A control method for modular constructed wetland sewage system based on artificial intelligence
Through the modular control method based on artificial intelligence, the purification unit of the wetland sewage system is optimized, and the problem of low efficiency in traditional wetland sewage treatment is solved, and the sewage treatment efficiency is improved and precise regulation is achieved.
Patent Information
- Application Number
- CN202411097899.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-12
- Publication Date
- 2024-11-05
- Estimated Expiration
- 2044-08-12
AI Technical Summary
During the traditional wetland sewage treatment process, due to the different terrain, types and content of purification fillers, it is difficult to achieve precise regulation with a unified treatment strategy, resulting in the sewage treatment efficiency that does not meet the emission standards and is difficult to improve.
Adopt a modular artificial wetland sewage system control method based on artificial intelligence, obtain water quality parameters through water quality sensors, calculate sewage treatment efficiency, determine whether preset purification indicators are met, and use pre-trained learning models to generate control strategies to adjust the valve opening of the purification unit. Combine the angle and filler addition amount to optimize the sewage treatment process.
The sewage treatment efficiency is improved, the sewage removal rate meets the emission standards, and the precise regulation and efficient operation of the wetland sewage purification device are achieved.
Smart Images

Figure CN118642449B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of sewage purification, and in particular to a control method for a modular artificial wetland sewage system based on artificial intelligence. Background Art
[0002] Water resources play a vital role in daily production and life. When sewage is discharged, it generally needs to be processed by a sewage treatment plant before it is discharged. However, in the traditional sewage treatment process, it is generally treated according to a unified sewage treatment strategy.
[0003] In the wetland sewage treatment process, due to factors such as terrain, types and contents of purification fillers, the removal rate of sewage treatment according to a unified treatment strategy does not meet the emission standards. The workload of manual control is large and it is difficult to achieve precise control, and the sewage treatment efficiency needs to be improved. Summary of the invention
[0004] In view of this, an object of the present invention is to provide a control method for a modular artificial wetland sewage system based on artificial intelligence.
[0005] In a first aspect, an embodiment of the present invention provides a control method for a modular artificial wetland sewage system based on artificial intelligence, the method being applied to a control unit in the modular artificial wetland sewage system, the modular artificial wetland sewage system further comprising a wetland sewage purification device, the device comprising a plurality of parallel purification units perpendicular to the sewage flow direction, one end of the purification unit being connected to a sewage source through a water distribution pipe, and the other end of the purification unit being connected to a purified water outlet through a water collection pipe; water quality sensors are provided at the outlet ends of the water distribution pipe and the water collection pipe; the water quality sensor is communicatively connected to the control unit;
[0006] The method includes:
[0007] Obtaining a first water quality parameter of an outlet end of a water collecting pipe and a second water quality parameter of a water distribution pipe;
[0008] calculating the sewage treatment efficiency of the wetland sewage purification device according to the first water quality parameter and the second water quality parameter;
[0009] Determine whether the sewage treatment efficiency meets the preset purification indicators;
[0010] If not, obtain the wastewater removal rate of each purification unit in the wetland wastewater purification device;
[0011] Input all sewage removal rates and preset purification indicators into the pre-trained learning model and output the corresponding control strategy;
[0012] Based on the control strategy, the operation of the wetland sewage purification device is controlled.
[0013] In combination with the first aspect, the step of calculating the sewage treatment efficiency of the wetland sewage purification device according to the water quality parameter and the second water quality parameter of the sewage source includes:
[0014] calculating a difference between a first water quality parameter and a second water quality parameter;
[0015] The ratio of the difference to the first water quality parameter is calculated to obtain the sewage treatment efficiency of the wetland sewage purification device.
[0016] In combination with the first aspect, after the step of obtaining the sewage removal rate of each purification unit in the wetland sewage purification device, the method further includes:
[0017] For each purification unit, determining whether the sewage removal rate of the purification unit meets a second preset target;
[0018] The purification unit that meets the second preset target is defined as a first target adjustment unit.
[0019] In combination with the first aspect, a first valve is provided between each purification unit and the water distribution pipe; the first valve is connected to the control unit; the control strategy includes a target opening and closing angle of the first valve corresponding to the target adjustment unit;
[0020] The steps of controlling the operation of the wetland sewage purification device based on the control strategy include:
[0021] The opening and closing angle of the valve corresponding to the target regulating unit is controlled to increase to the target opening and closing angle to adjust the flow of the target regulating unit entering the sewage source.
