CN117682682A - Optimized control system and method for sewage treatment aeration process - Google Patents
Optimized control system and method for sewage treatment aeration process Download PDFInfo
- Publication number
- CN117682682A CN117682682A CN202410135241.0A CN202410135241A CN117682682A CN 117682682 A CN117682682 A CN 117682682A CN 202410135241 A CN202410135241 A CN 202410135241A CN 117682682 A CN117682682 A CN 117682682A
- Authority
- CN
- China
- Prior art keywords
- dissolved oxygen
- time sequence
- oxygen concentration
- valve opening
- adaptive
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000005273 aeration Methods 0.000 title claims abstract description 144
- 238000000034 method Methods 0.000 title claims abstract description 100
- 239000010865 sewage Substances 0.000 title claims abstract description 96
- 238000011282 treatment Methods 0.000 title claims abstract description 93
- 230000008569 process Effects 0.000 title claims abstract description 78
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims abstract description 295
- 229910052760 oxygen Inorganic materials 0.000 claims abstract description 295
- 239000001301 oxygen Substances 0.000 claims abstract description 295
- 230000001105 regulatory effect Effects 0.000 claims abstract description 72
- 230000001276 controlling effect Effects 0.000 claims abstract description 18
- 238000004891 communication Methods 0.000 claims abstract description 5
- 238000012549 training Methods 0.000 claims description 90
- 238000010586 diagram Methods 0.000 claims description 65
- 230000003044 adaptive effect Effects 0.000 claims description 43
- 239000011159 matrix material Substances 0.000 claims description 43
- 238000005728 strengthening Methods 0.000 claims description 30
- 238000003062 neural network model Methods 0.000 claims description 21
- 230000002787 reinforcement Effects 0.000 claims description 16
- 238000005457 optimization Methods 0.000 claims description 15
- 239000003623 enhancer Substances 0.000 claims description 14
- 230000003247 decreasing effect Effects 0.000 claims description 13
- 238000010219 correlation analysis Methods 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 6
- 238000004065 wastewater treatment Methods 0.000 claims description 6
- 238000013527 convolutional neural network Methods 0.000 claims description 3
- 238000011176 pooling Methods 0.000 claims description 3
- 238000005265 energy consumption Methods 0.000 abstract description 11
- 238000003912 environmental pollution Methods 0.000 abstract description 9
- 230000008859 change Effects 0.000 description 16
- 230000000694 effects Effects 0.000 description 16
- 244000005700 microbiome Species 0.000 description 11
- 238000012544 monitoring process Methods 0.000 description 9
- 239000000126 substance Substances 0.000 description 7
- 230000007613 environmental effect Effects 0.000 description 5
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 5
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 4
- 230000015556 catabolic process Effects 0.000 description 4
- 238000006731 degradation reaction Methods 0.000 description 4
- 230000000813 microbial effect Effects 0.000 description 4
- 239000003344 environmental pollutant Substances 0.000 description 3
- 231100000719 pollutant Toxicity 0.000 description 3
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000011217 control strategy Methods 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 230000002503 metabolic effect Effects 0.000 description 2
- 229910052757 nitrogen Inorganic materials 0.000 description 2
- 229910052698 phosphorus Inorganic materials 0.000 description 2
- 239000011574 phosphorus Substances 0.000 description 2
- 238000004886 process control Methods 0.000 description 2
- 238000004064 recycling Methods 0.000 description 2
- 239000010802 sludge Substances 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000015271 coagulation Effects 0.000 description 1
- 238000005345 coagulation Methods 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 230000007274 generation of a signal involved in cell-cell signaling Effects 0.000 description 1
- 238000011221 initial treatment Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 239000005416 organic matter Substances 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 238000004062 sedimentation Methods 0.000 description 1
- 238000004659 sterilization and disinfection Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02W—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO WASTEWATER TREATMENT OR WASTE MANAGEMENT
- Y02W10/00—Technologies for wastewater treatment
- Y02W10/10—Biological treatment of water, waste water, or sewage
Abstract
The application discloses an optimized control system and method for sewage treatment aeration process, which receives and processes incoming sewage through an aeration tank; detecting the dissolved oxygen concentration of the aeration tank by a dissolved oxygen sensor; controlling the air flow entering the aeration tank by adjusting the opening value of the valve; providing compressed air to the regulating valve by a blower; and a controller is connected with the dissolved oxygen sensor, the regulating valve and the blower in a communication way, and a control signal for controlling the valve opening value of the regulating valve is generated by the controller according to the dissolved oxygen concentration of the aeration tank. By the mode, the optimal control of the aeration process can be realized, the sewage treatment efficiency is improved, the energy consumption is saved, and the environmental pollution is reduced.
Description
Technical Field
The application relates to the technical field of intelligent sewage treatment, in particular to an optimal control system and method for a sewage treatment aeration process.
Background
The sewage treatment is an important environmental protection engineering, and aims to remove or reduce harmful substances in sewage so as to enable the harmful substances to reach emission standards or recycling requirements. In the sewage treatment process, aeration is a common biological treatment method, and the principle is that microorganisms are utilized to decompose organic matters in sewage into harmless inorganic matters, and simultaneously pollutants such as nitrogen, phosphorus and the like in the sewage are removed. During aeration, the concentration of dissolved oxygen is an important parameter affecting microbial activity and sewage treatment, and therefore, effective monitoring and control thereof is required to provide suitable environmental conditions for microbial growth.
However, conventional aeration process control systems typically employ fixed air flow rates or time-switched blowers, or alternatively, adjust the air flow rate in the aeration tank based on fixed time schedules or empirical rules. The method can not be dynamically adjusted according to the real-time change of the concentration of the dissolved oxygen, and is often not suitable for the change of the concentration of the dissolved oxygen under different conditions, so that the problems of high energy consumption, low efficiency, large pollution and the like in the aeration process are caused.
Accordingly, an optimal control system for a sewage treatment aeration process is desired.
Disclosure of Invention
The application provides an optimized control system and method for sewage treatment aeration process, which are used for receiving and treating incoming sewage through an aeration tank; detecting the dissolved oxygen concentration of the aeration tank by a dissolved oxygen sensor; controlling the air flow entering the aeration tank by adjusting the opening value of the valve; providing compressed air to the regulating valve by a blower; and a controller is connected with the dissolved oxygen sensor, the regulating valve and the blower in a communication way, and a control signal for controlling the valve opening value of the regulating valve is generated by the controller according to the dissolved oxygen concentration of the aeration tank. By the mode, the optimal control of the aeration process can be realized, the sewage treatment efficiency is improved, the energy consumption is saved, and the environmental pollution is reduced.
The application also provides an optimization control system of sewage treatment aeration process, which comprises: an aeration tank for receiving and treating incoming sewage; a dissolved oxygen sensor for detecting a dissolved oxygen concentration of the aeration tank; the adjusting valve is used for adjusting the opening value of the valve to control the air flow entering the aeration tank; a blower for supplying compressed air to the regulating valve; the controller can be in communication connection with the dissolved oxygen sensor, the regulating valve and the blower, and is used for generating a control signal for controlling the valve opening value of the regulating valve according to the dissolved oxygen concentration of the aeration tank.
