Intelligent aeration control system, method, device and storage medium

Abstract

The embodiments of this specification provide an intelligent aeration control system and method, device, and storage medium. The system includes a primary control unit, a secondary control unit, a monitoring unit, an aeration control unit, a water flow regulation unit, and a water quality collection unit. The water quality collection unit is used to collect water quality data, and the monitoring unit is used to obtain monitoring data through at least one monitoring device. The water flow regulation unit regulates water flow based on water flow control instructions issued by the primary control unit. The aeration control unit adjusts at least one aeration device based on aeration control instructions issued by the secondary control unit. The primary control unit is configured to determine a water flow control amount and generate a water flow control instruction based on the monitoring data and water quality data. The secondary control unit is configured to determine aeration parameters of at least one aeration device during at least one target time period and generate an aeration control instruction.

Description

[0001] Description of the case

[0002] This application is a divisional application filed for the Chinese application with application date of May 7, 2024, application number 202410553101.5, and invention name “A flowing water aeration control system, method, device and storage medium”. Technical Field

[0003] This specification relates to the field of sewage aeration treatment, and in particular to an intelligent aeration control system, method, device and storage medium. Background Art

[0004] During wastewater treatment, aeration is often used to forcibly oxygenate the wastewater, enhancing contact between organic matter, microorganisms, and dissolved oxygen within the tank, leading to the oxidation and decomposition of organic matter. However, current control of aeration devices and systems often results in inaccurate aeration parameters, resulting in unnecessary energy consumption.

[0005] To address the issue of inaccurate aeration parameters, CN114132980B proposes a short-range intelligent precision aeration control method and system for sewage treatment. This method monitors key sewage treatment parameters, discards difficult-to-measure and low-relevance parameters, and shortens the time between feedforward and feedback, achieving short-range precision aeration control. However, it does not involve accurate long-term monitoring and evaluation of water quality and the aeration treatment process.

[0006] Therefore, it is hoped that an intelligent aeration control system, method, device and storage medium can be provided to achieve long-term monitoring of the water body and the aeration treatment process in the aeration tank, and timely adjust the parameters related to the aeration treatment process to reasonably save energy. Summary of the Invention

[0007] One or more embodiments of the present specification provide an intelligent aeration control system, the system comprising a primary control unit, a secondary control unit, a monitoring unit, an aeration control unit, a water volume regulating unit, and a water quality collection unit, wherein: the water quality collection unit, the water volume regulating unit, and the secondary control unit are communicatively connected to the primary control unit, and the monitoring unit and the aeration control unit are communicatively connected to the secondary control unit; the water quality collection unit is used to collect water quality data, and the monitoring unit is used to obtain monitoring data through at least one monitoring device, the monitoring data including environmental parameters, water temperature, and water flow rate, wherein the environmental parameters include ambient air temperature, ambient air pressure, and air humidity; the water volume regulating unit regulates water volume based on a water volume control instruction issued by the primary control unit, the water volume control instruction including a water flow control amount; the aeration control unit adjusts aeration parameters of at least one aeration device based on the aeration control instruction issued by the secondary control unit; the primary control unit is configured on a terminal device in a control room, The first-level control unit is configured to determine a second continuous time point based on the jump point data in the first monitoring data set of the first continuous time point collected by the monitoring unit; determine the collection period of the water quality collection unit based on the second continuous time point; obtain the second monitoring data set of the second continuous time point through the monitoring unit, and obtain the water quality data set collected based on the collection period through the water quality collection unit; determine the credible monitoring data corresponding to the second continuous time point based on the monitoring data in the second monitoring data set and the jump point data corresponding to the second monitoring data set; determine the water body flow control amount and generate the water volume control instruction based on the credible monitoring data, the water quality data set, the estimated blowing power and the estimated fan blade speed; the second-level control unit is configured on the at least one aeration device, and the second-level control unit is configured to determine the aeration parameters of the at least one aeration device in at least one target time period and generate the aeration control instruction, and the aeration parameters include at least one of blowing power and fan blade speed.

[0008] One or more embodiments of the present specification provide an intelligent aeration control method, which is implemented by the intelligent aeration control system, and includes: determining a second continuous time point based on jump point data in a first monitoring data set collected by a monitoring unit at a first continuous time point; determining a collection period of a water quality collection unit based on the second continuous time point; obtaining a second monitoring data set at the second continuous time point through the monitoring unit, and obtaining a water quality data set collected based on the collection period through the water quality collection unit; determining the second continuous time point based on the monitoring data in the second monitoring data set and the jump point data corresponding to the second monitoring data set. Corresponding trusted monitoring data; determining the water flow control amount and generating a water control instruction based on the trusted monitoring data, the water quality data set, the estimated blowing power and the estimated fan blade speed, and controlling the water flow regulation unit to perform water flow regulation based on the water flow control instruction; wherein, the monitoring data is collected by at least one monitoring device configured in the monitoring unit, and the water quality data is collected by the water quality collection unit; determining the aeration parameters of at least one aeration device in at least one target time period and generating an aeration control instruction, and adjusting the at least one aeration device based on the aeration control instruction, wherein the aeration parameters include at least one of the blowing power and the fan blade speed.

[0009] One or more embodiments of this specification provide an intelligent aeration control device, characterized in that the device includes at least one processor and at least one memory; the at least one memory is used to store computer instructions; and the at least one processor is used to execute at least part of the computer instructions to implement the intelligent aeration control method described in the above embodiments.

[0010] One or more embodiments of this specification provide a computer-readable storage medium storing computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the intelligent aeration control method described in the above embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] This specification will be further described in the form of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting, and in these embodiments, like numbers represent like structures, wherein:

[0012] Figure 1 is a schematic structural diagram of an intelligent aeration control system according to some embodiments of this specification;

[0013] Figure 2 is an exemplary flow chart of an intelligent aeration control method according to some embodiments of this specification;

[0014] Figure 3 is an exemplary flow chart of generating aeration control instructions according to some embodiments of this specification;

[0015] Figure 4 is an exemplary flow chart for determining a water flow control amount according to some embodiments of this specification;

[0016] Figure 5 This is an exemplary schematic diagram of a jump point data prediction model according to some embodiments of this specification. DETAILED DESCRIPTION

[0017] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following briefly introduces the drawings required for describing the embodiments. The drawings do not represent all implementation methods.

[0018] It should be understood that the terms "system," "device," "unit," and / or "module" used herein are a method for distinguishing different components, elements, parts, portions, or assemblies at different levels. If other terms can achieve the same purpose, the terms may be replaced by other expressions.

[0019] As used in this specification and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not refer to the singular but also include the plural. Generally speaking, the terms "comprises" and "include" only indicate the inclusion of the steps and elements specifically identified, and these steps and elements do not constitute an exclusive list. A method or apparatus may also include other steps or elements.

[0020] When operations are performed according to the step descriptions in the embodiments of this specification, unless otherwise specified, the order of the steps is interchangeable, steps can be omitted, and other steps can be included in the operation process.

[0021] Wastewater treatment is a vital component of urban water circulation. Currently, aeration is the most common method of wastewater treatment, which oxidizes and decomposes organic matter in wastewater by enhancing contact between organic matter and microorganisms and dissolved oxygen within the tank. Certain embodiments of this specification provide an intelligent aeration control system, method, device, and storage medium. By acquiring water monitoring data, these systems can predict water quality fluctuations in advance and adjust aeration parameters promptly to accommodate anticipated changes before they occur. This prevents water quality issues, improves the energy efficiency of the aeration system, and maintains the stability of key water quality parameters, demonstrating both practicality and economic benefits.

[0022] Figure 1 It is a structural diagram of an intelligent aeration control system according to some embodiments of this specification.

[0023] In some embodiments, the intelligent aeration control system 100 may include a primary control unit 110, a secondary control unit 120, a monitoring unit 130, an aeration control unit 140, a water quantity adjustment unit 150, and a water quality collection unit 160. The water quality collection unit 160, the water quantity adjustment unit 150, and the secondary control unit 120 are communicatively connected to the primary control unit 110, and the monitoring unit 130 and the aeration control unit 140 are communicatively connected to the secondary control unit 120.

[0024] The water flow regulating unit 150 is used to regulate the flow of water entering the aeration tank. In some embodiments, the water flow regulating unit 150 can regulate the water flow based on the water flow control instruction issued by the primary control unit 110.