[0022] In combination with the first aspect, the purification unit includes a plurality of sub-purification units connected in series in a sewage flow direction; a second valve is provided on the connecting pipeline between two adjacent sub-purification units; the second valve is connected to the control unit; the control unit pre-stores filler information in each sub-purification unit; the control strategy also includes determining a first number of target sub-purification units according to the descending order of the sewage treatment effect of the filler, and a target opening and closing angle of the second valve corresponding to each target sub-purification unit;
[0023] Based on the control strategy, the steps of controlling the operation of the wetland sewage purification device include:
[0024] For each target sub-purification unit, the opening and closing angle of the target second valve corresponding to the target sub-purification unit is controlled to increase to the target opening and closing angle.
[0025] In combination with the first aspect, the control unit further stores the serial number of each sub-purification unit; the control strategy further includes: the amount of filler added corresponding to each target sub-purification unit;
[0026] Based on the control strategy, the steps of controlling the operation of the wetland sewage purification device include:
[0027] Returns the number corresponding to the target sub-purification unit and the amount of filler added corresponding to the target sub-purification unit.
[0028] In combination with the first aspect, the purification unit further comprises a reflux pipe, the inlet end of the reflux pipe is connected to the first sub-purification unit, and the outlet end of the reflux pipe is connected to all the second sub-purification units located in the first sub-purification unit; and a reflux valve is provided on the reflux pipe near the inlet end;
[0029] The control strategy also includes: target opening and closing angles of the return valve;
[0030] Based on the control strategy, the steps of controlling the operation of the wetland sewage purification device include:
[0031] Control the reflux valve to rotate to the target opening and closing angle.
[0032] In combination with the first aspect, the control unit is further connected to a human-computer interaction interface, and a designated key connection is provided on the human-computer interaction interface; the method further includes:
[0033] In response to a user's touch or press operation on a designated key, the first water quality parameter, the second parameter, the preset purification index and the control strategy are displayed on the human-computer interaction interface.
[0034] In combination with the first aspect, the method further includes:
[0035] In response to a user's adjustment operation on a preset purification index, updating the preset purification index according to the adjusted purification index;
[0036] The preset purification indicators are input into the pre-trained learning model and the current control strategy is output.
[0037] In combination with the first aspect, it also includes an artificial intelligence voice interaction model, and the output end of the artificial intelligence voice interaction model is connected to the input end of the pre-trained learning model; the method also includes:
[0038] Receive user's voice command information;
[0039] Input voice command information into the artificial intelligence voice interaction model, output at least one voice recognition result and display it on the human-computer interaction interface;
[0040] In response to the user's touch or selection operation on the target speech recognition result, the speech recognition result is input into the pre-trained learning model, and the target control strategy is output and fed back to the human-computer interaction interface.
[0041] The embodiments of the present invention bring about the following beneficial effects: The present application provides a control method for a modular artificial wetland sewage system based on artificial intelligence. When the sewage treatment efficiency of a wetland sewage purification device does not meet the preset purification index, the method generates a targeted control strategy based on the data processing capability of a pre-trained learning model, according to the obtained sewage removal rate of each purification unit and the preset purification index, to control the operation of the wetland sewage purification device to improve the sewage treatment effect.
[0042] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description, claims and drawings.
[0043] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0044] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without paying any creative work.
[0045] Figure 1 A schematic diagram of a wetland sewage treatment method according to an embodiment of the present invention;
[0046] Figure 2 A schematic diagram of the structure of a wetland sewage purification device provided by an embodiment of the present invention;
[0047] Figure 3 A schematic diagram of a wetland sewage treatment method and device provided by an embodiment of the present invention;
[0048] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention.
[0049] Reference numerals:
[0050] 1-purification unit, 2-sub-purification unit, 3-reflux valve, 4-reflux pipe, 5-water quality sensor, 6-water distribution pipe, 7-water collection pipe, 8-first valve;
[0051] 10-first acquisition module, 20-calculation module, 30-judgment module, 40-second acquisition module, 50-output module, 60-control module;
[0052] 130 - processor, 131 - memory, 132 - bus, 133 - communication interface. DETAILED DESCRIPTION
[0053] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.
[0054] To facilitate understanding of this embodiment, the application scenarios and design concepts of the embodiments of the present application are briefly introduced below.