In the above-mentioned optimizing control system of sewage treatment aeration process, the controller includes: the data acquisition module is used for acquiring a time sequence of the dissolved oxygen concentration of the aeration tank and a time sequence of the valve opening value of the regulating valve; the data multi-parameter time sequence association coding module is used for performing time sequence association coding on the time sequence of the dissolved oxygen concentration and the time sequence of the valve opening value to obtain a valve opening-dissolved oxygen concentration time sequence association matrix; the valve opening-dissolved oxygen concentration time sequence correlation feature extraction module is used for extracting features of the valve opening-dissolved oxygen concentration time sequence correlation matrix through a valve opening-dissolved oxygen concentration time sequence correlation feature extractor based on a deep neural network model so as to obtain a valve opening-dissolved oxygen concentration time sequence correlation feature map; the self-adaptive strengthening module is used for enabling the valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram to pass through a self-adaptive strengthening device based on a self-adaptive attention layer to obtain a self-adaptive strengthening valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram as a self-adaptive strengthening valve opening-dissolved oxygen concentration time sequence correlation characteristic; and the valve opening value control module is used for determining that the valve opening value at the current time point should be increased, decreased or maintained based on the self-adaptive reinforced valve opening-dissolved oxygen concentration time sequence correlation characteristic.
In the above-mentioned optimizing control system of sewage treatment aeration process, the data multiparameter time sequence associated coding module includes: the data multi-parameter time sequence arrangement unit is used for respectively arranging the time sequence of the dissolved oxygen concentration and the time sequence of the valve opening value into a dissolved oxygen concentration time sequence input vector and a regulating valve opening time sequence input vector according to a time dimension; the valve opening-dissolved oxygen concentration time sequence correlation analysis module is used for calculating a sample covariance correlation matrix of the dissolved oxygen concentration time sequence input vector relative to the regulating valve opening time sequence input vector so as to obtain the valve opening-dissolved oxygen concentration time sequence correlation matrix.
In the above-mentioned optimizing control system of sewage treatment aeration process, the valve opening-dissolved oxygen concentration time sequence correlation analysis module is used for: calculating a sample covariance correlation matrix of the dissolved oxygen concentration time sequence input vector relative to the regulating valve opening time sequence input vector by using the following covariance formula to obtain a valve opening-dissolved oxygen concentration time sequence correlation matrix; wherein, the covariance formula is:the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>Is the time sequence input vector of the dissolved oxygen concentration, < > >Is the transpose of the time sequence input vector of the dissolved oxygen concentration,>is the valve opening time sequence input vector of the regulating valve, < >>Is the transposed vector of the time sequence input vector of the opening degree of the regulating valve>Is the valve opening-dissolved oxygen concentration time sequence correlation matrix.
In the optimized control system for the sewage treatment aeration process, the deep neural network model is a convolutional neural network model.
In the above-mentioned optimizing control system of sewage treatment aeration process, the self-adaptive strengthening module is used for: processing the valve opening-dissolved oxygen concentration time sequence correlation characteristic map through an adaptive enhancer based on an adaptive attention layer according to the following adaptive enhancement formula to obtain the adaptive enhancement valve opening-dissolved oxygen concentration time sequence correlation characteristic map; wherein, the self-adaptive strengthening formula is:
；
；
；
；
wherein,is the valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram,>representing global mean pooling of individual feature matrices along the channel dimension in the feature map,/->Is the channel characteristic vector of the valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram, +.>And->Is the weight and bias of the convolutional layer, +. >To activate the function +.>Is a convolution eigenvector of said channel eigenvector, ">Is saidCharacteristic values of various positions in the convolution characteristic vector, +.>Is a weight vector, +.>Is multiplied by the position point +.>Is the self-adaptive reinforced valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram.
In the above-mentioned optimizing control system of sewage treatment aeration process, the valve opening value control module is used for: and passing the self-adaptive intensified valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram through a classifier to obtain a classification result, wherein the classification result is used for indicating that the valve opening value at the current time point should be increased, decreased or maintained.
The optimized control system for the sewage treatment aeration process further comprises a training module for training the valve opening-dissolved oxygen concentration time sequence correlation characteristic extractor based on the deep neural network model, the adaptive enhancer based on the adaptive attention layer and the classifier.
In the above-mentioned optimizing control system of sewage treatment aeration process, the training module includes: the training data acquisition unit is used for acquiring a time sequence of training the concentration of dissolved oxygen in the aeration tank and a time sequence of training the opening value of the valve of the regulating valve; the training data multi-parameter time sequence associated coding unit is used for performing time sequence associated coding on the time sequence of the training dissolved oxygen concentration and the time sequence of the training valve opening value to obtain a training valve opening-dissolved oxygen concentration time sequence associated matrix; a training valve opening-dissolved oxygen concentration time sequence correlation feature extraction unit, which is used for extracting features of the training valve opening-dissolved oxygen concentration time sequence correlation matrix through a valve opening-dissolved oxygen concentration time sequence correlation feature extractor based on the deep neural network model so as to obtain a training valve opening-dissolved oxygen concentration time sequence correlation feature map; the training self-adaptive strengthening unit is used for enabling the training valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram to pass through the self-adaptive strengthening device based on the self-adaptive attention layer so as to obtain the training self-adaptive strengthening valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram; the training optimization unit is used for optimizing the training self-adaptive reinforcement valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram to obtain an optimized training self-adaptive reinforcement valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram; the training classification unit is used for enabling the optimized training self-adaptive reinforcement valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram to pass through the classifier so as to obtain a classification loss function value; and the training unit is used for training the valve opening-dissolved oxygen concentration time sequence correlation characteristic extractor based on the deep neural network model, the adaptive enhancer based on the adaptive attention layer and the classifier based on the classification loss function value.
The application also provides an optimization control method of the sewage treatment aeration process, which comprises the following steps: receiving and treating the entered sewage through an aeration tank; detecting the dissolved oxygen concentration of the aeration tank by a dissolved oxygen sensor; controlling the air flow entering the aeration tank by adjusting the opening value of the valve; providing compressed air to the regulating valve by a blower; a controller is communicably connected with the dissolved oxygen sensor, the regulating valve and the blower, and a control signal for controlling the valve opening value of the regulating valve is generated by the controller according to the dissolved oxygen concentration of the aeration tank; wherein, through the controller according to the dissolved oxygen concentration of aeration tank generates the control signal of the valve aperture value of control valve, include: acquiring a time sequence of the dissolved oxygen concentration of the aeration tank and a time sequence of a valve opening value of the regulating valve; performing time sequence association coding on the time sequence of the dissolved oxygen concentration and the time sequence of the valve opening value to obtain a valve opening-dissolved oxygen concentration time sequence association matrix; performing feature extraction on the valve opening-dissolved oxygen concentration time sequence correlation matrix by a valve opening-dissolved oxygen concentration time sequence correlation feature extractor based on a deep neural network model to obtain a valve opening-dissolved oxygen concentration time sequence correlation feature map; the valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram is used for obtaining an adaptive reinforced valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram as an adaptive reinforced valve opening-dissolved oxygen concentration time sequence correlation characteristic through an adaptive enhancer based on an adaptive attention layer; based on the self-adaptive reinforced valve opening-dissolved oxygen concentration time sequence correlation characteristic, the valve opening value at the current time point is determined to be increased, decreased or maintained.