[0025] The water control instruction is an instruction for controlling the water flow regulating unit 150 to regulate water flow. In some embodiments, the water flow control instruction may include a water flow control value. In response to receiving the water flow control instruction, the water flow regulating unit 150 may regulate water flow according to the water flow control value included in the water flow control instruction.

[0026] Water quality collection unit 160 is used to collect water quality data. In some embodiments, water quality collection unit 160 can be deployed in the water body to be monitored to collect water quality data. In some embodiments, water quality collection unit 160 can be deployed before the entrance of the aeration tank or within the aeration tank to collect water quality data before aeration treatment. In some embodiments, water quality collection unit 160 can be deployed at the water outlet of the aeration tank to collect water quality data after aeration treatment. An aeration tank refers to a location where aeration treatment is provided.

[0027] In some embodiments, the water quality collection unit 160 may include at least one water quality collection device, and the at least one water quality collection device may be configured near at least one aeration device (eg, at least one aeration disk or at least one stirring device).

[0028] Water quality data refers to data related to the composition of the water in the aeration tank. In some embodiments, water quality data may include sewage composition, dissolved oxygen, chemical oxygen demand, ammonia nitrogen, etc. Sewage components may include heavy metal ions, harmful organic matter, etc.

[0029] In some embodiments, the water quality collection unit 160 may collect water quality data based on a preset period. For example, the water quality collection unit 160 may collect water quality data once every preset period. The preset period may be pre-set based on historical experience.

[0030] The monitoring unit 130 is used to obtain monitoring data through at least one monitoring device. In some embodiments, the monitoring unit may include multiple monitoring devices. For example, an environmental monitoring device and a water monitoring device. Among them, the environmental monitoring device may include a temperature sensor, a pressure sensor, and a humidity sensor. The water monitoring device may include a temperature sensor, a flow rate detector, etc. The temperature sensor in the environmental monitoring device is used to collect the ambient temperature, and the temperature sensor in the water monitoring device is used to collect the water temperature. The environmental monitoring device can be configured near the aeration tank, and the water monitoring device can be configured before the inlet of the aeration tank or inside the aeration tank to obtain the water temperature and water flow rate before aeration treatment.

[0031] In some embodiments, the monitoring data may include environmental parameters, water temperature, and water flow rate. The environmental parameters may include ambient air temperature, ambient air pressure, and air humidity.

[0032] In some embodiments, the monitoring unit 130 may collect monitoring data based on a preset period, which may be pre-set based on historical experience.

[0033] The aeration control unit 140 is configured to adjust aeration parameters of at least one aeration device. In some embodiments, the aeration control unit may adjust aeration parameters of at least one aeration device based on an aeration control instruction issued by the secondary control unit 120 .

[0034] The aeration control instruction refers to an instruction for controlling the aeration control unit 140 to adjust aeration parameters.

[0035] Aeration equipment refers to equipment used to aerate water. In some embodiments, at least one aeration equipment can be distributed and arranged at at least one preset location within the aeration tank. The preset location can be pre-set based on historical experience.

[0036] In some embodiments, the aeration equipment may include a blower and a stirring device.

[0037] The blower is used to mix air bubbles into the water. The stirring device is used to stir the water.

[0038] Aeration parameters refer to parameters related to the operation of the aeration equipment. In some embodiments, aeration parameters may include blower power and fan blade speed. Blower power refers to the operating power of the blower. Fan blade speed refers to the speed of the fan blades of the stirring device.

[0039] The secondary control unit 120 may process data and / or information from the monitoring unit 130 .

[0040] In some embodiments, the secondary control unit 120 can be configured on at least one aeration device.

[0041] In some embodiments, the secondary control unit 120 can be connected to the monitoring unit 130 and the aeration control unit 140 in any feasible manner, such as communication cables, wireless transmission, etc.

[0042] In some embodiments, the secondary control unit 120 may be configured to determine the aeration parameters of at least one aeration device in at least one target period and generate an aeration control instruction. For instructions on how to generate an aeration control instruction, see Figure 2 and its related descriptions.

[0043] In some embodiments, the secondary control unit 120 can be further configured to: determine the jump point data in the first monitoring data set based on the first continuous time point collected by the monitoring unit, and send the jump point data to the primary control unit; and adjust the aeration parameters based on the estimated blowing power and estimated fan blade speed corresponding to the future time period obtained from the primary control unit, and generate an aeration control instruction based on the adjusted aeration parameters. For more information about this part, please refer to Figure 3 and its related descriptions.

[0044] The primary control unit 110 can process data and / or information from at least one unit of the intelligent aeration control system 100. Based on this data, information, and / or processing results, the primary control unit 110 can execute program instructions to perform one or more functions described in the embodiments of this specification. In some embodiments, the primary control unit 110 can include one or more sub-processing devices (e.g., a single-core processing device or a multi-core processing device). By way of example only, the primary control unit 110 can include a central processing unit (CPU), an application-specific integrated circuit (ASIC), an application-specific instruction set processor (ASIP), a graphics processing unit (GPU), or any combination thereof.

[0045] In some embodiments, the primary control unit 110 can be configured on a terminal device in a control room. The control room refers to a space where the intelligent aeration control system 100 is controlled. The terminal device can include a mobile device, a tablet computer, a laptop computer, etc.

[0046] In some embodiments, the primary control unit 110 can be connected to the water quality collection unit 160 , the water quantity adjustment unit 150 , and the secondary control unit 120 in any feasible manner, such as communication cables, wireless transmission, and the like.

[0047] In some embodiments, the primary control unit 110 is configured to determine the water flow control amount and generate a water flow control instruction based on the monitoring data and water quality data. For instructions on how to generate a water flow control instruction, please refer to Figure 2 and its related descriptions.

[0048] In some embodiments, the primary control unit 110 may be further configured to determine the estimated blowing power and the estimated fan blade speed corresponding to the future time period based on the jump point data obtained from the secondary control unit 120, and send the estimated blowing power and the estimated fan blade speed to the secondary control unit 120. For more information on this part, please refer to Figure 3 and its related descriptions.

[0049] In some embodiments, the primary control unit 110 can be further configured to: determine interference data based on the jump point data in the first monitoring data set; determine credible monitoring data based on the first monitoring data set and the interference data; determine the estimated blowing power and the estimated fan blade speed based on the water flow, the credible monitoring data and the jump point data. For more information on this part, please refer to Figure 3 and its related descriptions.

[0050] In some embodiments, the primary control unit 110 may be further configured to determine the interference data through the interference data determination model based on the first monitoring data set, the jump point data, and the aeration parameters. Figure 3 and its related descriptions.

[0051] In some embodiments, the primary control unit 110 can be further configured to: determine the collection period of the water quality collection unit based on the second continuous time point; obtain the second monitoring data set of the second continuous time point through the monitoring unit, and obtain the water quality data set collected based on the collection period through the water quality collection unit; determine the water flow control amount based on the second monitoring data set and the water quality data set. For more information about this part, please refer to Figure 4 and its related descriptions.

[0052] In some embodiments of the present specification, the first-level control unit can regulate water flow based on monitoring data and water quality data to avoid excessive or insufficient water flow entering the aeration tank, which may lead to a decrease in aeration effect or energy waste. The second-level control unit can adjust the aeration parameters in real time before the water quality data changes or fluctuates, ensuring that the aeration effect meets the requirements while reducing energy consumption.

[0053] Figure 2 is an exemplary flow chart of the intelligent aeration control method according to some embodiments of this specification. In some embodiments, process 200 is executed by an intelligent aeration control system. Figure 2 As shown, process 200 includes the following steps:

[0054] Step 210: Based on the monitoring data and water quality data, determine the water flow control amount and generate a water volume control instruction.

[0055] For information on monitoring data and water quality data, please refer to Figure 1 and its related descriptions.

[0056] In some embodiments, the primary control unit can determine the water flow control amount in a variety of ways based on the water flow rate and water quality data in the monitoring data. For example, the primary control unit can query the reference water flow corresponding to the water flow rate and water quality data in a preset flow table based on the water flow rate and water quality data, calculate the difference between the reference water flow and the current water flow, and obtain the water flow control amount. If the current water flow is less than the reference water flow and the water flow needs to be increased, the water flow control amount is positive; if the current water flow is greater than the reference water flow and the water flow needs to be reduced, the water flow control amount is negative.