[0055] In the wetland sewage treatment process, the removal rate of sewage treated according to a unified treatment strategy does not meet the emission standards, and the sewage treatment efficiency needs to be improved.
[0056] Based on this, an embodiment of the present application provides a control method for a modular artificial wetland sewage system based on artificial intelligence.
[0057] Example 1
[0058] The present application provides a control method for a modular artificial wetland sewage system based on artificial intelligence. The method is applied to a control unit in the modular artificial wetland sewage system. The modular artificial wetland sewage system also includes a wetland sewage purification device. Figure 2 As shown, the device includes a plurality of parallel purification units 1 arranged perpendicular to the flow direction of sewage, one end of the purification unit 1 is connected to the sewage source via a water distribution pipe 6, and the other end of the purification unit 1 is connected to the purified water outlet via a water collecting pipe 7; water quality sensors 5 are provided at the outlet ends of the water distribution pipe 6 and the water collecting pipe 7; the water quality sensor 5 is communicatively connected to the control unit.
[0059] It is understandable that the number and length of the purification units 1 can be increased or decreased according to factors such as the terrain of the application scenario and the floor area. Two or more of the wetland sewage purification devices can also be assembled, such as in series, in parallel, or symmetrically arranged along both sides of the water collection pipe, and can be laid out according to usage requirements, which is not limited here.
[0060] Combination Figure 1 As shown, the method includes:
[0061] S110, obtaining a first water quality parameter of the outlet end of the water collecting pipe and a second water quality parameter of the water distribution pipe.
[0062] S120: Calculate the sewage treatment efficiency of the wetland sewage purification device according to the first water quality parameter and the second water quality parameter.
[0063] S130, determining whether the sewage treatment efficiency meets the preset purification index.
[0064] If not, execute steps S140-S160.
[0065] S140, obtaining the sewage removal rate of each purification unit in the wetland sewage purification device.
[0066] S150, inputting all sewage removal rates and preset purification indicators into a pre-trained learning model, and outputting a corresponding control strategy.
[0067] S160, based on the control strategy, controls the operation of the wetland sewage purification device.
[0068] In this embodiment, by obtaining the overall sewage treatment efficiency of the wetland sewage purification device including a plurality of parallel purification units 1, when it does not meet the preset purification index, the sewage removal rate of the plurality of parallel purification units 1 is obtained, and data analysis and processing are performed based on the pre-trained learning model combined with the sewage removal rate of each purification unit 1 and the preset purification index to output a control strategy, and the operation of the wetland sewage purification device is controlled according to this control strategy to improve the efficiency of the wetland sewage purification device.
[0069] Before actual application, the training process of the learning model is also included, specifically:
[0070] S010, obtaining a training sample set.
[0071] Specifically, each training sample in the training sample set can be obtained through preprocessing based on historical sewage treatment cases, or can be current or historical laboratory simulation data, or related data obtained from the Internet based on crawler technology. These training samples should at least contain water quality parameter information and purification index information corresponding to each sample data, where the water quality parameter information at least includes pH value, dissolved oxygen content, and chemical oxygen demand.
[0072] It is understandable that the training samples can also be associated with other information, such as sewage flow, pollutant concentration, sewage source pollution level, terrain information, geographical location information, etc. corresponding to the sample data, so as to facilitate the accuracy of the training model from different dimensions.
[0073] It is understandable that in order to improve the diversity and representativeness of the data and to achieve accurate specified control strategies through the trained model, the training sample set should cover most water quality conditions and treatment requirements. In addition, in order to enrich the training sample set, the data expansion method can be used to derive new sample data based on the characteristics of the existing sample data, and then merge the new sample data with the existing training sample data to expand the number of training samples in the training sample set.
[0074] S020, labeling each training sample in the training sample set.
[0075] Manually label the optimal control strategy corresponding to the training sample data.
[0076] S030, dividing the training sample set into a training set and a verification set, using the training set to train the initial model, and using the verification set to verify the recommended control strategy output by the initial model, so as to obtain a trained learning model that meets the expected requirements.