Compared with the prior art, the sewage treatment aeration process optimization control system and method can realize the optimization control of the aeration process, improve the sewage treatment efficiency, save the energy consumption and reduce the environmental pollution.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
In the drawings: fig. 1 is a block diagram of an optimized control system for a sewage treatment aeration process provided in an embodiment of the present application.
Fig. 2 is a flowchart of an optimized control method for a sewage treatment aeration process according to an embodiment of the present application.
Fig. 3 is a schematic diagram of a system architecture of an optimized control method for a sewage treatment aeration process according to an embodiment of the present application.
Fig. 4 is an application scenario diagram of an optimizing control system for a sewage treatment aeration process provided in an embodiment of the present application.
Detailed Description
For the purposes of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the embodiments of the present application will be described in further detail with reference to the accompanying drawings. The illustrative embodiments of the present application and their description are presented herein to illustrate the application and not to limit the application.
Unless defined otherwise, all technical and scientific terms used in the examples of this application have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the present application is for the purpose of describing particular embodiments only and is not intended to limit the scope of the present application.
In the description of the embodiments of the present application, unless otherwise indicated and defined, the term "connected" should be construed broadly, and for example, may be an electrical connection, may be a communication between two elements, may be a direct connection, or may be an indirect connection via an intermediary, and it will be understood by those skilled in the art that the specific meaning of the term may be understood according to the specific circumstances.
It should be noted that, the term "first\second\third" in the embodiments of the present application is merely to distinguish similar objects, and does not represent a specific order for the objects, it is to be understood that "first\second\third" may interchange a specific order or sequence where allowed. It is to be understood that the "first\second\third" distinguishing objects may be interchanged where appropriate such that the embodiments of the present application described herein may be implemented in sequences other than those illustrated or described herein.
The sewage treatment is a vital environmental protection engineering, and aims to remove or reduce harmful substances in sewage so as to enable the harmful substances to reach emission standards or recycling requirements, and the process is vital for maintaining ecological balance and protecting human health. Sewage treatment generally includes physical, chemical and biological treatment processes, and aeration is a common technique in biological treatment methods. The aeration process utilizes microorganisms to decompose organic matters in the sewage into harmless inorganic matters, and simultaneously removes pollutants such as nitrogen, phosphorus and the like in the sewage, and the process promotes the growth and metabolic activity of the microorganisms by providing sufficient oxygen, so that the sewage is effectively purified.
In the aeration process, the dissolved oxygen concentration is a key parameter affecting the activity of microorganisms and the sewage treatment effect, and the proper dissolved oxygen concentration can provide a good biological environment and promote the growth of microorganisms and the degradation of organic matters. Therefore, effective monitoring and control of dissolved oxygen concentration is of great importance. In addition to aeration processes, sewage treatment involves primary treatment (e.g., screens and settling tanks), chemical treatment (e.g., coagulation and settling), and final disinfection, which, in combination, can effectively purify sewage, protect the environment and human health.
It will be appreciated that effective monitoring and control of dissolved oxygen concentration is critical in wastewater treatment processes, as dissolved oxygen plays a critical role in biological treatment processes, affecting microbial activity and the effectiveness of the overall wastewater treatment system.
Microorganisms play a vital role in sewage treatment, and they purify sewage by decomposing organic substances. However, the growth and metabolic activity of the microorganism requires sufficient oxygen, and by monitoring and controlling the dissolved oxygen concentration, it is ensured that an appropriate oxygen supply is provided, thereby maintaining the activity of the microorganism and promoting the degradation of the organic matter. The concentration of dissolved oxygen directly influences the sewage treatment effect, and too low concentration of dissolved oxygen can limit the activity of microorganisms, reduce the degradation efficiency of organic matters, lead to the reduction of the treatment effect, and can ensure that the microorganisms have enough oxygen to finish the sewage treatment process by monitoring and controlling the concentration of the dissolved oxygen, thereby improving the treatment effect. The discharge after sewage treatment has an influence on the ecological environment of the surrounding water body, if the treatment effect is poor, organic matters and other pollutants possibly remain in the discharged water body to influence the ecological balance of the water body, and the sewage treatment can be ensured to reach the environmental discharge standard by monitoring and controlling the concentration of dissolved oxygen, so that the ecological system of the surrounding water body is protected. In the aeration process, energy is consumed to provide sufficient oxygen, and unnecessary energy waste can be avoided by monitoring and controlling the concentration of dissolved oxygen, so that the energy efficiency of the aeration system is improved.
Conventional aeration process control systems typically employ fixed air flow rates or time-switched blowers, or adjust the air flow rates in the aeration tank based on fixed time schedules or empirical rules, which cannot be dynamically adjusted based on real-time changes in dissolved oxygen concentration, and thus suffer from several drawbacks.
For example, a fixed air flow or a timed on-off blower may result in waste of energy, and when the sewage treatment system load changes, the fixed air flow may result in excessive or insufficient oxygen supply, thereby increasing energy consumption. Because the oxygen concentration cannot be adjusted according to the change of the dissolved oxygen concentration in real time, the conventional system may not provide proper oxygen supply, thereby affecting the activity of microorganisms and the degradation efficiency of organic matters, resulting in poor treatment effect. Because the aeration process can not be dynamically regulated, the traditional system can cause the condition that the concentration of dissolved oxygen in an aeration tank is too high or too low, thereby influencing the structure of a microbial community and the sewage treatment effect, even generating too many bubbles, causing the bubbles to strike sludge particles, influencing the sedimentation effect, even causing the problems of sludge floating and the like. The traditional method adjusts the air flow in the aeration tank based on fixed time scheduling or experience rules, and can not be flexibly adjusted according to the change of the concentration of the dissolved oxygen under different conditions, so that the adaptability of the system is poor when the load fluctuation or the change of the quality of the inlet water is dealt with.
In order to solve these problems, more advanced control strategies and technologies, such as an intelligent control system based on real-time monitoring data, are required to be introduced, and the aeration process can be dynamically adjusted according to the real-time change of the concentration of the dissolved oxygen, so that the energy utilization efficiency is improved, the treatment effect is improved, and the environmental risk is reduced.
In one embodiment of the present application, fig. 1 is a block diagram of an optimized control system for a sewage treatment aeration process provided in an embodiment of the present application. As shown in fig. 1, an optimization control system 100 for a sewage treatment aeration process according to an embodiment of the present application includes: an aeration tank 1 for receiving and treating incoming sewage; a dissolved oxygen sensor 2 for detecting a concentration of dissolved oxygen in the aeration tank 1; a regulating valve 3 for regulating a valve opening value to control the flow rate of air into the aeration tank 1; a blower 4 for supplying compressed air to the regulating valve 3; a controller 5, the controller 5 may be communicatively connected to the dissolved oxygen sensor 2, the regulating valve 3 and the blower 4, and the controller 5 may be configured to generate a control signal for controlling a valve opening value of the regulating valve 3 according to the dissolved oxygen concentration of the aeration tank 1.
