A blower optimization control system and method for wastewater treatment

Abstract

The application discloses a kind of blast fan optimization control system and method for wastewater treatment, it is related to wastewater treatment technical field, including: reading predetermined wastewater index, the characteristic collection of target wastewater is carried out, and target wastewater characteristic information is obtained;Target wastewater characteristic information is used as the input information of dissolved oxygen demand prediction model, and target demand dissolved oxygen concentration is obtained;Reading predetermined aeration index, and the target aeration control space is obtained by analyzing predetermined aeration index;Predetermined control fitness function is introduced as optimization evaluation strategy, and target demand dissolved oxygen concentration is used as optimization constraint, global optimization is carried out in target aeration control space, and the optimal aeration control scheme is obtained;According to optimal aeration control scheme, the target blast fan of target wastewater is carried out energy-saving aeration treatment.The application solves the technical problems that the existing technology has low processing efficiency and serious energy consumption when carrying out biological treatment on wastewater, achieves the technical effects of efficient wastewater treatment and significant energy saving.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of wastewater treatment, in particular to an air blower optimization control system and method for wastewater treatment. BACKGROUND

[0002] With the acceleration of industrialization and urbanization, the amount of wastewater discharge is increasing, and wastewater treatment has become an important part of environmental protection and resource management. However, the traditional wastewater treatment system has many shortcomings in energy management, and it is difficult to meet the needs of modern society for high efficiency, energy saving and environmental protection.

[0003] The biological treatment link in the wastewater treatment process, especially the aeration link, usually consumes a large amount of energy. The traditional aeration control method leads to low wastewater treatment efficiency and serious energy waste. With the continuous expansion of wastewater treatment scale and the complication of treatment process, these problems are more prominent, and an more efficient and intelligent control method is urgently needed to optimize the wastewater treatment process and reduce energy consumption. SUMMARY

[0004] The present application provides an air blower optimization control system and method for wastewater treatment, which is used to solve the technical problems of low treatment efficiency and serious energy consumption in the prior art for biological treatment of wastewater.

[0005] In view of the above problems, the present application provides an air blower optimization control system and method for wastewater treatment.

[0006] The first aspect of the present application provides an air blower optimization control system for wastewater treatment, which comprises:

[0007] a feature collection module for reading a predetermined wastewater index and collecting features of target wastewater based on the predetermined wastewater index to obtain target wastewater feature information; a dissolved oxygen demand prediction module for taking the target wastewater feature information as input information of a dissolved oxygen demand prediction model to obtain a target required dissolved oxygen concentration, wherein the target required dissolved oxygen concentration refers to the minimum dissolved oxygen concentration for biological treatment of the target wastewater; a predetermined aeration index reading module for reading a predetermined aeration index and analyzing the predetermined aeration index to obtain a target aeration control space; an optimization module for introducing a predetermined control fitness function as an optimization evaluation strategy and taking the target required dissolved oxygen concentration as an optimization constraint to perform global optimization in the target aeration control space to obtain an optimal aeration control scheme; and an aeration treatment module for controlling a target air blower to perform aeration treatment on the target wastewater according to the optimal aeration control scheme.

[0008] In a second aspect of the present application, a method for optimizing control of a blower for wastewater treatment is provided, the method comprising:

[0009] reading a predetermined wastewater index and collecting features of target wastewater based on the predetermined wastewater index to obtain target wastewater feature information; taking the target wastewater feature information as input information of a dissolved oxygen demand prediction model to obtain a target required dissolved oxygen concentration, wherein the target required dissolved oxygen concentration refers to the minimum dissolved oxygen concentration for biological treatment of the target wastewater; reading a predetermined aeration index and analyzing the predetermined aeration index to obtain a target aeration control space; introducing a predetermined control fitness function as an optimization evaluation strategy and taking the target required dissolved oxygen concentration as an optimization constraint to perform global optimization in the target aeration control space to obtain an optimal aeration control scheme; and controlling a target blower to perform aeration treatment on the target wastewater according to the optimal aeration control scheme.