[0077] Among them, as an implementable method, the initial model uses a convolutional neural network (CNN), which is a feedforward neural network that includes convolution calculations and has a deep structure. It has representation learning capabilities and can perform translation-invariant classification of input information according to its hierarchical structure. In this embodiment, the convolutional neural network is a model constructed based on sewage treatment technical specifications, wetland sewage purification costs, and purification indicators. The artificial intelligence model is a convolutional neural network after multiple learning for a set number of times. The value of the set number of times is positively correlated with the sewage purification efficiency. In each learning of the convolutional neural network, the control strategy is used as the output of the neural network, and the sewage removal rate of each sewage treatment module calculated based on the water quality parameters is used as input to complete a single learning of the convolutional neural network. Convolutional neural networks are usually used to identify and classify images. By extracting the spatial features of the image, the prediction results are continuously convolved and pooled to output. In this application, the method of obtaining image information can be adopted to determine the water quality parameters by extracting the features of the image information, and then output the control strategy based on the water quality parameters and the target purification indicators through the data processing capability of the artificial intelligence model.
[0078] As another feasible approach, the initial model uses a long short-term memory (LSTM) recurrent neural network, which can overcome the gradient problem encountered in traditional recurrent neural network training, can selectively forget, save or read information, and has better performance when processing long sequences.
[0079] As another feasible method, the initial model adopts the recurrent neural network (RNN), which is a type of recursive neural network that takes sequence data as input, recursively in the direction of sequence evolution, and all nodes are connected in a chain. It can handle input sequences of different lengths and is better at handling speech recognition, modeling and prediction problems. In this way, managers can participate in and correct the model through voice questions and answers, voice target purification indicator input, etc., so as to output more accurate control strategies.
[0080] In this embodiment, the initial model integrates the deep learning artificial intelligence model and the model with the Transformer architecture as the core (such as the GPT model, the BERT model, the Transformer-XLmoxing, etc.). Based on the deep learning ability and combined with the reinforcement learning or meta-learning algorithm, the control strategy can be continuously optimized through the feedback data of the previous execution of the control strategy to improve the control accuracy and prediction ability; the model based on the Transformer architecture as the core can handle complex time series data and optimize the control method, so as to use the previous information to better process the information currently input by the customer. Relatively speaking, the model obtained by the training of the initial model has a higher prediction accuracy of water quality changes in the process of processing based on time series data, and then the control strategy for optimizing the sewage treatment process specified based on the predicted water quality changes is more reliable. In addition, the Transformer architecture can capture the global dependencies in the time series in reinforcement learning, and is not limited by the length of the sequence. By applying such a fusion model, it is possible to achieve efficient operation and accurate output control strategies in the ever-changing water quality conditions and operating environment.
[0081] It can be understood that if the judgment result of step S130 is yes, that is, it meets the preset purification index, the water quality parameter acquisition and monitoring can be continued.
[0082] In combination with the first aspect, step S110 includes:
[0083] S111, calculating the difference between the first water quality parameter and the second water quality parameter.
[0084] S112, calculating the ratio of the difference to the first water quality parameter to obtain the sewage treatment efficiency of the wetland sewage purification device.
[0085] By calculating the difference between the first water quality parameter and the second water quality parameter, the sewage removal amount is obtained, and then the sewage treatment efficiency of the wetland sewage purification device is calculated.
[0086] In combination with the first aspect, after step S120, the method further includes:
[0087] S121, for each purification unit, obtaining a third water quality parameter of a pipeline connecting the purification unit and the water collecting pipe, and calculating a sewage removal rate corresponding to the purification unit based on the third water quality parameter.
[0088] S122, defining the purification unit that meets the second preset target as the first target adjustment unit.
[0089] When the overall modular artificial wetland sewage system does not meet the sewage treatment efficiency, the third water quality parameters are obtained for the multiple purification units 1 connected in parallel in the modular artificial wetland sewage system to calculate the sewage removal rate, and the purification units 1 that meet the second preset target are selected, which are defined as the first target adjustment units. By adjusting these second target adjustment units to compensate for the overall sewage treatment effect of the modular artificial wetland sewage system, the overall sewage treatment efficiency is improved.
[0090] In combination with the first aspect, a first valve 8 is provided between each purification unit 1 and the water distribution pipe 6; the first valve 8 is connected to the control unit. The control unit can adjust the opening and closing angle of the first valve 8 to adjust the water flow into the purification unit 1.
[0091] In this embodiment, the control strategy includes the target opening and closing angle of the first valve corresponding to the first target adjustment unit. Step S160 includes:
[0092] S161, controlling the opening and closing angle of the first valve corresponding to the first target regulating unit to increase to the target opening and closing angle, so as to adjust the flow of the first target regulating unit entering the sewage source.