The working principle of the optimized control system for the sewage treatment aeration process is as follows: when the concentration of the dissolved oxygen is lower than the target value, the controller outputs a signal for increasing the aeration intensity, the regulating valve is opened, the air flow is increased, and the concentration of the dissolved oxygen in the aeration tank is increased; when the dissolved oxygen concentration is higher than the target value, the controller outputs a signal for reducing the aeration intensity, the regulating valve is closed, the air flow is reduced, and the dissolved oxygen concentration in the aeration tank is reduced. By the mode, the system can realize the optimal control of the aeration process, improve the sewage treatment efficiency, save the energy consumption and reduce the environmental pollution.
The system can generate a control signal for adjusting the valve opening value of the valve through an intelligent algorithm according to the real-time change of the concentration of the dissolved oxygen, so that the optimal control of the aeration process is realized. Specifically, when the dissolved oxygen concentration is low, the controller outputs a control signal for increasing the valve opening value of the regulating valve, and controls the valve opening value of the regulating valve to be increased, the air flow is increased, and the dissolved oxygen concentration in the aeration tank is increased; when the concentration of the dissolved oxygen is higher, the controller outputs a control signal for reducing the valve opening value of the regulating valve, and the valve opening value of the regulating valve is controlled to be reduced, the air flow is reduced, and the concentration of the dissolved oxygen in the aeration tank is reduced. By the mode, the system can realize the optimal control of the aeration process, improve the sewage treatment efficiency, save the energy consumption and reduce the environmental pollution.
Correspondingly, in order to adjust the valve opening value in real time according to the dissolved oxygen concentration in the aeration tank, the air flow can be adjusted according to the requirement, so that the optimization of the aeration process is realized, and the sewage treatment efficiency is improved. Therefore, the valve opening value of the regulating valve can be adaptively regulated based on the change condition of the dissolved oxygen concentration of the aeration tank, so that the optimal control of the sewage treatment aeration process is realized, the sewage treatment efficiency is improved, the energy consumption is saved, and the environmental pollution is reduced.
In one embodiment of the present application, the controller 5 includes: the data acquisition module is used for acquiring a time sequence of the dissolved oxygen concentration of the aeration tank and a time sequence of the valve opening value of the regulating valve; the data multi-parameter time sequence association coding module is used for performing time sequence association coding on the time sequence of the dissolved oxygen concentration and the time sequence of the valve opening value to obtain a valve opening-dissolved oxygen concentration time sequence association matrix; the valve opening-dissolved oxygen concentration time sequence correlation feature extraction module is used for extracting features of the valve opening-dissolved oxygen concentration time sequence correlation matrix through a valve opening-dissolved oxygen concentration time sequence correlation feature extractor based on a deep neural network model so as to obtain a valve opening-dissolved oxygen concentration time sequence correlation feature map; the self-adaptive strengthening module is used for enabling the valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram to pass through a self-adaptive strengthening device based on a self-adaptive attention layer to obtain a self-adaptive strengthening valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram as a self-adaptive strengthening valve opening-dissolved oxygen concentration time sequence correlation characteristic; and the valve opening value control module is used for determining that the valve opening value at the current time point should be increased, decreased or maintained based on the self-adaptive reinforced valve opening-dissolved oxygen concentration time sequence correlation characteristic.
The data acquisition module ensures reliable data acquisition and timely and accurately transmits data, and provides a data base of the dissolved oxygen concentration and the valve opening of the aeration tank in real time. The data multi-parameter time sequence associated coding module carries out time sequence associated coding on the time sequence of the dissolved oxygen concentration and the time sequence of the valve opening value, is beneficial to establishing an associated relation between the valve opening and the dissolved oxygen concentration, and provides a basis for subsequent control decisions. The valve opening-dissolved oxygen concentration time sequence correlation characteristic extraction module is used for extracting the characteristics of the valve opening-dissolved oxygen concentration time sequence correlation matrix based on the characteristic extractor of the deep neural network model, and extracting useful characteristics from complex data so as to facilitate subsequent decision and control. The self-adaptive strengthening module converts the valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram into the self-adaptive strengthening valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram through the self-adaptive strengthening device based on the self-adaptive attention layer so as to improve the attention degree to key characteristics and help the system to more flexibly cope with the changes under different conditions. The valve opening value control module determines that the valve opening value at the current time point should be increased, decreased or kept based on the self-adaptive reinforced valve opening-dissolved oxygen concentration time sequence correlation characteristic, and ensures the dynamic adjustment of the aeration process according to the real-time condition.
The optimized control system for the sewage treatment aeration process is beneficial to improving the energy utilization efficiency and the treatment effect, and can better adapt to the change under different conditions.
Specifically, in the technical scheme of the present application, first, a time series of the dissolved oxygen concentration of the aeration tank and a time series of the valve opening value of the regulating valve are acquired. Next, it is considered that both the dissolved oxygen concentration and the valve opening value are time-varying during aeration of the sewage treatment. That is, the dissolved oxygen concentration and the valve opening value both have a time-series variation law in the time dimension. In order to integrate and arrange the time sequence data information thereof so as to facilitate the subsequent time sequence collaborative correlation analysis and the self-adaptive control of the valve opening degree for the two, in the technical scheme of the application, the time sequence of the dissolved oxygen concentration and the time sequence of the valve opening degree value are required to be respectively arranged into a dissolved oxygen concentration time sequence input vector and a regulating valve opening degree time sequence input vector according to a time dimension.
In a specific embodiment of the present application, the data multi-parameter timing related encoding module includes: the data multi-parameter time sequence arrangement unit is used for respectively arranging the time sequence of the dissolved oxygen concentration and the time sequence of the valve opening value into a dissolved oxygen concentration time sequence input vector and a regulating valve opening time sequence input vector according to a time dimension; the valve opening-dissolved oxygen concentration time sequence correlation analysis module is used for calculating a sample covariance correlation matrix of the dissolved oxygen concentration time sequence input vector relative to the regulating valve opening time sequence input vector so as to obtain the valve opening-dissolved oxygen concentration time sequence correlation matrix.
Then, it is considered that the change of the valve opening value during aeration of sewage treatment affects the concentration of dissolved oxygen, because the change of the valve opening value causes the change of the air flow rate, thereby affecting the concentration of dissolved oxygen. Therefore, in order to establish and analyze a time sequence association relationship between a valve opening value and a dissolved oxygen concentration so as to adaptively adjust the valve opening value according to a change of the dissolved oxygen concentration, in the technical scheme of the application, a sample covariance association matrix of the dissolved oxygen concentration time sequence input vector relative to the adjusting valve opening time sequence input vector is calculated so as to obtain a valve opening-dissolved oxygen concentration time sequence association matrix. By calculating the valve opening-dissolved oxygen concentration time-series correlation matrix between the valve opening value and the dissolved oxygen concentration, the correlation and interaction therebetween can be revealed. It should be noted that the valve opening-dissolved oxygen concentration time sequence correlation matrix can provide time sequence correlation information between the valve opening and the dissolved oxygen concentration, and the correlation information can reflect the influence degree of the valve opening on the dissolved oxygen concentration, so that a basis is provided for generating a subsequent control signal, and a more accurate control strategy is provided for an optimized control system.
