram of an example electronic device 800 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are provided as examples only and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0132] like Figure 8 As shown, the device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. Various programs and data required for the operation of the device 800 can also be stored in the RAM 803. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0133] Various components in device 800 are connected to I / O interface 805, including an input unit 806, such as a keyboard, mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a magnetic disk, optical disk, etc.; and a communication unit 809, such as a network card, modem, wireless communication transceiver, etc. The communication unit 809 allows device 800 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0134] The computing unit 801 can be a variety of general-purpose and / or specialized processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 801 performs the various methods and processes described above, such as the water production control method. For example, in some embodiments, the water production control method can be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as the storage unit 808. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the water production control method described above can be performed. Alternatively, in other embodiments, the computing unit 801 can be configured to perform the water production control method by any other suitable means (e.g., by means of firmware).

[0135] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system comprising at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and commands from a storage system, at least one input device, and at least one output device, and transmit data and commands to the storage system, the at least one input device, and the at least one output device.

[0136] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0137] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use with a command execution system, device or equipment or used in combination with a command execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0138] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0139] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0140] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact through a communication network. The client-server relationship arises through computer programs running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, a server in a distributed system, or a server integrated with a blockchain.

[0141] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not limited herein.

[0142] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A water production control method, comprising: Acquire water consumption data within a historical target time and at least one alternative water production time within the historical target time; Inputting the water consumption data within the historical target time and the at least one alternative water production time into a second target model, and having the second target model output reference water production data obtained by the water production system within the at least one alternative water production time; Determining a water production time range within the current target time from the at least one alternative water production time based on the reference water production data and the water consumption data within the historical target time, wherein the water production time range is a reasonable time range for staff to stay at the water plant; Determining available water information of the water production system corresponding to at least one expected water production time within the water production time range; Determining a target water production time requiring water production from the at least one expected water production time based on the water consumption within the current target time and the available water information, comprising: inputting the water consumption and the available water information of the nth expected water production time into a first target model, and having the first target model output indication information based on the water consumption and the available water information, wherein the indication information is used to indicate whether the nth expected water production time is the target water production time or not; n is a positive integer; The water production system is controlled to produce water within the target water production time.

2. The method according to claim 1, wherein Obtaining the water consumption within the current target time according to the first target data using the first prediction model; The first target data includes at least one of the current target time, weather information within the current target time, and information related to water consumption within the current target time.

3. The method according to claim 1, further comprising: Obtaining a capacity indicator parameter of the water production system at the nth expected water production time; The determining, based on the water consumption within the current target time and the available water information, a target water production time for required water production from the at least one expected water production time includes: Based on the water consumption within the target time, the available water information corresponding to the nth expected water production time, and the capacity indicator parameter, it is determined whether the nth expected water production time is the target water production time or not.

4. The method according to claim 3, wherein obtaining the capacity index parameter of the water production system at the nth expected water production time comprises: Acquiring water quality information at the nth expected water production time; The water quality information is input into a second prediction model, and the second prediction model outputs the capability index parameter according to the water quality information.

5. The method according to claim 1, wherein the water production system comprises at least one standby water extraction pump; The standby water pump is used to control the water source to provide the water required for water production to the water production system; the method further includes: Obtaining the working capacity parameters of the alternative water supply pump; According to the water consumption within the current target time, the available water information of the target water production time and the working capacity parameters of the alternative water collection pumps, a target water collection pump that enters the open state within the target water production time is determined from the alternative water collection pumps.

6. The method according to claim 5, wherein: The controlling the water production system to produce water within the target water production time includes: The water required for water production is obtained by controlling the target water pump to be in an on state within the target water production time.

7. A water production control device comprising: A first acquisition unit is configured to acquire water consumption data within a historical target time and at least one alternative water production time within the historical target time; Inputting the water consumption data within the historical target time and the at least one alternative water production time into a second target model, the second target model outputting reference water production data obtained by the water production system within the at least one alternative water production time; determining a water production time range within the current target time from the at least one alternative water production time based on the reference water production data and the water consumption data within the historical target time, wherein the water production time range is a reasonable time range for staff to stay at the water plant; a first determining unit, configured to determine available water information of the water production system corresponding to at least one expected water production time within the water production time range; a second determining unit, configured to determine a target water production time requiring water production from the at least one expected water production time based on the water consumption within the current target time and the available water information, comprising: inputting the water consumption and the available water information of the n-th expected water production time into a first target model, and having the first target model output indication information based on the water consumption and the available water information, wherein the indication information is used to indicate whether the n-th expected water production time is the target water production time or not; n is a positive integer; A control unit is used to control the water production system to produce water within the target water production time.

8. The device according to claim 7, wherein The first acquiring unit is further configured to: Obtaining the water consumption within the current target time according to the first target data using the first prediction model; The first target data includes at least one of the current target time, weather information within the current target time, and information related to water consumption within the current target time.

9. The device according to claim 7, wherein The device further includes a second acquisition unit for acquiring a capacity index parameter of the water production system at the nth expected water production time; The second determination unit is used to determine whether the nth expected water production time is the target water production time or not based on the water consumption within the target time, the available water information corresponding to the nth expected water production time, and the capacity indicator parameter.

10. The device according to claim 9, wherein The second acquiring unit is configured to: Acquiring water quality information at the nth expected water production time; The water quality information is input into a second prediction model, and the second prediction model outputs the capability index parameter according to the water quality information.

11. The device according to claim 7, wherein the water production system comprises at least one standby water pump; the standby water pump is used to control a water source to provide the water required for water production to the water production system; The device further includes a third acquiring unit and a third determining unit; The third acquisition unit is used to obtain the working capacity parameter of the standby water pump; The third determination unit is used to determine a target water intake pump that will be turned on within the target water production time from the alternative water intake pumps based on the water consumption within the current target time, the available water information within the target water production time, and the working capacity parameters of the alternative water intake pumps.

12. The device according to claim 11, wherein The control unit is used to: The water required for water production is obtained by controlling the target water pump to be in an on state within the target water production time.

13. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 6.

14. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 6.

15. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 6.

Images