[0093] In this way, when the total sewage inflow is constant, the sewage inflow of the target regulating unit with better sewage effect efficiency is increased to reduce the water flow of other purification units with poor sewage treatment effect, thereby adjusting the overall sewage removal effect of the wetland sewage purification device. The specific target opening and closing angle of the first valve 8 is obtained through data analysis based on the learning model in the control unit, so that reasonable and accurate specific data can be obtained.
[0094] In combination with the first aspect, the purification unit 1 includes a plurality of sub-purification units 2 connected in series in the sewage flow direction (combined Figure 1 As shown); a second valve (not shown in the figure) is provided on the connecting pipeline between two adjacent sub-purification units 2; the second valve is connected to the control unit; the packing information in each sub-purification unit 2 is pre-stored in the control unit.
[0095] It is understandable that the length of the purification unit can be changed by increasing or decreasing the number of sub-purification units 2 according to different actual application situations. In this way, different application requirements can be used in a modular form, and the sub-purification unit 2 with a smaller area has low production difficulty, low transportation and storage costs, is easy to assemble, and has a flexible and changeable structure compared to the traditional method of customizing a large-area wetland sewage purification device.
[0096] In this embodiment, the control strategy further includes: determining a first number of target sub-purification units according to the descending order of sewage treatment effects of the fillers, and a target opening and closing angle of the second valve corresponding to each target sub-purification unit.
[0097] Step S160 includes:
[0098] S162: For each target sub-purification unit, control the opening and closing angle of the target second valve corresponding to the target sub-purification unit to increase to a target opening and closing angle.
[0099] In this way, without changing the flow rate entering the purification unit, by increasing the opening and closing angle of the target second valve, more sewage can be introduced into the sub-purification unit 2 filled with better removal efficiency, thereby increasing the time the sewage stays in the sub-purification unit 2, so that more sewage can be purified under the purification effect of the filler, thereby improving the overall sewage treatment efficiency of the purification unit; and further, when the treatment efficiency of multiple purification units is improved, the overall sewage treatment efficiency of the wetland sewage purification device can be improved.
[0100] In combination with the first aspect, the control unit also stores the serial number of each sub-purification unit 2; the control strategy also includes: the filler addition amount corresponding to each target sub-purification unit.
[0101] Step S160 also includes:
[0102] S163, returning the serial number corresponding to the target sub-purification unit and the filler addition amount corresponding to the target sub-purification unit.
[0103] Similarly, when the amount of sewage entering the purification unit 1 does not change, the sewage treatment effect can be improved by adding fillers with good sewage treatment effects. The data analysis capability of the learning model pre-trained in the control unit is used to obtain the amount of filler added in the target sub-purification unit, thereby improving the sewage treatment efficiency of the sub-purification unit, and further improving the sewage treatment efficiency of the purification unit and the overall wetland sewage purification device.
[0104] In combination with the first aspect, the purification unit 1 also includes a return pipe 4, the inlet end of the return pipe 4 is connected to the first sub-purification unit, and the outlet end of the return pipe 4 is connected to all the second sub-purification units located at the front end of the first sub-purification unit (the front end along the sewage flow direction); a return valve 3 is provided on the return pipe 4 near the inlet end.
[0105] The control strategy also includes: a target opening and closing angle of the reflux valve 3 .
[0106] Step S160 also includes:
[0107] S164, controlling the reflux valve to increase the opening and closing angle to the target opening and closing angle.
[0108] As another feasible method, the water flow rate returning to the front sub-purification unit 2 can be increased to increase the residence time of the sewage in the front sub-purification unit 2 for further purification, thereby improving the sewage treatment efficiency of the purification unit 1.
[0109] In summary, when the sewage treatment effect of the overall wetland sewage purification device cannot meet the preset purification indicators, the data analysis and processing capabilities of the learning model pre-trained in the control unit can be used to output appropriate control strategies and control the operation of the wetland sewage purification device, thereby adjusting the distribution flow or reflux flow or filler content entering each purification unit 1 and sub-purification unit 2, thereby improving the sewage treatment effect of the wetland sewage purification device.
[0110] It can be understood that as an implementable method, the input of the initial model can have multiple input channels, each input channel can correspond to an output channel, so as to train the model from different management dimensions and output control strategies that meet different management needs from different output channels. In the actual application of sewage treatment control process, management needs can also include: cost, energy consumption, environmental impact and other multiple goals, for example, greenhouse gas emission reduction effect, investment cost, operating cost, etc., by inputting different training data to train the initial model, and output the control strategy in the corresponding output channel.
[0111] As another feasible method, the input of the initial model can have multiple input channels and only one output channel, so as to output control strategies of multiple different management dimensions, and then combine these multiple control strategies to output the final control strategy convolution and pooling.
[0112] For example, water quality parameters also include the conductivity corresponding to each purification unit 1. The level of conductivity is closely related to the type, quantity and temperature of ions in the water. The conductivity of industrial wastewater or polluted water may increase due to the presence of a large amount of dissolved matter. The conductivity of each purification unit 1 is used as a training sample to train the initial model so as to output a control strategy that meets the anti-blocking requirements from the corresponding output channel.
[0113] It can be understood that an aerator can be added at the end of the sub-purification unit 2 connected in series in the purification unit 1, and the sewage treatment efficiency can be further improved by turning on the aerator. The aerator can be turned on or off and the specific opening time can be controlled by the control unit to achieve regulation under different situations.
[0114] In combination with the first aspect, the control unit is further connected to a human-computer interaction interface, and a designated key connection is provided on the human-computer interaction interface; the method further includes:
[0115] In response to a user's touch or press operation on a designated key, the first water quality parameter, the second water quality parameter, the preset purification index and the control strategy are displayed on the human-computer interaction interface.
[0116] In this embodiment, the user (management personnel, designers, etc.) touches or presses a designated key to send an information acquisition request to the control unit through the human-computer interaction interface, and the control unit feeds back and displays various information corresponding to the request on the human-computer interaction interface. The various information corresponding to the request includes but is not limited to the first water quality parameter, the second water quality parameter, the preset purification index and the output control strategy. It can be understood that it can also include: current time information, wetland location information, terrain information, and the preferred control strategy corresponding to the terrain information.
[0117] In combination with the first aspect, the method further includes:
[0118] In response to a user's adjustment operation on a preset purification index, updating the preset purification index according to the adjusted purification index;
[0119] The preset purification indicators are input into the pre-trained learning model and the current control strategy is output.
[0120] It is understandable that the preset purification index can be set and modified according to the actual purification needs. In the actual application process, the user adjusts the preset purification index through the human-computer interaction interface, and inputs the adjusted preset purification index into the pre-trained learning model, so that the model can perform data analysis and processing based on the obtained sewage treatment efficiency of the wetland sewage purification device, the sewage removal rate of each purification unit 1 and the new preset purification index, so as to output a new control strategy, namely the current control strategy. In this way, the adaptability to various application scenarios can be improved.
[0121] In combination with the first aspect, it also includes an artificial intelligence voice interaction model, and the output end of the artificial intelligence voice interaction model is connected to the input end of the pre-trained learning model; the method also includes:
[0122] Receive user's voice command information;
[0123] Input voice command information into the artificial intelligence voice interaction model, output at least one voice recognition result and display it on the human-computer interaction interface;
[0124] In response to the user's touch or selection operation on the target speech recognition result, the speech recognition result is input into the pre-trained learning model, and the target control strategy is output and fed back to the human-computer interaction interface.
[0125] In this embodiment, the artificial intelligence voice interaction model adopts the GPT model with the Transformer architecture as the core. Compared with the traditional GNN, it can better process long sequences and realize efficient parallel computing, thereby improving the efficiency and performance of the model. It understands the context of the input text through the self-attention mechanism, which is suitable for language translation, question answering, text summarization and other scenarios. Furthermore, the ChatGPT model obtained by the improved version of the GPT model can also be used. Through the training of conversational interaction tasks, a ChatGPT model that can better understand and process dialogue characters with people can be obtained.
[0126] Due to the use of the ChatGPT model, based on the natural language processing capabilities of the model, the user's voice command information can be recognized, and according to the recognized voice recognition results, various data information can be adjusted, and based on the adjusted data information, the pre-trained learning model can be driven to perform data processing to feedback the target control strategy corresponding to the voice command information.
[0127] For example, the voice command information is "optimize the overall sewage removal rate", and the actual command obtained by the ChatGPT model after recognizing the voice command information is "increase the preset purification index". The ChatGPT model can feedback one or more optimization schemes to the human-computer interaction interface (for example: increase the preset purification index to A, increase the preset purification index to B, increase the preset purification index to C, where A<B<C). After the user selects one of the optimization schemes by touching or clicking, the optimization scheme selected by the user is determined as the final voice recognition result. At this time, the preset purification index is updated and the target control strategy is formulated based on the data computing and processing capabilities of the learning model and fed back to the human-computer interaction interface.
[0128] It is understandable that the above-mentioned artificial intelligence voice interaction model can also be used for dialogue question and answer, fault diagnosis, operation suggestions, visual remote control of system operation status, etc. The artificial intelligence voice interaction model can also be ChatGPT-4o, Doubao, Kimi, Tencent Yuanbao, Tongyi Qianwen, Wenxin Yiyan, iFlytek Spark and Zhipu Qingyan, etc., which can be selected according to actual needs and are not limited here. Based on the information input by the user's voice or text, combined with the pre-stored or networked knowledge base, various parameters and indicators in the system operation, the reply text related to the user's input command is generated and output to assist the user in remote control of the system operation status.
[0129] It is understandable that in this application, the wetland sewage treatment system can also be divided into multiple units, each unit is used to perform a specific function, and the efficient management of sewage treatment efficiency is achieved through the collaborative work between the various units. For example, the water quality detection and water flow detection of each sewage treatment unit are performed by the detection unit. And in order to improve the remote monitoring and management capabilities, a communication connection is established between each unit and the remote monitoring unit to facilitate the maintenance, upgrade and expansion of the system. This is a relatively common application technical means and will not be elaborated here.
[0130] Combination Figure 3 As shown, the device includes: a first acquisition module 10, a calculation module 20, a judgment module 30, a second acquisition module 40, an output module 50 and a control module 60.
[0131] The first acquisition module 10 is used to acquire a first water quality parameter of the outlet end of the water collecting pipe and a second water quality parameter of the water distribution pipe.
[0132] The calculation module 20 is used to calculate the sewage treatment efficiency of the wetland sewage purification device according to the first water quality parameter and the second water quality parameter.
[0133] The determination module 30 is used to determine whether the sewage treatment efficiency meets the preset purification index.
[0134] The second acquisition module 40 is used to acquire the sewage removal rate of each purification unit in the wetland sewage purification device when the sewage treatment efficiency does not meet the preset purification index.
[0135] The output module 50 is used to input all sewage removal rates and preset purification indicators into a pre-trained learning model and output a corresponding control strategy.
[0136] The control module 60 is used to control the operation of the wetland sewage purification device based on the control strategy.
[0137] In a third aspect, the present application provides an electronic device, Figure 4 As shown, the electronic device includes a memory 131 and a processor 130. The memory 131 is used to store computer programs, and the processor 130 runs the computer programs to enable the electronic device to perform the above method.
[0138] Furthermore, combined with Figure 4 The electronic device shown further includes a bus 132 and a communication interface 133 , and the processor 130 , the communication interface 133 and the memory 131 are connected via the bus 132 .
[0139] The memory 131 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk storage. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 133 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used. The bus 132 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.
[0140] The processor 130 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 130. The above processor 130 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present invention can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiment of the present invention can be directly embodied as a hardware decoding processor for execution, or a combination of hardware and software modules in the decoding processor for execution. The software module may be located in a storage medium mature in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 131, and the processor 130 reads the information in the memory 131 and completes the steps of the method of the above embodiment in combination with its hardware.
[0141] In a fourth aspect, an embodiment of the present application provides a readable storage medium, in which computer program instructions are stored. When the computer program instructions are read and executed by a processor, the above method is executed.
[0142] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system and device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.
[0143] In addition, in the description of the embodiments of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, and it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.
[0144] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.
[0145] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.
[0146] Finally, it should be noted that the above embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above embodiments, those skilled in the art should understand that any person skilled in the art can still modify the technical solutions recorded in the above embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.
Claims
1. A control method for a modular artificial wetland sewage system based on artificial intelligence, It is characterized in that The method is applied to a control unit in a modular artificial wetland sewage system, wherein the modular artificial wetland sewage system also includes a wetland sewage purification device, which includes a plurality of parallel purification units perpendicular to the sewage flow direction, one end of the purification unit is connected to a sewage source through a water distribution pipe, and the other end of the purification unit is connected to a purified water outlet through a water collecting pipe; water quality sensors are provided at the outlet ends of the water distribution pipe and the water collecting pipe; the water quality sensor is communicatively connected with the control unit; the purification unit also includes a reflux pipe, the inlet end of the reflux pipe is connected to a first sub-purification unit, and the outlet end of the reflux pipe is connected to all second sub-purification units located at the front end of the first sub-purification unit; a reflux valve is provided on the reflux pipe near the inlet end; The method comprises: Acquire a first water quality parameter of the outlet end of the water collecting pipe and a second water quality parameter of the water distribution pipe; Calculating the sewage treatment efficiency of the wetland sewage purification device according to the first water quality parameter and the second water quality parameter; Determining whether the sewage treatment efficiency meets the preset purification index; If not, for each of the purification units, obtain a third water quality parameter of the pipeline connecting the purification unit and the water collecting pipe, and calculate the sewage removal rate corresponding to the purification unit based on the third water quality parameter; The total sewage removal rate and the preset purification index are input into the pre-trained learning model, and the corresponding control strategy is output; wherein the control strategy includes: the target opening and closing angle of the return valve; Based on the control strategy, each of the return valves in the wetland sewage purification device is controlled to rotate to a corresponding target opening and closing angle.
2. The method according to claim 1, It is characterized in that The step of calculating the sewage treatment efficiency of the wetland sewage purification device according to the water quality parameter and the second water quality parameter of the sewage source comprises: Calculating a difference between a first water quality parameter and the second water quality parameter; The ratio of the difference to the first water quality parameter is calculated to obtain the sewage treatment efficiency of the wetland sewage purification device.
3. The method according to claim 1, It is characterized in that A first valve is provided between each of the purification units and the water distribution pipe; the first valve is connected to the control unit; the control strategy includes a target opening and closing angle of the valve corresponding to the first target adjustment unit; Based on the control strategy, the step of controlling each of the return valves in the wetland sewage purification device to rotate to a corresponding target opening and closing angle includes: defining the purification unit that meets the second preset target as the first target adjustment unit; The opening and closing angle of the first valve corresponding to the first target regulating unit is controlled to increase to a target opening and closing angle, so as to adjust the flow rate of the first target regulating unit entering the sewage source.
4. The method according to claim 1, It is characterized in that The purification unit includes a plurality of sub-purification units connected in series in the direction of sewage flow; a second valve is provided on the connecting pipe between two adjacent sub-purification units; the second valve is connected to the control unit; the control strategy also includes: determining a first number of target sub-purification units according to the descending order of the sewage treatment effect of the filler, and a target opening and closing angle of the second valve corresponding to each target sub-purification unit; Based on the control strategy, the step of controlling each of the return valves in the wetland sewage purification device to rotate to a corresponding target opening and closing angle includes: For each of the target sub-purification units, the opening and closing angle of the target second valve corresponding to the target sub-purification unit is controlled to increase to a target opening and closing angle.
5. The method according to claim 4, It is characterized in that The control unit also stores the serial number of each sub-purification unit; the control strategy also includes: the amount of filler added corresponding to each target sub-purification unit; Based on the control strategy, the steps of controlling the operation of the wetland sewage purification device include: Return the serial number corresponding to the target sub-purification unit and the filler addition amount corresponding to the target sub-purification unit.
6. The method according to claim 1, It is characterized in that The control unit is also connected to a human-machine interaction interface, and a designated key connection is provided on the human-machine interaction interface; The method comprises: In response to a user's touch or press operation on a designated key, the first water quality parameter, the second parameter, the preset purification index and the control strategy are displayed on the human-computer interaction interface.
7. The method according to claim 6, It is characterized in that The method further comprises: In response to a user's adjustment operation on the preset purification index, updating the preset purification index according to the adjusted purification index; The preset purification index is input into the pre-trained learning model, and the current control strategy is output.
8. The method according to claim 6, It is characterized in that It also includes an artificial intelligence voice interaction model, wherein the output end of the artificial intelligence voice interaction model is connected to the input end of the pre-trained learning model; the method also includes: Receive user's voice command information; Input the voice command information into the artificial intelligence voice interaction model, output at least one voice recognition result and display it on the human-computer interaction interface; In response to a user's touch or selection operation on a target speech recognition result, the speech recognition result is input into the pre-trained learning model, and a target control strategy is output and fed back to the human-computer interaction interface.