[0057] In some embodiments, the primary control unit may use the product of the water flow rate and the inlet surface area of ​​the aeration tank as the current water flow rate.

[0058] The preset flow table can be pre-set based on historical data. The preset flow table can include multiple combinations of water body flow rates and water quality data and reference water body flow rates corresponding to each of the multiple combinations. The reference water body flow rate can be obtained through multiple experiments. The experimental process can include selecting multiple water body flow rates based on a set of water body flow rate and water quality data to conduct multiple experiments, and using the water body flow rate corresponding to the experimental process with the best aeration effect as the reference water body flow rate corresponding to the set of water body flow rate and water quality data. The aeration effect can characterize the amount of sewage components in the water quality data of the water body after aeration treatment. The less sewage components, the better the aeration effect.

[0059] In some embodiments, the primary control unit can determine the collection period of the water quality collection unit based on the second continuous time point; obtain the second monitoring data set of the second continuous time point through the monitoring unit, and obtain the water quality data set collected based on the collection period through the water quality collection unit; determine the water flow control amount based on the second monitoring data set and the water quality data set. For more information about this part, please refer to Figure 4 and its related descriptions.

[0060] In some embodiments, the primary control unit may generate a water volume control instruction based on the water volume flow control quantity.

[0061] Step 220: Control the water volume regulating unit to regulate the water volume based on the water volume control instruction.

[0062] In some embodiments, the primary control unit may send a water volume control instruction to the water volume regulating unit to control the water volume regulating unit to regulate the water volume according to the water flow control amount.

[0063] Step 230 : Determine aeration parameters of at least one aeration device in at least one target time period and generate an aeration control instruction.

[0064] The target period refers to the future period during which aeration treatment is performed. For aeration parameters, see Figure 1 and its related descriptions.

[0065] In some embodiments, the secondary control unit may determine a preset aeration parameter as an aeration parameter of at least one aeration device in at least one target period and generate an aeration control instruction. The preset aeration parameter may be pre-set based on historical experience.

[0066] In some embodiments, the secondary control unit can determine the jump point data in the first monitoring data set based on the first continuous time point collected by the monitoring unit; determine the estimated blowing power and estimated fan blade speed corresponding to the future time period based on the jump point data; and adjust the current aeration parameters of at least one aeration device based on the estimated blowing power and estimated fan blade speed corresponding to the future time period, and generate an aeration control instruction based on the adjusted aeration parameters. For more information about this part, please refer to Figure 3 and its related descriptions.

[0067] Step 240: Adjust at least one aeration device based on the aeration control instruction.

[0068] In some embodiments, the secondary control unit may send an aeration control instruction to the aeration control unit to adjust at least one aeration device.

[0069] In some embodiments, in response to the aeration control unit adjusting the aeration parameters of at least one aeration device based on the aeration control instruction issued by the secondary control unit, the primary control unit can obtain water quality data after aeration treatment through the water quality collection unit; and determine the status of the monitoring device based on the water quality data after aeration treatment.

[0070] The monitoring device condition can reflect the operating condition of the monitoring device.In some embodiments, the monitoring device condition can include whether there is a fault in the monitoring device.

[0071] In some embodiments, the primary control unit can determine whether the wastewater composition in the aerated water quality data meets preset conditions and, based on the determination, determine the status of the monitoring device. If the wastewater composition in the water quality data meets the preset conditions, the monitoring device status can be determined to be normal; if the wastewater composition in the water quality data does not meet the preset conditions, the monitoring device status can be determined to be faulty. The preset condition can be that the wastewater component content is below a threshold. The threshold can be pre-set based on historical experience.

[0072] In some embodiments of the present specification, whether a monitoring device fails is determined by monitoring water quality data after aeration treatment, so that the monitoring device can be repaired or replaced in a timely manner to ensure the certainty of the monitoring data.

[0073] In some embodiments of the present specification, water volume control instructions and aeration control instructions can be used to adjust aeration parameters and water flow in a timely manner before water quality data changes or fluctuates, thereby greatly improving the efficiency and energy saving of the aeration system while ensuring the stability of important water quality parameters in the water body.

[0074] It should be noted that the above description of process 200 is for illustrative purposes only and does not limit the scope of application of this specification. Those skilled in the art may, under the guidance of this specification, make various modifications and alterations to the hand-eye calibration process. However, such modifications and alterations remain within the scope of this specification.

[0075] Figure 3 is an exemplary flow chart of generating aeration control instructions according to some embodiments of this specification. In some embodiments, process 300 is executed by an intelligent aeration control system. Figure 3 As shown, process 300 includes the following steps:

[0076] Step 310 : Determine jumping point data in a first monitoring data set based on a first continuous time point collected by a monitoring unit.

[0077] The first continuous time points refer to multiple consecutive historical time points during which monitoring data is obtained within a preset period. The preset period is a historical time period. The preset period can be pre-set, for example, a day, a morning period of a day, etc.

[0078] In some embodiments, the first continuous time points can be preset. For example, a time point can be set every hour within a preset period, and the number of set time points can also be preset. All time points within the preset period can be determined as the first continuous time points.

[0079] The first monitoring data set refers to a set of multiple historical monitoring data collected by the monitoring unit at the first continuous time point. For example, the first monitoring data set can be a set consisting of multiple continuous historical time points and corresponding historical monitoring data. For an explanation of monitoring data, please refer to Figure 1 and its related descriptions.

[0080] Jump point data refers to monitoring data with large fluctuations in the first monitoring data set and its corresponding historical time points.

[0081] In some embodiments, the secondary control unit can determine whether the historical monitoring data corresponding to each historical time point in the first monitoring data set meets a preset condition, and determine the historical monitoring data and its corresponding historical time point that meet the preset condition as the jump point data. When the historical monitoring data meets the preset condition, the historical monitoring data is considered historical monitoring data with a jump point. The historical time point corresponding to the historical monitoring data is the jump point time.

[0082] In some embodiments, the preset condition includes: the presence of two or more sub-monitoring data exceeding a preset percentile interval in the historical monitoring data corresponding to a certain historical time point. The monitoring data includes multiple sub-monitoring data such as ambient temperature, ambient pressure and humidity, water temperature and water flow rate.

[0083] The preset quantile interval is an interval consisting of the sub-monitoring data corresponding to the upper quantile and the sub-monitoring data corresponding to the lower quantile. The preset quantile interval can be determined based on the preset quantile.

[0084] The preset quantile is used to divide a set of data sorted in numerical order (for example, from small to large) into multiple equal parts.

[0085] In some embodiments, the preset quantile can be preset. For example, the system or a human can preset the preset quantile to 4, and a set of data can be divided into 4 equal parts. For another example, the system or a human can preset the preset quantile to 3, and a set of data can be divided into 3 equal parts.

[0086] In some embodiments, the secondary control unit can determine the upper quantile and the lower quantile in a group of data sorted in numerical order (for example, from small to large) based on a preset quantile. The upper quantile refers to the position corresponding to the largest equal portion after a group of data sorted in numerical order from small to large is divided into multiple equal portions. The lower quantile refers to the position corresponding to the smallest equal portion after a group of data sorted in numerical order from small to large is divided into multiple equal portions.

[0087] For example, a group of data (12) are arranged from small to large according to the numerical value, and the preset quantile can be 4. The upper quantile can be the position in the top 25% of the group of data (9th in the ranking), and the lower quantile can be the position in the bottom 25% of the group of data (3rd in the ranking).

[0088] In some embodiments, the preset quantile interval can be a data interval consisting of sub-monitoring data corresponding to the upper quantile and the lower quantile, respectively, in a set of sub-monitoring data arranged in numerical order. For different sub-monitoring data items, the preset quantile interval for each sub-monitoring data item can be determined based on the upper quantile and the lower quantile.

[0089] In some embodiments, for each item of sub-monitoring data, the secondary control unit can sort the multiple sub-monitoring data corresponding to the first continuous time point (the multiple sub-monitoring data are the sub-monitoring data corresponding to the same sub-monitoring data at multiple different historical time points at the first continuous time point) according to the data size, and determine the preset quantile interval of each sub-monitoring data based on the preset quantile. For example, if the preset quantile is 4, then the numerical interval between the sub-monitoring data corresponding to the first continuous time point and the sub-monitoring data at the top 25% (i.e., upper quantile) and the sub-monitoring data at the bottom 25% (i.e., lower quantile) can be used as the preset quantile interval.