[0010] The technical solutions provided in the present application have at least the following technical effects or advantages:

[0011] The present application reads a predetermined wastewater index and collects features of target wastewater based on the predetermined wastewater index to obtain target wastewater feature information; takes the target wastewater feature information as input information of a dissolved oxygen demand prediction model to obtain a target required dissolved oxygen concentration, wherein the target required dissolved oxygen concentration refers to the minimum dissolved oxygen concentration for biological treatment of the target wastewater; reads a predetermined aeration index and analyzes the predetermined aeration index to obtain a target aeration control space; introduces a predetermined control fitness function as an optimization evaluation strategy and takes the target required dissolved oxygen concentration as an optimization constraint to perform global optimization in the target aeration control space to obtain an optimal aeration control scheme; and controls a target blower to perform aeration treatment on the target wastewater according to the optimal aeration control scheme. The present application solves the technical problems of low treatment efficiency and high energy consumption in biological treatment of wastewater in the prior art, calculates the dissolved oxygen demand by obtaining wastewater and aeration indexes and using big data analysis and prediction models, and optimizes aeration parameters by a global optimization algorithm to control the blower to perform energy-saving aeration treatment, thereby achieving the technical effects of efficient wastewater treatment and significant energy saving. BRIEF DESCRIPTION OF DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative effort.

[0013] Figure 1A structure schematic diagram of an air blower optimization control system for wastewater treatment is provided for the embodiment of the present application.

[0014] Figure 2 A flow schematic diagram of an air blower optimization control method for wastewater treatment is provided for the embodiment of the present application.

[0015] Legend: feature collection module 11, dissolved oxygen demand prediction module 12, predetermined aeration index reading module 13, optimization module 14, aeration treatment module 15. DETAILED DESCRIPTION

[0016] The present application provides an air blower optimization control system and method for wastewater treatment, which solves the technical problems of low processing efficiency and high energy consumption in biological treatment of wastewater in the prior art by obtaining wastewater and aeration indexes, calculating dissolved oxygen demand by using big data analysis and prediction model, and optimizing aeration parameters by using global optimization algorithm to control the air blower for energy-saving aeration treatment, thereby achieving the technical effects of efficient wastewater treatment and significant energy saving.

[0017] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0018] It should be noted that any variation of the terms "comprise" and "have" is intended to cover non-exclusive inclusion, for example, a process, method, system, product or server comprising a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or modules not clearly listed or inherent to the process, method, product or device.

[0019] Embodiment one, as shown in the present application provides an air blower optimization control system for wastewater treatment, which is used to execute an air blower optimization control method for wastewater treatment as shown in the present application. Figure 1 The system comprises: Figure 2

[0020] The feature collection module 11 reads predetermined wastewater indexes and collects features of target wastewater based on the predetermined wastewater indexes to obtain target wastewater feature information.

[0021] Further, in the system provided by the application, the predetermined wastewater indexes include sludge concentration, water flow rate, water temperature, influent flow rate and organic matter concentration.

[0022] ​In the embodiment of the present application, the feature collection module first reads the predetermined wastewater indicators. The predetermined wastewater indicators include sludge concentration, water flow rate, water temperature, influent flow rate and organic matter concentration. The sludge concentration refers to the content of suspended solids in wastewater, reflecting the density and volume of sludge; the water flow rate refers to the speed of wastewater flowing in the pipeline or treatment system; the water temperature is the temperature of the wastewater; the influent flow rate represents the speed and quantity of wastewater entering the treatment system; and the organic matter concentration is the content of organic pollutants in the wastewater.

[0023] After reading the predetermined wastewater indicators, the feature collection module collects features of the target wastewater based on these indicators, extracts key information that can accurately reflect the state of the wastewater and the treatment demand by measuring and analyzing various physical and chemical parameters of the wastewater. Specifically, during feature collection, a variety of sensors and measuring devices are used, such as a suspended solids sensor to measure sludge concentration, a flowmeter to measure water flow rate, a thermometer to measure water temperature, a flowmeter to measure influent flow rate, and a chemical analyzer to measure organic matter concentration. Through the above process, the target wastewater feature information is obtained.

[0024] The dissolved oxygen demand prediction module 12 takes the target wastewater feature information as input information of the dissolved oxygen demand prediction model, and obtains a target required dissolved oxygen concentration, wherein the target required dissolved oxygen concentration refers to the minimum dissolved oxygen concentration required for biological treatment of the target wastewater.

[0025] In the embodiment of the present application, the dissolved oxygen demand prediction module inputs the target wastewater feature information as input information of the dissolved oxygen demand prediction model into the dissolved oxygen demand prediction model. The dissolved oxygen demand prediction model is a pre-constructed machine learning model used to predict the minimum dissolved oxygen concentration required for wastewater in the biological treatment process. By processing and analyzing the input target wastewater feature information, the target required dissolved oxygen concentration is obtained.

[0026] Further, the dissolved oxygen demand prediction module 12 in the system provided by the application embodiment is also used for:

[0027] arbitrarily obtaining a first historical record in the historical wastewater biological treatment record; performing normalized weighted analysis on the extracted first historical treatment quality information in the first historical record to obtain a first historical treatment quality index; if the first historical treatment quality index reaches a predetermined quality index threshold, issuing a data building instruction; based on the data building instruction, extracting first historical wastewater feature information and a first historical dissolved oxygen concentration in the first historical record, and forming first training data; based on the principle of neural network, performing supervised learning and verification on the first training data to obtain the dissolved oxygen demand prediction model.

[0028] In the embodiments of the present application, first, a first historical record in the historical wastewater biological treatment record is randomly obtained from the storage database. The storage database contains a large amount of wastewater treatment data, which is collected and saved in real time during the wastewater treatment process through sensors and monitoring devices. The first historical record refers to a record randomly selected from these data.

[0029] Next, the first historical treatment quality information in the extracted first historical record is normalized and weighted for analysis, and a first historical treatment quality index is obtained. Specifically, the data standardization method is used to normalize the indicators of different dimensions, so that they are within the same scale range. Then, through the weighting algorithm, each index is given a weight preset according to its importance in the treatment quality, and a quality evaluation value is calculated, which is the first historical treatment quality index. If the first historical treatment quality index reaches a predetermined quality index threshold, a data set instruction is issued. The predetermined quality index threshold is a quality standard preset by technical experts, which ensures that only high-quality data can be used for model training. Based on the data set instruction, the first historical wastewater feature information and the first historical dissolved oxygen concentration are extracted from the first historical record. The wastewater feature information includes sludge concentration, water flow rate, water temperature, influent flow rate and organic matter concentration, etc., and the dissolved oxygen concentration refers to the content of oxygen in water during wastewater treatment. These extracted information is integrated into the first training data.

[0030] Then the first training data is input into the neural network model for supervised learning. The neural network model, such as the long short-term memory network, uses the back propagation algorithm to continuously adjust the network weights by inputting the training data and the corresponding output labels, and learns the mapping relationship between the input and the output. During training, part of the historical data is reserved as a validation data set. The validation data set is a part of data randomly extracted from the historical wastewater biological treatment record, which does not participate in training and is only used to evaluate the performance of the model during and after training. After training is completed, the model is tested using this validation data set to evaluate its prediction accuracy and generalization ability. By comparing the prediction results with the actual results of the validation data set, it is determined whether the model has good prediction ability, ensuring that it can accurately predict the minimum dissolved oxygen concentration required for wastewater during biological treatment.

[0031] Finally, through the above steps, the construction of the dissolved oxygen demand prediction model is completed.

[0032] Further, the dissolved oxygen demand prediction module 12 in the system provided by the embodiments of the present application is also used for:

[0033] read predetermined quality characteristics, and based on the predetermined quality characteristics, traverse extraction is performed on the first historical treatment quality information to obtain first historical quality characteristic parameters; the first historical quality characteristic parameters are processed and analyzed by using a coefficient of variation principle to obtain the first historical treatment quality index; wherein the predetermined quality characteristics at least include water quality dimensions, biochemical quality dimensions, and microbial quality dimensions, the water quality dimensions include a suspended solid rate, a total nitrogen rate, a total phosphorus rate, and a pH value, the biochemical quality dimensions include a sludge settling ratio and a sludge concentration, and the microbial quality dimensions include a microbial species, a microbial quantity, and biological activity.

[0034] In the embodiments of the present application, predetermined quality characteristics are first read. The predetermined quality characteristics are various indicators defined in advance for evaluating wastewater treatment quality, including water quality dimensions, biochemical quality dimensions, and microbial quality dimensions. Specifically, the water quality dimensions include a suspended solid rate, a total nitrogen rate, a total phosphorus rate, and a pH value. The suspended solid rate refers to the content of solid particles in water; the total nitrogen rate and the total phosphorus rate represent the contents of total nitrogen and total phosphorus in water, respectively, which are important indicators reflecting water quality; and the pH value is the acidity or alkalinity of water, which affects the survival and activity of microorganisms. The biochemical quality dimensions include a sludge settling ratio and a sludge concentration. The sludge settling ratio refers to the settling rate of sludge within a certain time; and the sludge concentration is the content of sludge in water. The microbial quality dimensions include a microbial species, a microbial quantity, and biological activity. The microbial species and the microbial quantity reflect the diversity and abundance of microorganisms participating in the degradation of organic matter in the wastewater treatment process; and the biological activity refers to the metabolic activity of microorganisms, which directly affects the efficiency of wastewater treatment.

[0035] Based on the predetermined quality characteristics, traverse extraction is performed on the first historical treatment quality information to obtain first historical quality characteristic parameters. Traverse extraction refers to sequentially reading the treatment quality information in each historical record and extracting data related to the predetermined quality characteristics. For example, parameters such as the suspended solid rate, the total nitrogen rate, the total phosphorus rate, the pH value, the sludge settling ratio, the sludge concentration, the microbial species, the microbial quantity, and the biological activity are extracted from the historical records as the first historical quality characteristic parameters. Then, the first historical quality characteristic parameters are processed and analyzed by using a coefficient of variation principle to obtain the first historical treatment quality index. The coefficient of variation refers to the ratio of the standard deviation to the mean, which is used to measure the dispersion degree of data. Specifically, the mean and the standard deviation of each quality characteristic parameter are first calculated, and then the coefficient of variation formula is used for calculation. For example, for the suspended solid rate, the mean and the standard deviation are calculated, and then the coefficient of variation is obtained. After calculating the coefficients of variation of all quality characteristic parameters, a weighted average is performed according to the importance of each characteristic to finally obtain a comprehensive treatment quality index, i.e., the first historical treatment quality index.

[0036] A predetermined aeration index reading module 13 reads the predetermined aeration index and analyzes the predetermined aeration index to obtain a target aeration control space.

[0037] Further, in the system provided by the application, the predetermined aeration index includes air pressure, air flow, aeration duration and bubble size.

[0038] In the application, the predetermined aeration index reading module first reads the predetermined aeration index, which refers to the key parameters that need to be monitored and adjusted in the wastewater treatment process, including air pressure, air flow, aeration duration and bubble size.

[0039] Next, the predetermined aeration index is analyzed to obtain a target aeration control space. Specifically, a large number of historical wastewater treatment records are collected from the database, including all the data of the predetermined aeration index in the past treatment process. Historical data collection refers to extracting the data of air pressure, air flow, aeration duration and bubble size recorded in the past treatment process for analysis. Next, through data mining technology, these historical data are analyzed to identify the influence of different combinations of air pressure, air flow, aeration duration and bubble size on the wastewater treatment effect. Through the use of regression analysis technology, the relationship between different parameter combinations and the treatment effect is found. For example, through analysis, it is found that a certain range of air pressure and air flow combination has the best treatment effect under the condition of a certain aeration duration and bubble size. Based on the data analysis results, the target aeration control space is constructed. The target aeration control space refers to the range of aeration control parameters that can be used in the actual wastewater treatment process by analyzing the predetermined aeration index.

[0040] An optimization module 14 introduces a predetermined control fitness function as an optimization evaluation strategy and uses the target required dissolved oxygen concentration as an optimization constraint to perform global optimization in the target aeration control space to obtain an optimal aeration control scheme.

[0041] In the application, the optimization module introduces a predetermined control fitness function as an optimization evaluation strategy, and then uses the target required dissolved oxygen concentration as an optimization constraint. The target required dissolved oxygen concentration refers to the minimum dissolved oxygen concentration required for biological treatment of the target wastewater.

[0042] After the control fitness function and the optimization constraint are determined, global optimization is performed in the target aeration control space to find the optimal aeration control scheme by using some optimization algorithms, such as particle swarm optimization or genetic algorithm.

[0043] Further, the optimization module 14 in the system provided by the application is also used for:

[0044] Step a: the first aeration control scheme extracted from the target aeration control space is traversed in the aeration database to obtain a first control log of a first most similar aeration control scheme; step b: whether the first dissolved oxygen concentration in the first control log meets the optimization constraint is judged; step c: if yes, the optimization evaluation strategy is called to analyze and evaluate the first control log to obtain a first control fitness; step d: a second control fitness is obtained, which is the control fitness of a second aeration control scheme extracted from the target aeration control space; step e: the optimal aeration control scheme is obtained according to a comparison result of comparing the first control fitness with the second control fitness; and step f: steps a to e are repeated until a predetermined number of repeated iterations is reached, and the optimal aeration control scheme at this time is output.

[0045] In the embodiments of the present application, first, the optimization module starts step a, the first aeration control scheme extracted from the target aeration control space is searched in the aeration database, through the search, the database query technology is used to find the most similar scheme to the first aeration control scheme, and the first control log thereof is recorded. The control log contains the dissolved oxygen concentration and aeration amount and other data monitored by the dissolved oxygen sensor during the actual operation of the scheme. In step b, whether the first dissolved oxygen concentration in the first control log meets the optimization constraint is judged. The dissolved oxygen concentration refers to the content of oxygen in water, and the optimization constraint is the minimum dissolved oxygen concentration requirement, which is used to ensure that the aerobic microorganisms in wastewater can normally carry out metabolic activities. If the first dissolved oxygen concentration meets the optimization constraint, it means that the scheme meets the minimum requirement of the dissolved oxygen concentration in the actual operation. In step c, if the first dissolved oxygen concentration meets the requirement, the optimization evaluation strategy is called to analyze and evaluate the first control log to obtain the first control fitness. The optimization evaluation strategy is an evaluation method based on a predetermined control fitness function. Through the calculation of the fitness function, the control fitness is obtained by comprehensively considering the dissolved oxygen concentration, energy consumption and treatment effect and other indicators.

[0046] Then in step d, the second most similar aeration control scheme is obtained by the same method as described above, the optimization evaluation strategy is called to analyze and evaluate the second control log to obtain the second control fitness. In step e, the first control fitness and the second control fitness are compared, and by comparing the two fitness values, it is judged which scheme is better.

[0047] In step f, steps a to e are repeated for multiple iterations. In each iteration, a new control scheme is extracted from the target aeration control space, and traversal, judgment, evaluation and comparison are performed. An iterative algorithm such as genetic algorithm or particle swarm optimization is used to update and optimize the scheme in the iteration process. This process continues until a predetermined number of repeated iterations is reached,

[0048] Finally, when the predetermined number of iterations is reached, the optimal aeration control scheme at that time will be output.

[0049] Furthermore, in the system provided in the application embodiment, the expression of the predetermined control fitness function is as follows:

[0050] ;

[0051] in, This refers to the aeration control scheme. Controlling fitness, This refers to the aeration control scheme. Aeration volume, This refers to the energy consumption coefficient per unit of aeration. This refers to the aeration control scheme. Dissolved oxygen concentration, This refers to the target required dissolved oxygen concentration. and These refer to the first fitness coefficient and the second fitness coefficient, respectively. .

[0052] In this embodiment of the application, when calculating the control fitness, the calculation is performed using the aforementioned predetermined control fitness function, wherein the unit aeration energy consumption coefficient represents the energy consumed per unit air flow rate, which is preset by technical experts. The first fitness coefficient and the second fitness coefficient are also preset by technical experts according to the performance requirements of the specific wastewater treatment system.

[0053] The control fitness is calculated using a predetermined control fitness function.

[0054] The aeration treatment module 15 is used to control the target blower to aerate the target wastewater according to the optimal aeration control scheme.

[0055] In this embodiment, the parameters of the optimal aeration control scheme are input into the control system of the target blower. The target blower is a device used to deliver air into the wastewater, and its operating parameters include air pressure, air flow rate, aeration time, and bubble size. Based on the optimal aeration control scheme, the operating parameters of the blower are adjusted to perform energy-saving aeration treatment of the target wastewater using the target blower.

[0056] Furthermore, the aeration treatment module 15 in the system provided in the application embodiment is also used for:

[0057] extracting an optimal bubble size in the optimal aeration control scheme, and determining a predetermined bubble threshold based on the optimal bubble size; obtaining any aeration control scheme in the aeration database, the any aeration control scheme comprising any aerator control scheme; issuing an optimal pickup instruction when any bubble size in the any aerator control scheme meets the predetermined bubble threshold; reading a predetermined bubble control index based on the optimal pickup instruction, and performing traversal matching in the any aerator control scheme based on the predetermined bubble control index to obtain any bubble control parameter; taking the any bubble control parameter as an optimal aerator control scheme, and performing energy-saving aeration treatment on the target aerator of the target wastewater according to the optimal aerator control scheme.

[0058] Further, the system provided by the application embodiment, the predetermined bubble control index comprises the installation depth and the aperture of the target aerator.

[0059] In the application embodiment, first, the optimal bubble size in the optimal aeration control scheme is read, and then the predetermined bubble threshold is determined according to the preset rule based on the optimal bubble size, for example, 1±5% of the optimal bubble size is set as the predetermined bubble threshold.

[0060] Then, any aeration control scheme is obtained from the aeration database through database query technology. The aeration database saves historical aeration records and control parameters under different operating conditions, including air pressure, air flow, aeration time and bubble size. Then, it is detected whether any bubble size in the any aeration control scheme meets the predetermined bubble threshold. If it is detected that the any bubble size is within the threshold range, an optimal pickup instruction is issued.

[0061] Next, based on the optimal pickup instruction, the predetermined bubble control index is read, including the installation depth and the aperture of the target aerator. Through database query technology, the control parameters meeting the predetermined bubble control index are extracted from the any aeration control scheme. Then, traversal matching is performed in the any aerator control scheme to obtain any bubble control parameter. The traversal matching is performed through a heuristic search algorithm to ensure that the selected parameter combination can generate a bubble size meeting the predetermined bubble threshold. These parameters include air pressure, air flow, aeration time, etc.

[0062] Then, these any bubble control parameters are taken as the optimal aerator control scheme, and the target aerator of the target wastewater is subjected to energy-saving aeration treatment according to the optimal aerator control scheme.

[0063] In the aeration process, factors such as air flow rate, water flow rate and additives are monitored in real time by sensors. Air flow rate refers to the speed of air entering the wastewater, water flow rate refers to the flow speed of wastewater in the treatment tank, and additives refer to chemicals added to wastewater that can change the surface tension of water and affect bubble formation. Sensors collect these data in real time and transmit them to the control system through wireless transmission technology. Based on the data collected by the sensors, a feedback control algorithm is used for dynamic adjustment. Feedback control algorithm is an automatic adjustment method that adjusts control parameters in real time based on the deviation between actual measured value and set value to achieve the desired effect. The specific implementation includes using fuzzy control algorithm to automatically reduce air flow when the sensor detects that the air flow rate is too high; adjust the angle of the aerator or increase the air pressure when the water flow rate is too low; and automatically add an appropriate amount of chemicals when the additive concentration is insufficient. Through this process, the bubble size is always within the predetermined threshold range, ensuring optimal oxygen transfer efficiency and treatment effect while reducing energy consumption.

[0064] In the embodiments of the present application, as described above, the embodiments of the present application have at least the following technical effects:

[0065] The present application reads the predetermined wastewater index and collects features of the target wastewater based on the predetermined wastewater index to obtain target wastewater feature information; the target wastewater feature information is used as input information of a dissolved oxygen demand prediction model to obtain a target required dissolved oxygen concentration, wherein the target required dissolved oxygen concentration refers to the minimum dissolved oxygen concentration for biological treatment of the target wastewater; the predetermined aeration index is read and analyzed to obtain a target aeration control space; a predetermined control fitness function is introduced as an optimization evaluation strategy, and the target required dissolved oxygen concentration is used as an optimization constraint to perform global optimization in the target aeration control space to obtain an optimal aeration control scheme; and the target blower for the target wastewater is subjected to energy-saving aeration treatment according to the optimal aeration control scheme. The present application solves the technical problems of low treatment efficiency and high energy consumption in the prior art for biological treatment of wastewater, calculates the dissolved oxygen demand by obtaining wastewater and aeration indexes, optimizes aeration parameters by using a global optimization algorithm, and controls the blower to perform energy-saving aeration treatment, thereby achieving the technical effects of efficient wastewater treatment and significant energy saving.

[0066] In the embodiments of the present application, as described above, the embodiments of the present application have at least the following technical effects: Figure 2 As shown in the foregoing embodiments, the embodiments of the present application provide a blower optimization control method for wastewater treatment, which comprises:

[0067] reading a predetermined wastewater index, and collecting features of target wastewater based on the predetermined wastewater index to obtain target wastewater feature information; taking the target wastewater feature information as input information of a dissolved oxygen demand prediction model to obtain a target required dissolved oxygen concentration, wherein the target required dissolved oxygen concentration refers to a minimum dissolved oxygen concentration for biological treatment of the target wastewater; reading a predetermined aeration index, and analyzing the predetermined aeration index to obtain a target aeration control space; introducing a predetermined control fitness function as an optimization evaluation strategy, and taking the target required dissolved oxygen concentration as an optimization constraint to perform global optimization in the target aeration control space to obtain an optimal aeration control scheme; and controlling a target blower to perform aeration treatment on the target wastewater according to the optimal aeration control scheme.

[0068] Further, the method further comprises:

[0069] The predetermined wastewater index includes sludge concentration, water flow rate, water temperature, influent flow rate, and organic matter concentration.

[0070] Further, the method further comprises:

[0071] arbitrarily obtaining a first historical record in a historical wastewater biological treatment record; performing normalized weighted analysis on first historical treatment quality information in the extracted first historical record to obtain a first historical treatment quality index; if the first historical treatment quality index reaches a predetermined quality index threshold, issuing a data assembly instruction; extracting first historical wastewater feature information and a first historical dissolved oxygen concentration in the first historical record based on the data assembly instruction, and assembling first training data; performing supervised learning on the first training data based on a neural network principle and verifying to obtain the dissolved oxygen demand prediction model.

[0072] Further, the method further comprises:

[0073] reading a predetermined quality feature, and performing traversal extraction on first historical treatment quality information based on the predetermined quality feature to obtain first historical quality feature parameters; processing and analyzing the first historical quality feature parameters using a coefficient of variation principle to obtain the first historical treatment quality index; wherein the predetermined quality feature at least includes a water quality dimension, a biochemical quality dimension, and a microbial quality dimension, the water quality dimension includes a suspended solid rate, a total nitrogen rate, a total phosphorus rate, and a pH value, the biochemical quality dimension includes a sludge settling ratio and a sludge concentration, and the microbial quality dimension includes a microbial species, a microbial quantity, and a biological activity.

[0074] Further, the method further comprises:

[0075] The predetermined aeration index includes air pressure, air flow rate, aeration duration, and bubble size.

[0076] Further, the method further comprises:

[0077] Step a: traversing the first aeration control scheme extracted from the target aeration control space in the aeration database to obtain a first control log of the first most similar aeration control scheme; step b: judging whether the first dissolved oxygen concentration in the first control log meets the optimization constraint; step c: if yes, calling the optimization evaluation strategy to analyze and evaluate the first control log to obtain a first control fitness; step d: obtaining a second control fitness, which refers to the control fitness of the second aeration control scheme extracted from the target aeration control space; step e: obtaining the optimal aeration control scheme according to the comparison result of the comparison between the first control fitness and the second control fitness; step f: repeating steps a to e until a predetermined number of repeated iterations is reached, and outputting the optimal aeration control scheme at that time.

[0078] Further, the expression of the predetermined control fitness function is as follows:

[0079] ;

[0080] wherein, refers to the control fitness of the aeration control scheme , refers to the aeration amount of the aeration control scheme , refers to the unit aeration energy consumption coefficient, refers to the dissolved oxygen concentration of the aeration control scheme , refers to the target required dissolved oxygen concentration, and respectively refer to a first fitness coefficient and a second fitness coefficient, and .

[0081] Further, the method further comprises:

[0082] extracting an optimal bubble size in the optimal aeration control scheme, and determining a predetermined bubble threshold based on the optimal bubble size; obtaining any aeration control scheme in the aeration database, the any aeration control scheme including any aerator control scheme; issuing an optimal pickup instruction when any bubble size in the any aerator control scheme meets the predetermined bubble threshold; reading a predetermined bubble control index based on the optimal pickup instruction, and performing traversal matching in the any aerator control scheme based on the predetermined bubble control index to obtain any bubble control parameter; taking the any bubble control parameter as an optimal aerator control scheme, and performing energy-saving aeration treatment on the target aerator of the target wastewater according to the optimal aerator control scheme.

[0083] Further, the method further comprises:

[0084] The predetermined bubble control index includes the installation depth and the aperture of the target aerator.

[0085] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. The above describes a specific embodiment of the present application. The processes depicted in the drawings do not necessarily require the specific order and continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are possible or can be advantageous.

[0086] The above only describes the preferred embodiments of the present application and does not limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

[0087] The specification and drawings are merely exemplary of the present application, and any and all modifications, variations, combinations or equivalents that fall within the scope of the present application are considered to be covered by the present application. Obviously, those skilled in the art can make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalents, the present application is intended to include these modifications and variations.

Claims

1. An optimized control system for a blower used in wastewater treatment, characterized in that, include: The feature collection module is used to read predetermined wastewater indicators and collect features of the target wastewater based on the predetermined wastewater indicators to obtain target wastewater feature information. A dissolved oxygen demand prediction module is used to take the target wastewater characteristic information as input information of the dissolved oxygen demand prediction model to obtain the target required dissolved oxygen concentration, wherein the target required dissolved oxygen concentration refers to the minimum dissolved oxygen concentration for biological treatment of the target wastewater. A predetermined aeration index reading module is used to read predetermined aeration indexes and analyze the predetermined aeration indexes to obtain the target aeration control space. The optimization module is used to introduce a predetermined control fitness function as an optimization evaluation strategy and use the target required dissolved oxygen concentration as an optimization constraint to perform global optimization in the target aeration control space to obtain the optimal aeration control scheme. An aeration treatment module is used to control a target blower to aerate the target wastewater according to the optimal aeration control scheme. The optimization module is also used for: Step a: Traverse the first aeration control scheme extracted from the target aeration control space in the aeration database to obtain the first control log of the first most similar aeration control scheme; Step b: Determine whether the first dissolved oxygen concentration in the first control log meets the optimization constraint; Step c: If the conditions are met, retrieve the optimization evaluation strategy to analyze and evaluate the first control log to obtain the first control fitness. Step d: Obtain the second control fitness, which refers to the control fitness of the second aeration control scheme extracted from the target aeration control space; Step e: Based on the comparison results between the first control fitness and the second control fitness, the optimal aeration control scheme is obtained; Step f: Repeat steps a to e until the predetermined number of iterations is reached, and output the optimal aeration control scheme at that time; The expression for the predetermined control fitness function is as follows: ； in, This refers to the aeration control scheme. Controlling fitness, This refers to the aeration control scheme. Aeration volume, This refers to the energy consumption coefficient per unit of aeration. This refers to the aeration control scheme. Dissolved oxygen concentration, This refers to the target required dissolved oxygen concentration. and These refer to the first fitness coefficient and the second fitness coefficient, respectively. .

2. The blower optimization control system for wastewater treatment according to claim 1, characterized in that, The predetermined wastewater parameters include sludge concentration, water flow velocity, water temperature, influent flow rate, and organic matter concentration.

3. The blower optimization control system for wastewater treatment according to claim 1, characterized in that, The dissolved oxygen demand prediction module is also used for: Arbitrarily retrieve the first historical record from historical wastewater biological treatment records; The first historical processing quality information extracted from the first historical record is subjected to normalized weighted analysis to obtain the first historical processing quality index. If the first historical processing quality index reaches the predetermined quality index threshold, a data assembly instruction is issued. Based on the data assembly instructions, extract the first historical wastewater feature information and the first historical dissolved oxygen concentration from the first historical record, and assemble them into the first training data; The dissolved oxygen demand prediction model is obtained by performing supervised learning and testing on the first training data based on neural network principles.

4. The blower optimization control system for wastewater treatment according to claim 3, characterized in that, The dissolved oxygen demand prediction module is also used for: Read the predetermined quality features, and extract the first historical processing quality information based on the predetermined quality features to obtain the first historical quality feature parameters; The first historical quality characteristic parameter is processed and analyzed using the principle of coefficient of variation to obtain the first historical processing quality index. The predetermined quality characteristics include at least water quality dimensions, biochemical quality dimensions, and microbiological quality dimensions. The water quality dimensions include suspended solids ratio, total nitrogen ratio, total phosphorus ratio, and pH value. The biochemical quality dimensions include sludge settling ratio and sludge concentration. The microbiological quality dimensions include microbial species, microbial quantity, and biological activity.

5. The blower optimization control system for wastewater treatment according to claim 1, characterized in that, The predetermined aeration parameters include air pressure, air flow rate, aeration duration, and bubble size.

6. The blower optimization control system for wastewater treatment according to claim 1, characterized in that, The aeration treatment module is also used for: Extract the optimal bubble size from the optimal aeration control scheme, and determine a predetermined bubble threshold based on the optimal bubble size; Obtain any aeration control scheme from the aeration database, wherein the arbitrary aeration control scheme includes any aerator control scheme; When the size of any bubble in the arbitrary aerator control scheme meets the predetermined bubble threshold, an optimal pickup command is issued. Based on the optimal picking instruction, the predetermined bubble control index is read, and based on the predetermined bubble control index, the arbitrary aerator control scheme is traversed and matched to obtain the arbitrary bubble control parameters. The arbitrary bubble control parameters are used as the optimal aerator control scheme, and the target aerator for the target wastewater is subjected to energy-saving aeration treatment according to the optimal aerator control scheme.

7. The blower optimization control system for wastewater treatment according to claim 6, characterized in that, The predetermined bubble control parameters include the installation depth and orifice diameter of the target aerator.

8. A method for optimizing the control of a blower used in wastewater treatment, characterized in that, The blower optimization control method for wastewater treatment is implemented by the blower optimization control system for wastewater treatment as described in any one of claims 1 to 7, wherein the blower optimization control method for wastewater treatment includes: Read the predetermined wastewater index, and collect the characteristics of the target wastewater based on the predetermined wastewater index to obtain the target wastewater characteristic information; The target wastewater characteristic information is used as input information for the dissolved oxygen demand prediction model to obtain the target required dissolved oxygen concentration, wherein the target required dissolved oxygen concentration refers to the minimum dissolved oxygen concentration for biological treatment of the target wastewater. Read the predetermined aeration index and analyze the predetermined aeration index to obtain the target aeration control space; A predetermined control fitness function is introduced as an optimization evaluation strategy, and the target required dissolved oxygen concentration is used as an optimization constraint. Global optimization is performed in the target aeration control space to obtain the optimal aeration control scheme. The target blower is controlled to aerate the target wastewater according to the optimal aeration control scheme.

Images