In a specific embodiment of the present application, the valve opening-dissolved oxygen concentration timing correlation analysis module is configured to: calculating a sample covariance correlation matrix of the dissolved oxygen concentration time sequence input vector relative to the regulating valve opening time sequence input vector by using the following covariance formula to obtain a valve opening-dissolved oxygen concentration time sequence correlation matrix; wherein, the covariance formula is:the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>Is the time sequence input vector of the dissolved oxygen concentration, < >>Is the transpose of the time sequence input vector of the dissolved oxygen concentration,>is the valve opening time sequence input vector of the regulating valve, < >>Is the transposed vector of the time sequence input vector of the opening degree of the regulating valve>Is the valve opening-dissolved oxygen concentration time sequence correlation matrix.
In the sewage treatment aeration process, the time sequence correlation characteristic between the opening of the valve and the concentration of the dissolved oxygen is critical to the optimization control system. And then, performing feature mining on the valve opening-dissolved oxygen concentration time sequence correlation matrix through a valve opening-dissolved oxygen concentration time sequence correlation feature extractor based on a deep neural network model so as to extract time sequence collaborative correlation feature information between the valve opening value and the dissolved oxygen concentration, thereby obtaining a valve opening-dissolved oxygen concentration time sequence correlation feature map.
The deep neural network model is a convolutional neural network model.
Further, considering that each channel of the valve opening-dissolved oxygen concentration time series correlation characteristic diagram represents different time series cooperative correlation characteristics between valve opening values and dissolved oxygen concentrations, some of the characteristics have an important role in time series correlation analysis of the valve opening values and the dissolved oxygen concentrations, and some of the characteristics are irrelevant interference characteristics. Therefore, in order to concentrate attention on important channel characteristics, the influence of irrelevant characteristics on time sequence correlation analysis between valve opening values and dissolved oxygen concentration is weakened, so that the accuracy of the classifier on valve opening value self-adaptive control is improved. Specifically, in the technical scheme of the application, the valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram is further obtained through an adaptive enhancer based on an adaptive attention layer. It should be appreciated that the adaptive attention module converts the feature map of each channel into a weight value by using a meta-weight generator. The weight values are multiplied by the valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram channel by channel, so that each channel in the characteristic diagram is focused to different degrees, and important channel characteristic information is highlighted. Therefore, attention can be focused on important features, and influence of irrelevant features is weakened, so that the self-adaptive reinforcement valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram can better reflect the correlation between the valve opening and the dissolved oxygen concentration, and provides more accurate basis for subsequent control signal generation.
In a specific embodiment of the present application, the adaptive reinforcement module is configured to: processing the valve opening-dissolved oxygen concentration time sequence correlation characteristic map through an adaptive enhancer based on an adaptive attention layer according to the following adaptive enhancement formula to obtain the adaptive enhancement valve opening-dissolved oxygen concentration time sequence correlation characteristic map; wherein, the self-adaptive strengthening formula is:
；
；
；
；
wherein,is the valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram,>representing global mean pooling of individual feature matrices along the channel dimension in the feature map,/->Is the channel characteristic vector of the valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram, +.>And->Is the weight and bias of the convolutional layer, +.>To activate the function +.>Is a convolution eigenvector of said channel eigenvector, ">Is the eigenvalue of each position in the convolution eigenvector,>is a weight vector, +.>Is multiplied by the position point +.>Is the self-adaptive reinforced valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram.
And then, the self-adaptive reinforced valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating that the valve opening value at the current time point should be increased, decreased or maintained. That is, the valve opening value at the present time point is adaptively controlled by performing classification processing using the time-series cooperative correlation characteristic of the valve opening value and the solution oxygen concentration after the adaptive reinforcement, and it is determined that the valve opening value should be increased, decreased, or maintained, and a control signal for adjusting the valve opening value of the valve is generated. Therefore, the valve opening value of the regulating valve can be adaptively regulated based on the change condition of the dissolved oxygen concentration of the aeration tank, so that the optimal control of the sewage treatment aeration process is realized, the sewage treatment efficiency is improved, the energy consumption is saved, and the environmental pollution is reduced.
In a specific embodiment of the present application, the valve opening value control module is configured to: and passing the self-adaptive intensified valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram through a classifier to obtain a classification result, wherein the classification result is used for indicating that the valve opening value at the current time point should be increased, decreased or maintained.
In one embodiment of the application, the optimized control system of the sewage treatment aeration process further comprises a training module for training the valve opening-dissolved oxygen concentration time sequence correlation feature extractor based on the deep neural network model, the adaptive enhancer based on the adaptive attention layer and the classifier. The training module comprises: the training data acquisition unit is used for acquiring a time sequence of training the concentration of dissolved oxygen in the aeration tank and a time sequence of training the opening value of the valve of the regulating valve; the training data multi-parameter time sequence associated coding unit is used for performing time sequence associated coding on the time sequence of the training dissolved oxygen concentration and the time sequence of the training valve opening value to obtain a training valve opening-dissolved oxygen concentration time sequence associated matrix; a training valve opening-dissolved oxygen concentration time sequence correlation feature extraction unit, which is used for extracting features of the training valve opening-dissolved oxygen concentration time sequence correlation matrix through a valve opening-dissolved oxygen concentration time sequence correlation feature extractor based on the deep neural network model so as to obtain a training valve opening-dissolved oxygen concentration time sequence correlation feature map; the training self-adaptive strengthening unit is used for enabling the training valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram to pass through the self-adaptive strengthening device based on the self-adaptive attention layer so as to obtain the training self-adaptive strengthening valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram; the training optimization unit is used for optimizing the training self-adaptive reinforcement valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram to obtain an optimized training self-adaptive reinforcement valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram; the training classification unit is used for enabling the optimized training self-adaptive reinforcement valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram to pass through the classifier so as to obtain a classification loss function value; and the training unit is used for training the valve opening-dissolved oxygen concentration time sequence correlation characteristic extractor based on the deep neural network model, the adaptive enhancer based on the adaptive attention layer and the classifier based on the classification loss function value.
In the technical scheme of the application, the training valve opening-dissolved oxygen concentration time sequence correlation matrix expresses the full-time domain correlation characteristics of the training dissolved oxygen concentration and the training regulating valve opening, so that each characteristic matrix of the training valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram expresses the local time domain high-order correlation characteristics of the training dissolved oxygen concentration and the training regulating valve opening, and the channel distribution of the convolution neural network model among the characteristic matrices. In this way, after the training valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram passes through the self-adaptive enhancer based on the self-adaptive attention layer, the obtained training self-adaptive enhancement valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram has local spatial distribution sparsity of the high-order correlation characteristic due to local self-adaptive attention enhancement on the spatial distribution of the high-order correlation characteristic, so that when the training self-adaptive enhancement valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram is classified by the classifier, probability density representation under a class probability density domain sparsity is caused, and regression convergence effect is affected when the training self-adaptive enhancement valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram is classified by the classifier.