[0090] For example, for the water body temperature data, the water body temperatures at the first consecutive time point are: 6, 47, 49, 15, 42, 41, 7, 39, 43, 40, 36. Sorted from smallest to largest, these water body temperatures are: 6, 7, 15, 36, 39, 40, 41, 42, 43, 47, 49. If the preset quantile is 4, the upper quantile is the 9th quantile (i.e., 43), and the lower quantile is the 3rd quantile (i.e., 15). Among the water body temperatures, 6 and 7 are both below the lower quantile, while 47 and 49 are both above the upper quantile. Therefore, 6, 7, 47, and 49 are all outliers.

[0091] In some embodiments, after determining the preset percentile interval, the secondary control unit can determine whether there are two or more sub-monitoring data in each historical monitoring data in the first monitoring data set that exceed their corresponding preset percentile interval. In response to the existence of two or more sub-monitoring data exceeding the preset percentile interval, the historical monitoring data and its corresponding historical time point are determined to be jump point data.

[0092] In some embodiments, the secondary control unit may send the hopping point data to the primary control unit.

[0093] In some embodiments, the secondary control unit may determine the preset quantile based on historical water quality fluctuation amplitudes of at least one historical aeration treatment process and a ratio of an aeration surface area to a water surface area in the aeration tank.

[0094] The historical water quality fluctuation amplitude can reflect the fluctuation of water quality data during historical aeration treatment processes. In some embodiments, the secondary control unit can calculate the variance and mean of the wastewater composition and / or dissolved oxygen in the historical water quality data of each historical aeration treatment process based on the historical water quality data of at least one historical aeration treatment process, and determine the ratio of the variance to the mean of the wastewater composition and / or dissolved oxygen as the historical water quality fluctuation amplitude corresponding to the historical aeration treatment process.

[0095] In some embodiments, the secondary control unit may store water quality data during the aeration treatment process in a storage device. The water quality data for a single aeration treatment process may include water quality data collected at at least one time point before the aeration treatment, water quality data collected at at least one time point during the aeration treatment, and / or water quality data collected at at least one time point after the aeration treatment.

[0096] In some embodiments, the secondary control unit can read water quality data for each aeration process from a storage device. The storage device can be a built-in storage device of the intelligent aeration control system or an external storage device not included in the intelligent aeration control system, such as a hard disk or optical disk. In some embodiments, water quality data for each aeration process can also be obtained using any method known to those skilled in the art, and this specification does not limit this.

[0097] In some embodiments, the secondary control unit may calculate historical water quality fluctuation amplitudes from multiple historical aeration processes based on historical data, and select at least one historical water quality fluctuation amplitude from the aeration process that conforms to a normal distribution. It is understood that historical water quality fluctuation amplitudes that conform to a normal distribution are more consistent with actual conditions.

[0098] The aeration surface area of ​​an aeration tank refers to the surface area of ​​the aeration discs of the aeration equipment performing aeration. If multiple aeration equipment are used in the aeration tank, the aeration surface area of ​​the aeration tank is the sum of the surface areas of the aeration discs of the multiple aeration equipment.

[0099] The water surface area refers to the surface area of ​​the water in the aeration tank. In some embodiments, the secondary control unit can obtain the aeration surface area and the water surface area in the aeration tank through user input or other methods.

[0100] In some embodiments, the secondary control unit may determine a preset quantile based on a correspondence relationship based on the historical water quality fluctuation amplitude of at least one historical aeration treatment process and the ratio of the aeration surface area in the aeration tank to the water surface area. The correspondence relationship may be pre-set based on historical experience. The correspondence relationship may include a positive correlation between the preset quantile and the historical water quality fluctuation amplitude of at least one historical aeration treatment process and the ratio of the aeration surface area in the aeration tank to the water surface area. For example, the greater the historical water quality fluctuation amplitude of at least one historical aeration treatment process and the greater the ratio of the aeration surface area in the aeration tank to the water surface area, the larger the preset quantile.

[0101] It is understandable that the greater the fluctuation amplitude of historical water quality in at least one historical aeration treatment process, the less stable the aeration treatment environment in the aeration tank is, so a larger preset quantile should be set, thereby making the standard for determining the monitoring data as jump point data more stringent; the larger the ratio of the aeration surface area to the water surface area in the aeration tank, the greater the aeration intensity, that is, the greater the impact of aeration on water treatment, and a higher aeration intensity will reduce the stability of the aeration treatment environment in the aeration tank, so a larger preset quantile should be set, thereby making the standard for determining the monitoring data as jump point data more stringent.

[0102] In some embodiments of the present specification, historical water quality fluctuations and the ratio of the aeration surface area to the water surface area in the aeration tank are taken into consideration when determining the preset quantiles, so that the setting of the preset quantiles is more in line with the actual environmental conditions of the aeration tank, thereby obtaining a more reasonable jump point data screening standard.

[0103] Step 320: Determine the estimated blowing power and the estimated fan blade speed corresponding to the future time period based on the jump point data.

[0104] The future time period refers to the time period after the aeration treatment. In some embodiments, the future time period may include the first consecutive time points after the aeration treatment. For example, the first consecutive time points may be 8:00, 9:00, and 10:00 in a day. If the aeration treatment period is from 10:00 to 15:00, the first consecutive time points after the aeration treatment are 16:00, 17:00, and 18:00.

[0105] The estimated blower power refers to the blower power estimated for a future time period. The estimated fan blade speed refers to the fan blade speed estimated for a future time period.

[0106] In some embodiments, the primary control unit can determine the estimated blast power and estimated fan blade speed based on the jump point data in a variety of ways. For example, the primary control unit can query the preset parameter table for the reference blast power and reference fan blade speed corresponding to the number of jump point times in the jump point data based on the jump point data, and use the determined reference blast power and reference fan blade speed as the estimated blast power and estimated fan blade speed. The jump point time refers to the historical time point corresponding to the historical monitoring data at which a jump point occurs in the first continuous time point. The number of jump point times is the number of jump point times in the first continuous time point.

[0107] The preset parameter table can be pre-set based on historical data. The preset parameter table may include multiple jump point time numbers and corresponding reference blast power and reference fan blade speed. For example, the primary control unit may select multiple aeration processes with good aeration effects from the historical data, construct a clustering vector based on the jump point time number in the jump point data corresponding to the first consecutive time points before each aeration process and the historical blast power and historical fan blade speed corresponding to the first consecutive time points after each jump point time number, and perform clustering to obtain a preset number of cluster center sets; the jump point time number of the cluster center of each cluster center set is counted into the preset parameter table, and the historical blast power and historical fan blade speed corresponding to the first consecutive time points after each jump point time number are counted as reference blast power and reference fan blade speed and are counted into the preset parameter table. The preset number can be pre-set. The types of clustering algorithms may include multiple types, for example, clustering algorithms may include K-Means clustering, density-based clustering method (DBSCAN), etc. The method for determining the cluster center can be any method well known to those skilled in the art.

[0108] In some embodiments, the primary control unit may send the estimated blowing power and the estimated fan blade speed corresponding to the future time period to the second control unit.

[0109] In some embodiments, the primary control unit can determine the interference data based on the jump point data in the first monitoring data set; determine the credible monitoring data based on the first monitoring data set and the interference data; and determine the estimated blowing power and estimated fan blade speed for the future time period based on the water flow, the credible monitoring data, and the jump point data. For an explanation of the water flow, please refer to Figure 2 and its related descriptions.

[0110] Interference data refers to data with sudden changes in values ​​in the first monitoring data set.

[0111] In some embodiments, the primary control unit may determine interference data based on the hopping point data in the first monitoring data set using various methods. For example, the primary control unit may calculate the hop rate of the hopping point data based on the hopping point data in the first monitoring data set, and determine hopping point data with a hop rate greater than a hop rate threshold as interference data. The hop rate threshold may be pre-set.

[0112] The jump degree of the jumping point data can represent the difference between the jumping point data and the monitoring data of the adjacent time points. In some embodiments, the jump degree of the jumping point data can be the average of the ratios of multiple sub-monitoring data in the jumping point data to multiple sub-monitoring data of the adjacent time points.