Based on the time sequence correlation characteristic diagram of the opening degree and the dissolved oxygen concentration of the training self-adaptive reinforced valveOptimization was performed, expressed as: the training self-adaptive reinforced valve is subjected to the following optimization formulaOptimizing the door opening-dissolved oxygen concentration time sequence correlation characteristic diagram to obtain an optimized training self-adaptive reinforced valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram; wherein, the optimization formula is:
；
；
wherein,representing the training self-adaptive reinforced valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram +.>Position-by-position square of>For the parameter trainable intermediate weight graph, for example, based on the spatial distribution sparsity of the training self-adaptive reinforced valve opening-dissolved oxygen concentration time sequence correlation characteristic graph, the characteristic value of each characteristic matrix is initially set as the training self-adaptive reinforced valve opening-dissolved oxygen concentration time sequence correlation characteristic graph->Global eigenvalue mean of the corresponding eigenvalue matrix of (2), furthermore,/-j>For all single bitmaps with characteristic value 1, +.>Is the training self-adaptive reinforced valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram, namely +.>Is the optimized training self-adaptive reinforced valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram, namely ∈10 >Representing addition by position +.>Representing multiplication by location.
Here, in order to optimize the training adaptive reinforcement valve opening-dissolved oxygen concentration timing correlation characteristic mapDistribution uniformity and consistency of sparse probability density in the whole probability space, and self-adaptively strengthening valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram for training through a tail distribution strengthening mechanism similar to standard cauchy distribution>The distance type space distribution in the high-dimensional characteristic space is optimized based on the space angle inclination type distance distribution so as to realize the training self-adaptive reinforcement valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram->The characteristic distribution space resonance of weak correlation of the distance of each local characteristic distribution of the self-adaptive reinforcement valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram is improved>The uniformity and consistency of the overall probability density distribution layer relative to regression probability convergence improve the classification convergence effect, namely the classification convergence speed and the classification result accuracy. Therefore, the self-adaptive control of the valve opening value can be performed based on the change condition of the dissolved oxygen concentration of the aeration tank, so that the optimal control of the sewage treatment aeration process is realized, the sewage treatment efficiency is improved, the energy consumption is saved, and the environmental pollution is reduced.
In summary, the optimized control system 100 for sewage treatment aeration process according to the embodiment of the present application is illustrated, which performs adaptive control of valve opening value by monitoring and collecting the dissolved oxygen concentration of an aeration tank and the valve opening value of a regulating valve in real time, and introducing an artificial intelligence-based data processing and analysis algorithm at the rear end to perform time-sequence collaborative correlation analysis of the dissolved oxygen concentration and the valve opening value. Therefore, the valve opening value of the regulating valve can be adaptively regulated based on the change condition of the dissolved oxygen concentration of the aeration tank, so that the optimal control of the sewage treatment aeration process is realized, the sewage treatment efficiency is improved, the energy consumption is saved, and the environmental pollution is reduced.
As described above, the optimal control system 100 for a sewage treatment aeration process according to the embodiment of the present application may be implemented in various terminal devices, such as a server or the like for optimal control of a sewage treatment aeration process. In one example, the optimal control system 100 for a sewage treatment aeration process according to an embodiment of the present application may be integrated into a terminal device as one software module and/or hardware module. For example, the optimal control system 100 of the sewage treatment aeration process may be a software module in the operating system of the terminal device, or may be an application program developed for the terminal device; of course, the optimal control system 100 for the sewage treatment aeration process may also be one of a plurality of hardware modules of the terminal device.
Alternatively, in another example, the optimal control system 100 of the sewage treatment aeration process and the terminal device may be separate devices, and the optimal control system 100 of the sewage treatment aeration process may be connected to the terminal device through a wired and/or wireless network and transmit interactive information in a agreed data format.
Fig. 2 is a flowchart of an optimized control method for a sewage treatment aeration process according to an embodiment of the present application, and as shown in fig. 2, the optimized control method for a sewage treatment aeration process includes: 210 receiving and treating incoming sewage through an aeration tank; 220, detecting the dissolved oxygen concentration of the aeration tank by a dissolved oxygen sensor; 230 controlling the air flow into the aeration tank by adjusting the valve opening value; 240, supplying compressed air to the regulating valve through a blower; 250, communicably connecting a controller to the dissolved oxygen sensor, the regulating valve and the blower, and generating a control signal for controlling a valve opening value of the regulating valve by the controller according to the dissolved oxygen concentration of the aeration tank.
Fig. 3 is a schematic diagram of a system architecture of an optimized control method for a sewage treatment aeration process according to an embodiment of the present application. As shown in fig. 3, generating a control signal for controlling the valve opening value of the regulating valve according to the dissolved oxygen concentration of the aeration tank, includes: firstly, obtaining a time sequence of dissolved oxygen concentration of the aeration tank and a time sequence of valve opening value of the regulating valve; then, performing time sequence association coding on the time sequence of the dissolved oxygen concentration and the time sequence of the valve opening value to obtain a valve opening-dissolved oxygen concentration time sequence association matrix; then, performing feature extraction on the valve opening-dissolved oxygen concentration time sequence correlation matrix by a valve opening-dissolved oxygen concentration time sequence correlation feature extractor based on a deep neural network model to obtain a valve opening-dissolved oxygen concentration time sequence correlation feature map; then, the valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram is used as an adaptive enhancement valve opening-dissolved oxygen concentration time sequence correlation characteristic by an adaptive enhancer based on an adaptive attention layer; finally, based on the self-adaptive reinforced valve opening-dissolved oxygen concentration time sequence correlation characteristic, determining that the valve opening value at the current time point should be increased, decreased or maintained.
It will be appreciated by those skilled in the art that the specific operations of the respective steps in the above-described optimized control method of the sewage treatment aeration process have been described in detail in the above description of the optimized control system of the sewage treatment aeration process with reference to fig. 1, and thus, repetitive descriptions thereof will be omitted.
Fig. 4 is an application scenario diagram of an optimizing control system for a sewage treatment aeration process provided in an embodiment of the present application. As shown in fig. 4, in this application scenario, first, a time series of the dissolved oxygen concentration of the aeration tank (e.g., C1 as illustrated in fig. 4) and a time series of the valve opening value of the regulating valve (e.g., C2 as illustrated in fig. 4) are acquired; then, the obtained time series of the dissolved oxygen concentration of the aeration tank and the time series of the valve opening value of the regulating valve are input to a server (e.g., S as illustrated in fig. 4) where an optimization control algorithm of the sewage treatment aeration process is deployed, wherein the server is capable of processing the time series of the dissolved oxygen concentration of the aeration tank and the time series of the valve opening value of the regulating valve based on the optimization control algorithm of the sewage treatment aeration process to determine that the valve opening value at the current point of time should be increased, should be decreased, or should be maintained.
The foregoing embodiments have been provided for the purpose of illustrating the general principles of the present application and are not meant to limit the scope of the invention, but to limit the scope of the invention.
Claims (9)
1. An optimized control system for a sewage treatment aeration process, comprising: an aeration tank for receiving and treating incoming sewage; a dissolved oxygen sensor for detecting a dissolved oxygen concentration of the aeration tank; the adjusting valve is used for adjusting the opening value of the valve to control the air flow entering the aeration tank; a blower for supplying compressed air to the regulating valve; the controller can be in communication connection with the dissolved oxygen sensor, the regulating valve and the blower, and is used for generating a control signal for controlling the valve opening value of the regulating valve according to the dissolved oxygen concentration of the aeration tank; wherein, the controller includes: the data acquisition module is used for acquiring a time sequence of the dissolved oxygen concentration of the aeration tank and a time sequence of the valve opening value of the regulating valve; the data multi-parameter time sequence association coding module is used for performing time sequence association coding on the time sequence of the dissolved oxygen concentration and the time sequence of the valve opening value to obtain a valve opening-dissolved oxygen concentration time sequence association matrix; the valve opening-dissolved oxygen concentration time sequence correlation feature extraction module is used for extracting features of the valve opening-dissolved oxygen concentration time sequence correlation matrix through a valve opening-dissolved oxygen concentration time sequence correlation feature extractor based on a deep neural network model so as to obtain a valve opening-dissolved oxygen concentration time sequence correlation feature map; the self-adaptive strengthening module is used for enabling the valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram to pass through a self-adaptive strengthening device based on a self-adaptive attention layer to obtain a self-adaptive strengthening valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram as a self-adaptive strengthening valve opening-dissolved oxygen concentration time sequence correlation characteristic; and the valve opening value control module is used for determining that the valve opening value at the current time point should be increased, decreased or maintained based on the self-adaptive reinforced valve opening-dissolved oxygen concentration time sequence correlation characteristic.
2. The optimal control system for a wastewater treatment aeration process according to claim 1, wherein the data multi-parameter time sequence associated coding module comprises: the data multi-parameter time sequence arrangement unit is used for respectively arranging the time sequence of the dissolved oxygen concentration and the time sequence of the valve opening value into a dissolved oxygen concentration time sequence input vector and a regulating valve opening time sequence input vector according to a time dimension; the valve opening-dissolved oxygen concentration time sequence correlation analysis module is used for calculating a sample covariance correlation matrix of the dissolved oxygen concentration time sequence input vector relative to the regulating valve opening time sequence input vector so as to obtain the valve opening-dissolved oxygen concentration time sequence correlation matrix.
3. The optimal control system for a sewage treatment aeration process according to claim 2, wherein the valve opening-dissolved oxygen concentration time series correlation analysis module is configured to: calculating a sample covariance correlation matrix of the dissolved oxygen concentration time sequence input vector relative to the regulating valve opening time sequence input vector by using the following covariance formula to obtain a valve opening-dissolved oxygen concentration time sequence correlation matrix; wherein, the covariance formula is: The method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>Is the time sequence input vector of the dissolved oxygen concentration, < >>Is the transpose of the time sequence input vector of the dissolved oxygen concentration,>is the valve opening time sequence input vector of the regulating valve, < >>Is the transposed vector of the time sequence input vector of the opening degree of the regulating valve>Is the valve opening-dissolved oxygen concentration time sequence correlation matrix.
4. The optimal control system for a sewage treatment aeration process according to claim 3, wherein the deep neural network model is a convolutional neural network model.
5. The optimal control system for a wastewater treatment aeration process according to claim 4, wherein the adaptive reinforcement module is configured to: processing the valve opening-dissolved oxygen concentration time sequence correlation characteristic map through an adaptive enhancer based on an adaptive attention layer according to the following adaptive enhancement formula to obtain the adaptive enhancement valve opening-dissolved oxygen concentration time sequence correlation characteristic map; wherein, the self-adaptive strengthening formula is:
；
；
；
；
wherein,is the valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram,>representing global mean pooling of individual feature matrices along the channel dimension in the feature map,/- >Is the channel characteristic vector of the valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram, +.>And->Is the weight and bias of the convolutional layer, +.>To activate the function +.>Is a convolution eigenvector of said channel eigenvector, ">Is the eigenvalue of each position in the convolution eigenvector,>is a weight vector, +.>Is multiplied by the position point +.>Is the self-adaptive reinforced valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram.
6. The optimal control system for a wastewater treatment aeration process according to claim 5, wherein the valve opening value control module is configured to: and passing the self-adaptive intensified valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram through a classifier to obtain a classification result, wherein the classification result is used for indicating that the valve opening value at the current time point should be increased, decreased or maintained.
7. An optimized control system for a sewage treatment aeration process according to claim 6, further comprising a training module for training the valve opening-dissolved oxygen concentration time-series correlation feature extractor based on the deep neural network model, the adaptive attention-layer-based adaptive enhancer, and the classifier.
8. The optimal control system for a wastewater treatment aeration process of claim 7, wherein the training module comprises: the training data acquisition unit is used for acquiring a time sequence of training the concentration of dissolved oxygen in the aeration tank and a time sequence of training the opening value of the valve of the regulating valve; the training data multi-parameter time sequence associated coding unit is used for performing time sequence associated coding on the time sequence of the training dissolved oxygen concentration and the time sequence of the training valve opening value to obtain a training valve opening-dissolved oxygen concentration time sequence associated matrix; a training valve opening-dissolved oxygen concentration time sequence correlation feature extraction unit, which is used for extracting features of the training valve opening-dissolved oxygen concentration time sequence correlation matrix through a valve opening-dissolved oxygen concentration time sequence correlation feature extractor based on the deep neural network model so as to obtain a training valve opening-dissolved oxygen concentration time sequence correlation feature map; the training self-adaptive strengthening unit is used for enabling the training valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram to pass through the self-adaptive strengthening device based on the self-adaptive attention layer so as to obtain the training self-adaptive strengthening valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram; the training optimization unit is used for optimizing the training self-adaptive reinforcement valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram to obtain an optimized training self-adaptive reinforcement valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram; the training classification unit is used for enabling the optimized training self-adaptive reinforcement valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram to pass through the classifier so as to obtain a classification loss function value; and the training unit is used for training the valve opening-dissolved oxygen concentration time sequence correlation characteristic extractor based on the deep neural network model, the adaptive enhancer based on the adaptive attention layer and the classifier based on the classification loss function value.