[0113] In some embodiments, the primary control unit may determine the interference data through an interference data determination model based on the first monitoring data set, the jump point data, and the aeration parameters.

[0114] The interference data determination model refers to a model used to determine interference data. In some embodiments, the interference data determination model may be a machine learning model. For example, the interference data determination model may include any one or a combination of a Long Short-Term Memory (LSTM) model or other custom model structures. The aeration parameter input into the interference data determination model may be the current aeration parameter of at least one aeration device.

[0115] In some embodiments, the interference data determination model may include a multi-layer structure, for example, an input layer, a hidden layer, and an output layer.

[0116] The input layer may include at least one input node, each input node being used to input a type of data. In some embodiments, the primary control unit may determine the number of input layer nodes based on the number of features of the first monitoring data set, aeration parameters, and jump point data, with each node corresponding to a feature. In some embodiments, the primary control unit may determine the number of features of the first monitoring data set, aeration parameters, and jump point data using any feasible method, such as statistical analysis or principal component analysis.

[0117] In some embodiments, the primary control unit may combine the monitoring data, aeration parameters, and jump point data in the first monitoring data set into a feature vector as input to the interference data determination model. In this case, the number of input nodes is one.

[0118] The hidden layer includes multiple LSTM units, each of which contains a memory cell, an input gate, a forget gate, and an output gate. The number of hidden layers and the number of LSTM units in each layer are determined based on the complexity and scale of the input data. The more complex and large the input data, the more hidden layers and the greater the number of LSTM units in each layer.

[0119] In some embodiments, because too many hidden layers can lead to overfitting, the number of hidden layers can be set between 1 and 3. In some embodiments, the number of long short-term memory network units can be set between 20 and 200. In some embodiments, the number of long short-term memory network units can be set between 30 and 180. In some embodiments, the number of long short-term memory network units can be set between 80 and 150. In some embodiments, the number of long short-term memory network units can be set between 100 and 120.

[0120] The output layer may include at least one output node. In some embodiments, the number of output nodes may be equal to the amount of interference data required to be obtained. The amount of interference data required to be obtained may be preset based on historical experience.

[0121] In some embodiments, the primary control unit can determine a model based on a large number of first training samples with first labels, using training interference data such as gradient descent. The first training samples can include a sample first monitoring data set, sample jump point data, and sample aeration parameters. The first label of the first training sample can be interference data in the sample jump point data. In some embodiments, the first training sample can be obtained based on historical data. The sample aeration parameters refer to the aeration parameters of at least one aeration device at the time the sample first monitoring data set was obtained.

[0122] In some embodiments, the first label can be determined based on manual labeling. For example, a technician can mark data in the sample jump point data that actually affects the determination of the estimated blowing power and the estimated fan blade speed, and determine it as the first label.

[0123] In some embodiments, the primary control unit may update the weights and biases of the interference data determination model based on a first preset algorithm. The weights refer to the degree of influence of the first monitoring data set, the jump point data, and the aeration parameters on the output of the interference data determination model. The bias refers to the adjustment value of the output of the interference data determination model. The first preset algorithm may include a backpropagation algorithm.

[0124] In some embodiments, the learning rate, batch size, and number of iterations of the interference data determination model can be pre-set. The learning rate refers to the step size for updating the interference data determination model parameters. The batch size refers to the number of samples used to update the interference data determination model parameters during each training iteration. For example, the batch size can be set between 32 and 256. The number of iterations refers to the total number of iterations used to train the interference data determination model.

[0125] During the model training process, by appropriately adjusting the above parameters, the interference data determination model can be better adapted to the prediction task, and the prediction accuracy and generalization ability of the interference data determination model can be improved.

[0126] In some embodiments, the primary control unit may preprocess the first monitoring data set, aeration parameters, and jump point data before inputting them into the interference data determination model. For example, the primary control unit may remove outliers and noise from the monitoring data, aeration parameters, and jump point data in the first monitoring data set, and perform normalization or standardization. Noise refers to data unrelated to the monitoring data, aeration parameters, and jump point data in the first monitoring data set.

[0127] In some embodiments, the input to the interference data determination model may include bubble characteristics at the first consecutive time points.

[0128] The bubble characteristics may characterize the distribution of air bubbles in the water body. In some embodiments, the bubble characteristics may include the amount of bubbles and the bubble density in each of a plurality of predetermined areas within the aeration tank.

[0129] In some embodiments, the preset area can be divided in a variety of ways. For example, the aeration tank can be divided into grids of a preset size, with each grid divided into a preset area. Another example is that the aeration tank can be divided into areas of a preset size near the location of each blower, with each area of ​​a preset size near the location of each blower divided into a preset area. Another example is that the aeration tank can be divided into areas of a preset size near the location of each monitoring device, with each area of ​​a preset size near the location of each monitoring device divided into a preset area.

[0130] In some embodiments, one or more cameras may be installed near the aeration tank to capture the water surface of the aeration tank. In some embodiments, in response to at least one aeration device being aerated, the primary control unit may control the one or more cameras to capture the water surface of the aeration tank to obtain at least one image. The primary control unit may mark the at least one image according to the divided preset areas, marking the image area of ​​each preset area in the image; recognize the at least one image based on an image recognition algorithm, obtain the amount of bubbles in each image area and the bubble spacing between multiple bubbles, and take the inverse of the average of the multiple bubble spacings to obtain the bubble density. The image recognition algorithm may include a convolutional neural network, a support vector machine, etc.

[0131] In some embodiments, if the input of the interference data determination model includes bubble features at first continuous time points, the first training sample includes sample bubble features.

[0132] In some embodiments of the present specification, bubble features are added to the input of the interference data determination model, and the interference data determination model can be used to obtain the correlation between the bubble features and the interference data. Then, when outputting the interference data, the distribution of air bubbles in the aerated water body can be taken into account, thereby improving the accuracy of determining the interference data.

[0133] In some embodiments of the present specification, the first monitoring data set, the jump point data, and the aeration parameters are processed using a machine learning model, and the self-learning ability of the machine learning model is utilized to improve the accuracy and efficiency of determining the interference data.

[0134] Credible monitoring data refers to monitoring data with a high degree of credibility.

[0135] In some embodiments, the primary control unit may remove interference data from the first monitoring data set based on the first monitoring data set and the interference data, and determine the monitoring data in the first monitoring data set after the interference data is removed as credible monitoring data.

[0136] In some embodiments, the primary control unit can determine the estimated blast power and the estimated fan blade speed in a variety of ways based on the water flow, credible monitoring data, and jump point data. For example, the primary control unit can construct a vector to be matched based on the water flow, credible monitoring data, and jump point data, match a standard vector that meets the preset matching conditions with the vector to be matched in the vector database, and determine the standard blast power and standard fan blade speed corresponding to the standard vector that meets the preset matching conditions as the estimated blast power and estimated fan blade speed corresponding to the vector to be matched. Among them, the vector to be matched can be a feature vector constructed based on the water flow, credible monitoring data, and jump point data. In some embodiments, the preset matching condition can include that the similarity between the standard vector and the vector to be matched is the highest. Among them, the vector distance is negatively correlated with the similarity, that is, the larger the vector distance, the smaller the similarity. The vector distance can include Euclidean distance, cosine distance, etc.

[0137] In some embodiments, the primary control unit may construct a vector database based on historical data. The vector database may include multiple standard vectors and standard blast powers and standard fan blade speeds corresponding to the standard vectors. The standard vectors may be feature vectors constructed based on water flow, reliable monitoring data, and jump point data in the historical data.

[0138] In some embodiments, the primary control unit may select multiple aeration processes with good aeration effects from historical data, construct the water flow, credible monitoring data, jump point data, blast power, and fan blade speed corresponding to each aeration process into a cluster vector for clustering, thereby forming a preset number of cluster centers; construct a feature vector based on the water flow, credible monitoring data, and jump point data corresponding to the cluster center, determine the obtained feature vector as a standard vector, and use the blast power and fan blade speed corresponding to the cluster center as the standard blast power and standard fan blade speed corresponding to the standard vector. The preset number can be pre-set.

[0139] In some embodiments, the primary control unit can determine the estimated blowing power and the estimated fan blade speed through a machine learning model based on water flow, trusted monitoring data, and jump point data.

[0140] like Figure 5As shown, the first-level control unit can determine the estimated jump point data 540 for the future time period through the jump point data prediction model 520 based on the candidate blowing power 511, the candidate fan blade speed 512, the water flow 531, the trusted monitoring data 532 and the jump point data 533; and determine the estimated blowing power and the estimated fan blade speed corresponding to the future time period based on the estimated jump point data 540.

[0141] A hop data prediction model refers to a model used to determine estimated hop data. In some embodiments, the hop data prediction model may be a machine learning model. For example, the hop data prediction model may include any one or a combination of a Graph Neural Network (GNN) model, a Neural Network (NN) model, or other custom model structures.

[0142] In some embodiments, as Figure 5 As shown, the jumping point data prediction model 520 may include a water quality prediction layer 521 and a jumping point prediction layer 522. The water quality prediction layer may include a graph neural network (GNN) model, and the jumping point prediction layer may include a neural network (NN) model or any other custom model structure or combination thereof.

[0143] In some embodiments, as Figure 5 As shown, the input of the water quality prediction layer 521 may include the aeration graph structure 513 , and the output of the water quality prediction layer 521 may include the estimated water quality data 530 of each node.

[0144] The estimated water quality data refers to the estimated water quality data after aeration treatment according to the candidate blower power and the candidate fan blade speed.

[0145] The aeration graph structure 513 refers to a graph structure that reflects the positional relationship between aeration devices.

[0146] In some embodiments, the primary control unit can construct an aeration graph structure based on the positional relationships between aeration devices. Nodes in the aeration graph structure correspond to blowers or agitators. Node features can include node type, monitoring data, candidate blower power, or candidate fan speed.

[0147] Candidate blast power 511 refers to the blast power to be determined. Candidate fan blade speed 512 refers to the fan blade speed to be determined. In some embodiments, the primary control unit can randomly generate candidate blast powers and candidate fan blade speeds based on a reference range of blast power and fan blade speed. In some embodiments, the reference range can be pre-set based on historical experience.

[0148] In some embodiments, the first-level control unit can construct an aeration graph structure with different node characteristics (candidate blower power and candidate fan blade speed) based on different combinations of candidate blower power and candidate fan blade speed, and input them into the jump point data prediction model respectively to determine the estimated water quality data of each node under different combinations of candidate blower power and candidate fan blade speed, and further determine the estimated jump point data under different combinations of candidate blower power and candidate fan blade speed.

[0149] The edges of the aeration graph structure can represent the connectivity between nodes or the distance between nodes. In some embodiments, in response to the presence of a pipeline connection between two blowers, the primary control unit can connect the edges between the nodes representing the two blowers as first-class edges; in response to the distance between a blower and a stirring device being less than a distance threshold, the primary control unit can connect the edges between the nodes representing the blower and the stirring device as second-class edges; in response to the distance between the two stirring devices being less than a distance threshold, the primary control unit can connect the edges between the nodes representing the two stirring devices as third-class edges. The characteristics of the edges can include the distance between the nodes and the type of edge (e.g., first-class edge, second-class edge, or third-class edge).

[0150] In some embodiments, as Figure 5 As shown, the input of the jumping point prediction layer 522 may include water flow 531, estimated water quality data 530 (for example, including estimated water quality data of each node), trusted monitoring data 532 and jumping point data 533, and the output of the jumping point prediction layer 522 may include estimated jumping point data 540.

[0151] The estimated jump point data refers to the jump point data corresponding to the first consecutive time point in the estimated future time period.

[0152] In some embodiments, the primary control unit can train a jump point data prediction model based on a large number of second training samples with second labels, using methods such as gradient descent. The second training samples can include sample candidate blast power, sample candidate fan blade speed, sample aeration graph structure, sample water flow, sample trusted monitoring data, and sample jump point data. The second label of the second training sample can be the actual jump point data for a future time period after the aeration equipment is operated based on the sample candidate blast power and sample candidate fan blade speed. In some embodiments, the second training sample can be obtained based on historical data. The second label can be determined experimentally. The sample aeration graph structure can include a historical aeration graph structure determined based on historical data. The nodes and attributes, and the edges and attributes of the historical aeration graph structure are similar to those described above.

[0153] Exemplarily, the first-level control unit can input the sample candidate blowing power, the sample candidate fan blade speed and the sample aeration map structure into the initial water quality prediction layer to obtain the estimated water quality data output by the initial water quality prediction layer; the estimated water quality data is used as input, together with the sample water body flow, the sample credible monitoring data and the sample jump point data, into the initial jump point prediction layer, and a loss function is constructed through the second label and the estimated jump point data output by the initial jump point prediction layer; the initial jump point prediction layer is updated based on the iterative result of the loss function, and the initial water quality prediction layer is updated synchronously. When the loss function of the initial jump point prediction layer and the initial water quality prediction layer meets the preset conditions, the jump point data prediction model training is completed, wherein the preset conditions may be that the loss function converges, the number of iterations reaches a set value, etc.

[0154] In some embodiments, the first-level control unit can use the jump point data prediction model to process the aeration graph structures with different node characteristics (for example, different combinations of candidate blowing powers and candidate fan blade speeds) separately, and determine the estimated jump point data under different combinations of candidate blowing powers and candidate fan blade speeds; and select the aeration graph structure with the least estimated jump point data, and use the candidate blowing power and candidate fan blade speed in the node characteristics of the aeration graph structure as the estimated blowing power and estimated fan blade speed.

[0155] In some embodiments of the present specification, by constructing an aeration graph structure, scattered aeration equipment and its attributes can be effectively organized, which helps to quickly and efficiently obtain the positional relationship of the aeration equipment from the aeration graph structure; by processing candidate blowing powers, candidate fan blade speeds, aeration graph structures, water flow rates, trusted monitoring data, and jump point data through a jump point data prediction model, the unique advantages of machine learning models can be utilized to clarify the correlation between input content and output results based on a large amount of complex data, thereby obtaining more accurate estimated jump point data.

[0156] In some embodiments of the present specification, by removing interference data in the monitoring data, more reliable monitoring data can be obtained, thereby improving the accuracy of predicting the blowing power and fan blade speed in the future time period.

[0157] Step 330 : adjusting aeration parameters based on the estimated blowing power and the estimated fan blade speed, and generating an aeration control instruction based on the adjusted aeration parameters.

[0158] In some embodiments, the secondary control unit can determine the estimated blowing power and estimated fan blade speed as the blowing power and estimated fan blade speed in the aeration parameters based on the estimated blowing power and estimated fan blade speed obtained from the primary control unit, and generate an aeration control instruction based on the adjusted aeration parameters.

[0159] In some embodiments of the present specification, the blower power and fan blade speed that can better meet the aeration needs of the future time period can be predicted based on the jump point data, and the aeration parameters are adjusted based on the predicted blower power and fan blade speed, and then the aeration equipment is adjusted to ensure the quality of subsequent aeration treatment.

[0160] Figure 4 This is an exemplary flow chart for determining the water flow control amount according to some embodiments of this specification.

[0161] Step 410: Determine a collection period of the water quality collection unit based on the second continuous time points.

[0162] The second continuous time points refer to a plurality of continuous time points after a period of aeration treatment, and the second continuous time points can be adjusted according to actual conditions.

[0163] In some embodiments, the primary control unit may obtain the second continuous time points through user input, etc. For example, the user may specify multiple continuous time points as the second continuous time points.

[0164] In some embodiments, the primary control unit may determine the second continuous time point based on the jumping point data in the first monitoring data set.

[0165] In some embodiments, the primary control unit may query the preset continuous time points corresponding to the jumping point data in the preset time table based on the jumping point data in the first monitoring data set, and determine the preset continuous time points as the second continuous time points.

[0166] The preset flow table can be pre-set based on historical data. The preset flow table can include multiple sets of jump point data and corresponding preset continuous time points. For example, the primary control unit can select multiple aeration processes with good aeration effects from the historical data, calculate the jump point data for these multiple aeration processes, select the aeration process with the most jump point data using the same aeration parameters, and use the second continuous time point of this aeration process as the preset continuous time point. This data is then included in the preset time table along with the jump point data for this aeration process.

[0167] In some embodiments of the present specification, since the jumping point data can reflect the stability of the current monitoring data, a second continuous time point that better meets the current monitoring requirements can be determined based on the jumping point data.

[0168] The collection cycle refers to the period during which the water quality collection unit collects water quality data. The collection cycle may include multiple collection time points for water quality data collection.

[0169] In some embodiments, the primary control unit may determine the acquisition period as a ratio of the time length of the second continuous time points to the number of time points of the second continuous time points, wherein the time length of the second continuous time points refers to the time interval from the first time point to the last time point in the second continuous time.

[0170] Step 420: Acquire a second monitoring data set at a second continuous time point through the monitoring unit, and acquire a water quality data set collected based on a collection period through the water quality collection unit.

[0171] The second monitoring data set refers to a set of monitoring data collected by the monitoring unit at the second continuous time point. In some embodiments, the primary control unit can obtain the second monitoring data set at the second continuous time point through the monitoring unit.

[0172] The water quality data set refers to a set of water quality data collected by the water quality collection unit based on a collection period. In some embodiments, the water quality data set may include water quality data collected by at least one water quality collection device at multiple collection time points.

[0173] In some embodiments, the primary control unit may obtain a water quality data set through a water quality collection unit.

[0174] Step 430: Determine the water flow control amount based on the second monitoring data set and the water quality data set.

[0175] In some embodiments, the primary control unit may determine the water flow control amount based on the second monitoring data set and the water quality data set using a variety of methods. For example, the primary control unit may calculate the mean of each monitoring data in the second monitoring data set and determine the water flow control amount using a second preset algorithm.

[0176] For example, the second preset algorithm may be as shown in formula (1):

[0177] S=(k1*M+k2*cos(q,p))*AB (1)

[0178] Where S represents the water flow control amount, M represents the sum of the means of each monitoring data in the second monitoring data set, q represents the vector composed of water quality data, p represents the standard water quality data vector, A represents the standard water flow, B represents the current water flow, k1 represents the coefficient of the sum of the means of each monitoring data in the second monitoring data set, and k2 represents the coefficient of cos(q, p). For an explanation of water flow, please refer to Figure 3 and its related descriptions.

[0179] A standard water quality data vector is a vector consisting of standard water quality data. Standard water quality data refers to the theoretical water quality data for the current water body. Standard water flow rate refers to the theoretical water flow rate for the current water body. Standard water quality data and standard water flow rate can be pre-set based on experiments.

[0180] In some embodiments, the primary control unit can determine the credible monitoring data of the second continuous time point based on the monitoring data in the second monitoring data set and the jump point data corresponding to the second monitoring data set; determine the water flow control amount based on the credible monitoring data of the second continuous time point, the water quality data set, and the estimated blast power and the estimated fan blade speed. Among them, the method for determining the jump point data corresponding to the second monitoring data set and the method for determining the credible monitoring data of the second continuous time point are similar to those described above. For instructions on estimating blast power and estimating fan blade speed, please refer to Figure 3 and its related descriptions.

[0181] In some embodiments, the primary control unit may determine the water flow control amount through a third preset algorithm based on the trusted monitoring data at the second continuous time point, the water quality data set, the estimated blowing power, and the estimated fan blade speed.

[0182] Exemplarily, the third preset algorithm may be as shown in formula (2):

[0183] S=(w1*M+w2*cos(q,p)+w3*x+w4*y)*AB (2)

[0184] Among them, S represents the water flow control amount, M represents the sum of the means of each monitoring data in the second monitoring data set, q represents the vector composed of water quality data, p represents the standard water quality data vector, x represents the estimated blowing power, y represents the estimated fan blade speed, A represents the standard water flow, B represents the current water flow, w1 represents the coefficient of the sum of the means of each monitoring data in the second monitoring data set, w2 represents the coefficient of cos(q, p), w3 represents the coefficient of the estimated blowing power, and w4 represents the coefficient of the estimated fan blade speed.

[0185] In some embodiments of the present specification, a water flow control amount more suitable for a subsequent aeration treatment process can be determined based on the credible monitoring data at the second continuous time point, the water quality data set, the estimated blowing power, and the estimated fan blade speed.

[0186] In some embodiments, the primary control unit may determine the water flow control amount through a fourth preset algorithm based on the trusted monitoring data of the second continuous time point, the water quality data set, the estimated blowing power and the estimated fan blade speed.

[0187] In some embodiments, the fourth preset algorithm can be pre-set. For example, the fourth preset algorithm can be that in response to the estimated blast power, the estimated fan blade speed and the current blast power and fan blade speed being consistent, the water flow control amount is 0; in response to the estimated blast power, the estimated fan blade speed and the current blast power and fan blade speed being inconsistent, the estimated jump point data corresponding to the candidate water flow can be determined through the jump point data prediction model based on the trusted monitoring data, water quality data set, candidate water flow and estimated blast power and estimated fan blade speed at the second continuous time point, the candidate water flow with the least estimated jump point data is selected, and the difference between the candidate water flow and the current water flow is determined as the water flow control amount. Among them, if the current water flow is less than the candidate water flow and the water flow needs to be increased, the water flow control amount is positive; if the current water flow is greater than the candidate water flow and the water flow needs to be reduced, the water flow control amount is negative. For instructions on determining the estimated jump point data, please refer to Figure 3 and its related descriptions.

[0188] The candidate water flow rate refers to the water flow rate to be determined. In some embodiments, the primary control unit can randomly generate the candidate water flow rate based on a reference range of water flow rates. In some embodiments, the reference range can be pre-set based on historical experience.

[0189] In some embodiments of the present specification, an optimal candidate water flow rate may be selected based on the estimated jump point data, thereby determining a more reasonable water flow rate control amount.

[0190] In some embodiments of the present specification, the second monitoring data set and the water quality data set can reflect the aeration treatment effect after aeration treatment. A more appropriate water flow control amount can be determined based on the second monitoring data set and the water quality data set, thereby ensuring a better aeration treatment effect.

[0191] Some embodiments of this specification also provide an intelligent aeration control device, including at least one processor and at least one memory, the memory is used to store computer instructions, and the processor is used to execute at least part of the computer instructions to implement any of the intelligent aeration control methods described in the above embodiments.

[0192] Some embodiments of this specification further provide a computer-readable storage medium, which stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes any one of the intelligent aeration control methods described in the above embodiments.

[0193] Furthermore, certain features, structures, or characteristics in one or more embodiments of this specification may be appropriately combined.

[0194] In some embodiments, numbers are used to describe the quantity of components and attributes. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise stated, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the description and claims are approximate values, which may change according to the required characteristics of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the settings of such numerical values ​​are as accurate as possible within the feasible range.

[0195] If there is any inconsistency or conflict between the descriptions, definitions, and / or usage of terms in the materials cited in this specification and the contents described in this specification, the descriptions, definitions, and / or usage of terms in this specification shall prevail.

Claims

1. An intelligent aeration control system, characterized in that: The system includes a primary control unit, a secondary control unit, a monitoring unit, an aeration control unit, a water volume regulating unit, and a water quality collection unit, wherein: the water quality collection unit, the water volume regulating unit, and the secondary control unit are in communication with the primary control unit, and the monitoring unit and the aeration control unit are in communication with the secondary control unit; the water quality collection unit is used to collect water quality data, and the monitoring unit is used to obtain monitoring data through at least one monitoring device, wherein the monitoring data includes environmental parameters, water temperature, and water flow rate, wherein the environmental parameters include ambient temperature, ambient pressure, and air humidity; The water flow regulating unit performs water flow regulation based on the water flow control instruction issued by the primary regulating unit, wherein the water flow control instruction includes a water flow regulation amount; The aeration control unit adjusts the aeration parameters of at least one aeration device based on the aeration control instruction issued by the secondary control unit; The primary control unit is configured on a terminal device in the control room, and is configured as follows: determining a second continuous time point based on jumping point data in a first monitoring data set of first continuous time points collected by the monitoring unit; determining a collection period of the water quality collection unit based on the second continuous time points; Acquire, by the monitoring unit, a second set of monitoring data at the second continuous time point, and acquire, by the water quality acquisition unit, a set of water quality data acquired based on the acquisition period; Determining credible monitoring data corresponding to the second continuous time points based on the monitoring data in the second monitoring data set and the jumping point data corresponding to the second monitoring data set; Determining the water flow control amount and generating the water flow control instruction based on the trusted monitoring data, the water quality data set, the estimated blower power and the estimated fan blade speed; The secondary control unit is configured on the at least one aeration device, and is configured to determine an aeration parameter of the at least one aeration device in at least one target time period and generate the aeration control instruction, wherein the aeration parameter includes at least one of a blowing power and a fan blade speed; The secondary control unit is further configured to: Determine the jumping point data based on the first monitoring data set, and send the jumping point data to the primary control unit, wherein the jumping point data refers to the monitoring data with large fluctuations in the first monitoring data set and its corresponding historical time point. To determine the jumping point data, the secondary control unit is further configured to: determining a preset quantile based on a historical water quality fluctuation amplitude of at least one historical aeration treatment process and a ratio of an aeration surface area to a water surface area in the aeration tank, wherein the historical water quality fluctuation amplitude of the at least one historical aeration treatment process conforms to a normal distribution; A preset quantile interval is determined based on the preset quantile, the preset quantile interval is an interval composed of sub-monitoring data corresponding to an upper quantile and sub-monitoring data corresponding to a lower quantile, the preset quantile interval is determined based on a preset quantile, the preset quantile is used to divide a group of data sorted in order of numerical value into multiple equal parts, the secondary control unit determines the upper quantile and the lower quantile in the group of data sorted in order of numerical value based on the preset quantile, wherein the upper quantile refers to a position corresponding to the largest equal part after a group of data sorted in order of numerical value from small to large is divided into multiple equal parts, and the lower quantile refers to a position corresponding to the smallest equal part after a group of data sorted in order of numerical value from small to large is divided into multiple equal parts; determining whether the historical monitoring data corresponding to each historical time point in the first monitoring data set meets a preset condition, and determining the historical monitoring data that meets the preset condition and the corresponding historical time point as the jump point data, wherein the preset condition includes: two or more sub-monitoring data in the historical monitoring data corresponding to a certain historical time point exceed a preset quantile interval; adjusting the aeration parameters based on the estimated blowing power and the estimated fan blade speed corresponding to the future time period obtained from the primary control unit, and generating the aeration control instruction based on the adjusted aeration parameters; The primary control unit is further configured to: Determine the estimated blowing power and the estimated fan blade speed corresponding to the future time period based on the jump point data obtained from the secondary control unit, and send the estimated blowing power and the estimated fan blade speed to the secondary control unit; The primary control unit is further configured to: Acquiring water quality data after aeration treatment based on the water quality collection unit; determining a monitoring device condition based on the water quality data after the aeration treatment, wherein the monitoring device condition includes whether the monitoring device has a fault; The primary control unit is further configured to: determining interference data based on the hopping point data in the first monitoring data set; Determining, based on the first monitoring data set and the interference data, credible monitoring data corresponding to the first monitoring data set; Based on the candidate blower power and candidate fan blade speed, an aeration graph structure is constructed; Determining estimated jumping point data for a future time period using a jumping point data prediction model based on the aeration map structure, the water flow, the trusted monitoring data, and the jumping point data, wherein the jumping point prediction model is a machine learning model and includes a water quality prediction layer and a jumping point prediction layer; Based on the estimated jump point data, the estimated blowing power and the estimated fan blade speed are determined.

2. The system according to claim 1, wherein The primary control unit is further configured to: determining the interference data by an interference data determination model based on the first monitoring data set, the jump point data, and the aeration parameter, wherein the interference data determination model is a machine learning model; The input of the interference data determination model includes bubble characteristics at the first continuous time points, and the bubble characteristics include the bubble amount and bubble density of each of a plurality of preset areas in the aeration tank.

3. An intelligent aeration control method, characterized in that: The method is implemented by the intelligent aeration control system according to claim 1, and the method comprises: Determining a second continuous time point based on jump point data in a first monitoring data set of first continuous time points collected by the monitoring unit; determining a collection period of the water quality collection unit based on the second continuous time points; Acquire, by the monitoring unit, a second set of monitoring data at the second continuous time point, and acquire, by the water quality acquisition unit, a set of water quality data acquired based on the acquisition period; Determining credible monitoring data corresponding to the second continuous time points based on the monitoring data in the second monitoring data set and the jumping point data corresponding to the second monitoring data set; Determining a water flow control amount and generating a water flow control instruction based on the trusted monitoring data, the water quality data set, the estimated blower power, and the estimated fan blade speed, and controlling a water flow regulating unit to perform water flow regulation based on the water flow control instruction; wherein the monitoring data is collected by at least one monitoring device configured in the monitoring unit, and the water quality data is collected by the water quality collection unit; determining an aeration parameter of at least one aeration device in at least one target time period and generating an aeration control instruction, and adjusting the at least one aeration device based on the aeration control instruction, wherein the aeration parameter includes at least one of a blowing power and a fan blade speed; The method further comprises: Determining the jumping point data based on the first monitoring data set, and sending the jumping point data to the primary control unit, wherein the jumping point data refers to the monitoring data with large fluctuations in the first monitoring data set and its corresponding historical time point. To determine the jumping point data, the method further includes: determining a preset quantile based on a historical water quality fluctuation amplitude of at least one historical aeration treatment process and a ratio of an aeration surface area to a water surface area in the aeration tank, wherein the historical water quality fluctuation amplitude of the at least one historical aeration treatment process conforms to a normal distribution; A preset quantile interval is determined based on the preset quantile, the preset quantile interval is an interval composed of sub-monitoring data corresponding to an upper quantile and sub-monitoring data corresponding to a lower quantile, the preset quantile interval is determined based on a preset quantile, the preset quantile is used to divide a group of data sorted in order of numerical value into multiple equal parts, the secondary control unit determines the upper quantile and the lower quantile in the group of data sorted in order of numerical value based on the preset quantile, wherein the upper quantile refers to a position corresponding to the largest equal part after a group of data sorted in order of numerical value from small to large is divided into multiple equal parts, and the lower quantile refers to a position corresponding to the smallest equal part after a group of data sorted in order of numerical value from small to large is divided into multiple equal parts; determining whether the historical monitoring data corresponding to each historical time point in the first monitoring data set meets a preset condition, and determining the historical monitoring data that meets the preset condition and the corresponding historical time point as the jump point data, wherein the preset condition includes: two or more sub-monitoring data in the historical monitoring data corresponding to a certain historical time point exceed a preset quantile interval; adjusting the aeration parameters based on the estimated blowing power and the estimated fan blade speed corresponding to the future time period obtained from the primary control unit, and generating the aeration control instruction based on the adjusted aeration parameters; and determining interference data based on the hopping point data in the first monitoring data set; Determining, based on the first monitoring data set and the interference data, credible monitoring data corresponding to the first monitoring data set; Based on the candidate blower power and candidate fan blade speed, an aeration graph structure is constructed; Determining estimated jumping point data for a future time period using a jumping point data prediction model based on the aeration map structure, the water flow, the trusted monitoring data, and the jumping point data, wherein the jumping point prediction model is a machine learning model and includes a water quality prediction layer and a jumping point prediction layer; Determine the estimated blast power and the estimated fan blade speed corresponding to the future time period based on the estimated jump point data, and send the estimated blast power and the estimated fan blade speed to the secondary control unit; Acquiring water quality data after aeration treatment based on the water quality collection unit; The monitoring device status is determined based on the water quality data after the aeration treatment, where the monitoring device status includes whether there is a fault in the monitoring device.

4. The method according to claim 3, wherein The determining, based on the hopping point data in the first monitoring data set, interference data includes: determining the interference data by an interference data determination model based on the first monitoring data set, the jump point data, and the aeration parameter, wherein the interference data determination model is a machine learning model; The input of the interference data determination model includes bubble characteristics at the first continuous time points, and the bubble characteristics include the bubble amount and bubble density of each of a plurality of preset areas in the aeration tank.

5. An intelligent aeration control device, characterized in that: The apparatus comprises at least one processor and at least one memory; The at least one memory is for storing computer instructions; The at least one processor is configured to execute at least part of the computer instructions to implement the intelligent aeration control method according to any one of claims 3 to 4.

6. A computer-readable storage medium storing computer instructions, characterized in that: After the computer reads the computer instructions in the storage medium, the computer executes the intelligent aeration control method according to any one of claims 3 to 4.

Images