9. An optimized control method for sewage treatment aeration process is characterized by comprising the following steps: receiving and treating the entered sewage through an aeration tank; detecting the dissolved oxygen concentration of the aeration tank by a dissolved oxygen sensor; controlling the air flow entering the aeration tank by adjusting the opening value of the valve; providing compressed air to the regulating valve by a blower; a controller is communicably connected with the dissolved oxygen sensor, the regulating valve and the blower, and a control signal for controlling the valve opening value of the regulating valve is generated by the controller according to the dissolved oxygen concentration of the aeration tank; wherein, through the controller according to the dissolved oxygen concentration of aeration tank generates the control signal of the valve aperture value of control valve, include: acquiring a time sequence of the dissolved oxygen concentration of the aeration tank and a time sequence of a valve opening value of the regulating valve; performing time sequence association coding on the time sequence of the dissolved oxygen concentration and the time sequence of the valve opening value to obtain a valve opening-dissolved oxygen concentration time sequence association matrix; performing feature extraction on the valve opening-dissolved oxygen concentration time sequence correlation matrix by a valve opening-dissolved oxygen concentration time sequence correlation feature extractor based on a deep neural network model to obtain a valve opening-dissolved oxygen concentration time sequence correlation feature map; the valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram is used for obtaining an adaptive reinforced valve opening-dissolved oxygen concentration time sequence correlation characteristic diagram as an adaptive reinforced valve opening-dissolved oxygen concentration time sequence correlation characteristic through an adaptive enhancer based on an adaptive attention layer; based on the self-adaptive reinforced valve opening-dissolved oxygen concentration time sequence correlation characteristic, the valve opening value at the current time point is determined to be increased, decreased or maintained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410135241.0A CN117682682A (en) | 2024-01-31 | 2024-01-31 | Optimized control system and method for sewage treatment aeration process |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410135241.0A CN117682682A (en) | 2024-01-31 | 2024-01-31 | Optimized control system and method for sewage treatment aeration process |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117682682A true CN117682682A (en) | 2024-03-12 |
Family
ID=90133717
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410135241.0A Pending CN117682682A (en) | 2024-01-31 | 2024-01-31 | Optimized control system and method for sewage treatment aeration process |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117682682A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5989428A (en) * | 1996-06-21 | 1999-11-23 | Goronszy; Mervyn Charles | Controlling wastewater treatment by monitoring oxygen utilization rates |
| US6400996B1 (en) * | 1999-02-01 | 2002-06-04 | Steven M. Hoffberg | Adaptive pattern recognition based control system and method |
| CN1500204A (en) * | 2001-03-23 | 2004-05-26 | ������������ʽ���� | Method and appts. for endpoint detection using partial least squares |
| EP2196438A1 (en) * | 2008-12-11 | 2010-06-16 | Envicon Klärtechnik Verwaltungsgesellschaft mbH | Method for load-independent regulation of nitrification and denitrification in waste water treatment facilities with advanced denitrification |
| CN109111030A (en) * | 2018-08-27 | 2019-01-01 | 重庆固润科技发展有限公司 | Integrated sewage disposal intelligence control system and control method |
| CN116088450A (en) * | 2023-01-20 | 2023-05-09 | 北京首创生态环保集团股份有限公司 | Intelligent terminal control system of sewage treatment plant, construction method and control method |
| CN117058622A (en) * | 2023-08-28 | 2023-11-14 | 海宁市立洁环保有限公司 | Intelligent monitoring system and method for sewage treatment equipment |
| CN117164103A (en) * | 2023-07-03 | 2023-12-05 | 广西智碧达智慧环境科技有限公司 | Intelligent control method, terminal and system of domestic sewage treatment system |
| CN117251718A (en) * | 2023-11-20 | 2023-12-19 | 吉林省拓达环保设备工程有限公司 | Intelligent aeration management system based on artificial intelligence |
-
2024
- 2024-01-31 CN CN202410135241.0A patent/CN117682682A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5989428A (en) * | 1996-06-21 | 1999-11-23 | Goronszy; Mervyn Charles | Controlling wastewater treatment by monitoring oxygen utilization rates |
| US6400996B1 (en) * | 1999-02-01 | 2002-06-04 | Steven M. Hoffberg | Adaptive pattern recognition based control system and method |
| CN1500204A (en) * | 2001-03-23 | 2004-05-26 | ������������ʽ���� | Method and appts. for endpoint detection using partial least squares |
| EP2196438A1 (en) * | 2008-12-11 | 2010-06-16 | Envicon Klärtechnik Verwaltungsgesellschaft mbH | Method for load-independent regulation of nitrification and denitrification in waste water treatment facilities with advanced denitrification |
| CN109111030A (en) * | 2018-08-27 | 2019-01-01 | 重庆固润科技发展有限公司 | Integrated sewage disposal intelligence control system and control method |
| CN116088450A (en) * | 2023-01-20 | 2023-05-09 | 北京首创生态环保集团股份有限公司 | Intelligent terminal control system of sewage treatment plant, construction method and control method |
| CN117164103A (en) * | 2023-07-03 | 2023-12-05 | 广西智碧达智慧环境科技有限公司 | Intelligent control method, terminal and system of domestic sewage treatment system |
| CN117058622A (en) * | 2023-08-28 | 2023-11-14 | 海宁市立洁环保有限公司 | Intelligent monitoring system and method for sewage treatment equipment |
| CN117251718A (en) * | 2023-11-20 | 2023-12-19 | 吉林省拓达环保设备工程有限公司 | Intelligent aeration management system based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109669352B (en) | Oily sewage treatment process optimization control method based on self-adaptive multi-target particle swarm | |
| US20140052422A1 (en) | Method and system for wastewater treatment based on dissolved oxygen control by fuzzy neural network | |
| CN103570190B (en) | Method for controlling feeding amount of chemical phosphorus removal reagents of water reclamation plants based on fuzzy control | |
| CN113845205B (en) | High-salinity high-nitrogen sewage intelligent integrated desalting and denitrification control system | |
| Santín et al. | Control and decision strategies in wastewater treatment plants for operation improvement | |
| CN114427684A (en) | Control method and control device for combustion furnace in natural gas purification process | |
| CN117251718B (en) | Intelligent aeration management system based on artificial intelligence | |
| CN117682682A (en) | Optimized control system and method for sewage treatment aeration process | |
| CN117171677B (en) | Microbial restoration effect evaluation method, system and medium based on decision tree model | |
| CN112348253B (en) | Solid state fermentation utility prediction method based on full-connection neural network | |
| CN112250166B (en) | Printing and dyeing wastewater efficient detoxification gradient treatment method based on intelligent SBR electrode process | |
| CN114488822B (en) | Intelligent sewage treatment process optimization method based on high-dimensional multi-objective evolutionary algorithm | |
| CN116040892A (en) | Domestic garbage sewage treatment method | |
| CN101955278B (en) | Method for treating sewage from leather making | |
| Huang et al. | Modeling and optimization of the activated sludge process | |
| Husin et al. | Improving total nitrogen removal using a neural network ammonia-based aeration control in activated sludge process | |
| CN113003692A (en) | Case reasoning-based dosing control method for denitrification process of municipal sewage treatment | |
| CN111591968A (en) | Method for efficiently recovering nitrogen and phosphorus elements in urine separated from source step by step | |
| CN117247180A (en) | Device and method for treating high-fluorine high-ammonia-nitrogen wastewater | |
| CN113511736B (en) | Intelligent aeration method and device for sewage treatment | |
| Sadeghassadi et al. | Adaptive control and setpoint optimization for the BSM1 model of wastewater treatment | |
| Swarnalatha | Simulation and Analysis of Ammonium-Based Aeration Control Strategies to Enhance Efficiency in Wastewater Treatment Plant | |
| CN117518778A (en) | Multi-objective optimization control method for sewage treatment process with intermittent Pareto front | |
| CN117228894A (en) | Accurate aeration sewage treatment process method | |
| Ye et al. | Application of RBF network based on immune algorithm to predicting of wastewater treatment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |