Sewage treatment equipment operation management system and method thereof

Abstract

The invention discloses a sewage treatment equipment operation management system and method, and relates to the technical field of sewage equipment management. The system comprises an equipment monitoring module for regularly monitoring sewage treatment equipment to obtain monitoring data; the processing and analyzing module is used for processing and analyzing the monitoring data to obtain an analysis result; the operation control module is used for generating a control decision according to an analysis result and performing operation control on the sewage treatment equipment according to the control decision; and the maintenance management module is used for regularly maintaining the sewage treatment equipment according to an analysis result and carrying out emergency treatment on emergencies. Through the synergistic effect of the modules, analysis is carried out according to monitored data, and operation and management of the sewage treatment equipment are adjusted and optimized according to an analysis result, so that the operation efficiency of the sewage treatment equipment is improved, the automation and intelligence level of sewage treatment is improved, and the sewage treatment efficiency is improved. And the operation cost is reduced through scientific decisions while the human input is reduced, so that the economic benefits are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of sewage equipment management, and in particular relates to a sewage treatment equipment operation management system and method thereof. Background Art

[0002] Sewage treatment equipment refers to machinery and equipment used to treat and purify sewage to meet environmental emission standards. Most of these equipment are used in urban sewage treatment, industrial wastewater treatment, agricultural sewage treatment and other fields. The operation and management of sewage treatment equipment is an important link to ensure the sewage treatment effect and stable operation of equipment. However, in actual operation, the following problems are often encountered: incomplete data monitoring and collection, insufficient automation control, lagging equipment maintenance and management, insufficient energy consumption control, and insufficient emergency management capabilities. Therefore, effective management of the operation of sewage treatment equipment in response to the above problems has become an urgent problem to be solved. Summary of the invention

[0003] The object of the present invention is to provide a sewage treatment equipment operation management system and method thereof, which can be achieved through the following technical solutions:

[0004] In a first aspect, an embodiment of the present application provides a sewage treatment equipment operation management system, including:

[0005] Equipment monitoring module, used to regularly monitor sewage treatment equipment to obtain monitoring data;

[0006] A processing and analysis module, used for processing and analyzing the monitoring data to obtain analysis results;

[0007] An operation control module, used to generate a control decision based on the analysis result and thereby perform operation control on the sewage treatment equipment;

[0008] A maintenance management module is used to perform regular maintenance on the sewage treatment equipment according to the analysis results; and is also used to handle emergency events;

[0009] The monitoring data includes historical monitoring data and real-time monitoring data.

[0010] Preferably, the equipment monitoring module includes a data acquisition unit, a data classification unit and a data storage unit;

[0011] The data collection unit is used to collect monitoring data of the sewage treatment equipment at multiple predetermined time points within a predetermined time period;

[0012] The data classification unit uses the current time point as a time boundary to classify the monitoring data before the current time point into historical monitoring data, and classifies the monitoring data at the current time point into real-time monitoring data;

[0013] The data storage unit uses a dual ring buffer for data storage, specifically: using a first ring buffer to store historical monitoring data, and using a second ring buffer to store real-time monitoring data.

[0014] Preferably, the processing and analysis module includes a data processing unit, a type classification unit, a model building unit, an anomaly identification unit and an anomaly analysis unit;

[0015] The data processing unit is used to perform data preprocessing and data enhancement on the monitoring data;

[0016] The type classification unit is used to classify the processed historical monitoring data into equipment water quality data and equipment operation data;

[0017] The model building unit builds a water quality anomaly recognition model based on the equipment water quality data; and builds an operation anomaly recognition model based on the equipment operation data;

[0018] The abnormality identification unit performs abnormality identification on the processed real-time monitoring data based on the water quality abnormality identification model and the operation abnormality identification model, and generates a first identification result and a second identification result respectively;

[0019] The abnormality analysis unit performs an abnormality analysis on the equipment water quality data based on the first recognition result to generate a first analysis result; and performs an abnormality analysis on the equipment operation data based on the second recognition result to generate a second analysis result.

[0020] Preferably, the data preprocessing includes data cleaning, data conversion, data integration and time series processing.

[0021] Preferably, the equipment water quality data includes water quality parameters of equipment inlet water and water quality parameters of equipment outlet water; the equipment operation data includes equipment operation status, equipment operation parameters and operation energy consumption data.

[0022] Preferably, constructing the operation abnormality identification model includes the following contents:

[0023] Arranging the equipment operation data according to the time dimension into an operation data time series matrix of the sewage treatment equipment;

[0024] A time series correlation feature extractor based on a deep neural network model performs feature extraction on the operation data time series matrix to obtain an operation time series feature graph;

[0025] Performing feature association enhancement processing on the running time feature graph to obtain enhanced running time features;

[0026] An operation anomaly recognition model is established based on the enhanced operation timing characteristics.

[0027] Preferably, obtaining the enhanced running timing characteristics includes the following contents:

[0028] Passing the runtime feature graph through a channel attention module to obtain a channel explicit runtime feature graph;

[0029] Passing the channel explicit runtime feature map through a first convolutional layer of the deep neural network model to obtain a first feature map, and passing the first feature map through a second convolutional layer to obtain a second feature map;

[0030] Expanding each feature matrix of the second feature map along the channel dimension into feature vectors to obtain a sequence of first feature vectors, and calculating the cosine similarity between any two first feature vectors in the sequence of the first feature vectors to obtain a cosine similarity feature map;

[0031] Normalizing the cosine similarity feature map to obtain a normalized cosine similarity feature map and multiplying the normalized cosine similarity feature map by position points with the cosine similarity feature map to obtain a similarity mapping optimization feature map;

[0032] Passing the similarity map optimization feature map through a first deconvolution layer of the deep neural network model to obtain a first deconvolution feature map, and calculating an element-by-element sum of the first deconvolution feature map and the first feature map to obtain a first fused feature map;

[0033] Passing the first fused feature map through a second deconvolution layer of the deep neural network model to obtain a second deconvolution feature map, and calculating an element-by-element sum of the second deconvolution feature map and the channel-manifested runtime feature map to obtain a re-enhanced runtime feature map;

[0034] The enhanced operation timing characteristics are extracted from the re-enhanced operation timing characteristics graph.

[0035] Preferably, the water quality abnormality identification model is constructed, including the following contents:

[0036] Performing correlation analysis and dimensionality reduction processing on the water quality data of the equipment to select abnormal water quality features;

[0037] Inputting the abnormal water quality features into a convolutional neural network model to construct a feature space;

[0038] In the feature space, a long short-term memory neural network model is used to express the equipment water quality time series characteristics of the equipment water quality data;

[0039] A training data set and a test data set are established based on the water quality time series characteristics of the equipment, and a water quality anomaly recognition model is generated based on them.

[0040] Preferably, the operation of the sewage treatment equipment is controlled, including: controlling the operating power of the sewage treatment equipment, controlling the water flow in and out of the equipment, controlling the dissolved oxygen of the equipment, controlling the sludge return, adjusting water quality parameters when the water quality changes, selecting and switching the equipment operating status, and controlling the switch start and stop status and operating time of the corresponding control equipment through current signals.

[0041] In a second aspect, an embodiment of the present application provides a method for managing the operation of a sewage treatment equipment, which is applied to the sewage treatment equipment operation management system as described above, and includes the following steps:

[0042] Regularly monitor sewage treatment equipment to obtain monitoring data;

[0043] Processing and analyzing the monitoring data to obtain analysis results;

[0044] Generate a control decision based on the analysis result and use it to control the operation of the sewage treatment equipment;

[0045] The sewage treatment equipment is regularly maintained according to the analysis results; it is also used for emergency response to emergencies;

[0046] The monitoring data includes historical monitoring data and real-time monitoring data.

[0047] The beneficial effects of the present invention are as follows: the present invention first regularly monitors the sewage treatment equipment through the equipment monitoring module to obtain monitoring data; then processes and analyzes the monitoring data through the processing and analysis module to obtain analysis results; then generates control decisions based on the analysis results in the operation control module and uses them to control the operation of the sewage treatment equipment; finally, the maintenance management module regularly maintains the sewage treatment equipment based on the analysis results, and also handles emergencies. The present invention uses the synergy between the above-mentioned system modules to analyze the data monitored in real time, and adjusts and optimizes the operation and management of the sewage treatment equipment based on the analysis results, so as to improve the operating efficiency of the sewage treatment equipment, as well as the automation and intelligence level of sewage treatment, reduce manpower input, and reduce operating costs through scientific decision-making to improve economic benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] For better understanding and implementation, the technical solution of the present application is described in detail below with reference to the accompanying drawings.

[0049] Figure 1 A schematic diagram of the structure of a sewage treatment equipment operation management system provided in an embodiment of the present application;

[0050] Figure 2 A schematic diagram of the structure of the equipment monitoring module provided in the embodiment of the present application;

[0051] Figure 3 A flowchart of the steps for constructing an operation abnormality identification model provided in an embodiment of the present application;

[0052] Figure 4 A flowchart of the steps for constructing a water quality anomaly identification model provided in an embodiment of the present application;

[0053] Figure 5 A flowchart of the steps of a sewage treatment equipment operation management method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0054] In order to further explain the technical means and effects taken by the present invention to achieve the predetermined invention purpose, exemplary embodiments will be described in detail here, and examples thereof are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are only examples of methods and systems consistent with some aspects of the present application as detailed in the attached claims.

[0055] The terms used in this application are only for the purpose of describing specific embodiments and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in this article refers to any or all possible combinations of one or more associated listed items.

[0056] The specific implementation methods, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0057] Example 1

[0058] See also Figure 1 The present application embodiment provides a sewage treatment equipment operation management system, including:

[0059] Equipment monitoring module, used to regularly monitor sewage treatment equipment to obtain monitoring data;

[0060] A processing and analysis module, used for processing and analyzing the monitoring data to obtain analysis results;

[0061] An operation control module, used to generate a control decision based on the analysis result and thereby perform operation control on the sewage treatment equipment;

[0062] A maintenance management module is used to perform regular maintenance on the sewage treatment equipment according to the analysis results; and is also used to handle emergency events;

[0063] The monitoring data includes historical monitoring data and real-time monitoring data.

[0064] Specifically, since the operation and management of sewage treatment equipment is an important link to ensure the sewage treatment effect and stable operation of the equipment, the existing technology will face problems such as incomplete data monitoring and collection, insufficient automation control, delayed equipment maintenance and management, insufficient energy consumption control, and insufficient emergency management capabilities. Therefore, in order to improve the operating efficiency of sewage treatment equipment, reduce energy consumption and maintenance costs, this application improves the operation and management of sewage treatment equipment, specifically: first, the sewage treatment equipment is regularly monitored by the equipment monitoring module to obtain monitoring data; then the monitoring data is processed and analyzed by the processing and analysis module to obtain the analysis results; then, the control decision is generated in the operation control module based on the analysis results and the operation and control of the sewage treatment equipment is performed accordingly; finally, the sewage treatment equipment is regularly maintained by the maintenance management module based on the analysis results, and emergency treatment is also performed for emergency events. This application analyzes the data monitored in real time through the synergy between the above-mentioned system modules, and adjusts and optimizes the operation and management of the sewage treatment equipment based on the analysis results, so as to improve the operating efficiency of the sewage treatment equipment, and improve the automation and intelligence level of sewage treatment, reduce manpower input, and reduce operating costs through scientific decision-making to improve economic benefits.

[0065] like Figure 2 As shown, in one embodiment provided in the present application, the equipment monitoring module includes a data acquisition unit, a data classification unit and a data storage unit;

[0066] The data collection unit is used to collect monitoring data of the sewage treatment equipment at multiple predetermined time points within a predetermined time period;

[0067] The data classification unit uses the current time point as a time boundary to classify the monitoring data before the current time point into historical monitoring data, and classifies the monitoring data at the current time point into real-time monitoring data;

[0068] The data storage unit uses a dual ring buffer for data storage, specifically: using a first ring buffer to store historical monitoring data, and using a second ring buffer to store real-time monitoring data.

[0069] Specifically, the equipment monitoring module of this embodiment is mainly used to monitor the equipment in real time and collect equipment-related data. When collecting data, the module will set multiple predetermined time periods and collect data at multiple predetermined time points within the predetermined time periods. This can reflect the data changes of the sewage treatment equipment under different time series changes; and the collected data is divided into historical data and real-time data with the current time point as the dividing point, and stored in different circular buffers respectively.

[0070] It should be noted that this embodiment stores historical monitoring data and real-time monitoring data in different circular buffers respectively, which can achieve efficient data storage and reading; among them, the first circular buffer is used to store data that has been processed or no longer needs to be updated in real time (i.e., historical monitoring data); the second circular buffer is used to store data currently being processed for quick access and real-time processing.

[0071] Regarding the storage of historical monitoring data (first ring buffer), its storage strategy includes:

[0072] Sequential writing: When new data arrives, it is written sequentially to the first ring buffer and the oldest data is overwritten after it reaches a certain size. This ensures the integrity of historical data while maintaining a certain amount of storage space.

[0073] Snapshot preservation: A snapshot of real-time data can be written to the first ring buffer in each time period (eg, every minute, every hour) or when a specific event occurs (eg, a sudden failure of a sewage treatment device) to preserve the state at a specific moment.

[0074] Access method: Data is usually sorted by timestamp, and users can access data for a specific time period on demand; interfaces are provided for querying, statistics, and analysis of historical data.

[0075] Regarding the storage of real-time monitoring data (second ring buffer), its storage strategy includes:

[0076] Real-time writing: Newly arrived data is immediately written to the second ring buffer to ensure fast processing.

[0077] Ring overwrite: If the second ring buffer is full, the new data will overwrite the oldest data to ensure the latest real-time data.

[0078] Access method: Design fast access interfaces for real-time processing (such as reading the latest data for analysis or display); support asynchronous reading to ensure that read operations do not block write operations.

[0079] This embodiment uses a dual-ring buffer to store historical monitoring data and real-time monitoring data, which is an efficient solution. Through reasonable design and management, parallel processing and storage of two types of data can be achieved. Such a structure can not only ensure fast access to real-time data, but also effectively save historical data for subsequent analysis.

[0080] In an embodiment provided in the present application, the processing and analysis module includes a data processing unit, a type classification unit, a model building unit, an anomaly identification unit and an anomaly analysis unit;

[0081] The data processing unit is used to perform data preprocessing and data enhancement on the monitoring data;

[0082] The type classification unit is used to classify the processed historical monitoring data into equipment water quality data and equipment operation data;

[0083] The model building unit builds a water quality anomaly recognition model based on the equipment water quality data; and builds an operation anomaly recognition model based on the equipment operation data;

[0084] The abnormality identification unit performs abnormality identification on the processed real-time monitoring data based on the water quality abnormality identification model and the operation abnormality identification model, and generates a first identification result and a second identification result respectively;

[0085] The abnormality analysis unit performs an abnormality analysis on the equipment water quality data based on the first recognition result to generate a first analysis result; and performs an abnormality analysis on the equipment operation data based on the second recognition result to generate a second analysis result.

[0086] Specifically, this embodiment divides the processed data into two categories, and establishes two models, namely, a water quality anomaly identification model and an operation anomaly identification model, based on the two categories of data respectively. Then, based on the two types of models, the acquired real-time monitoring data is input into them, thereby obtaining the first identification result and the second identification result output by the two models; then, an anomaly analysis is performed based on the identification results, and the analysis results of the real-time monitoring data are obtained to determine whether the sewage treatment equipment has an abnormality, where the abnormality is located, whether it is an equipment operation failure or an equipment water quality abnormality, and the judgment result is provided to the subsequent maintenance management module for maintenance and processing.

[0087] It should be noted that the two models of this embodiment are constructed based on historical monitoring data, while the abnormality identification is performed based on real-time monitoring data. The above historical monitoring data and real-time monitoring data are only different in time series (the time of collection is different, and there is a difference in order), and there is no difference in essence (both can be used to reflect the status of sewage treatment equipment). In other words, the two models established based on historical monitoring data will not affect the identification and detection of real-time monitoring data by the two models.

[0088] In an embodiment provided in the present application, the data preprocessing includes data cleaning, data conversion, data integration and time series processing.

[0089] Specifically, in order to improve data quality and analysis results, the present embodiment performs the following preprocessing on the monitoring data: Data cleaning: Missing value processing: Identify missing values ​​in the data set and fill, delete or retain them; common filling methods include mean filling, median filling or interpolation; Duplicate data removal: Identify and delete duplicate data to ensure that each data is unique; Outlier detection: Identify and process outliers in the data; Data conversion: Standardization: Scale the data to a specific range (such as 0 to 1) or convert it to a standard normal distribution; Normalization: Transform the data linearly so that the features have similar scales; Discretization: Convert continuous data into discrete categories, for example, divide the numerical range into multiple categories (such as low, medium, and high); Data integration: Data merging: Merge data from different sources into a unified data set; Data conversion: Convert data in different formats to ensure data consistency; Time series processing: Timestamp processing: If the data contains timestamps, it needs to be converted to a suitable format, and features such as date, hour, and minute may need to be extracted; Smoothing: For time series data, use methods such as moving average to smooth the data and remove noise. This embodiment significantly improves the accuracy and robustness of the model through preprocessing.

[0090] It is understandable that data augmentation can improve the generalization ability of the model: by increasing the diversity of data, the model can better adapt to unseen data; reduce the risk of overfitting: increasing the amount of training data can reduce the overfitting of the model to specific samples; save data collection costs: when data collection is difficult or costly, augmentation technology can effectively increase the sample size.

[0091] In an embodiment provided in the present application, the equipment water quality data includes water quality parameters of the equipment inlet water and water quality parameters of the equipment outlet water; the equipment operation data includes equipment operation status, equipment operation parameters and operation energy consumption data.

[0092] Specifically, the water quality parameters of the equipment's inlet and outlet water include water quality monitoring index data for inlet and outlet water; the water quality monitoring indicators are one or more of pH value, chemical oxygen demand, suspended solids, ammonia nitrogen, total phosphorus, fecal coliform group, total nitrogen, animal and vegetable oil, conductivity and turbidity; and also include sludge parameters: sludge concentration: reflects the content of sludge in water, affecting sedimentation and dehydration effects; sludge sedimentation: refers to the sedimentation speed and effect of sludge in the sedimentation tank; sludge age: the average residence time of sludge in the system, affecting the activity and treatment effect of microorganisms, as well as disinfectant concentration and chemical additive parameters; the equipment operating status includes: the current status and remote control status of the working pump, the current status and remote control status of the emergency pump, the current status and remote control status of the fan, equipment operating time, equipment downtime, equipment load; the equipment operating energy consumption data includes: current, power, and electric energy of the pump and fan; the equipment operating parameters include inlet and outlet water flow, inlet and outlet water temperature, inlet and outlet water pressure, flow rate, etc.

[0093] like Figure 3 As shown, in one embodiment provided in the present application, constructing the operation abnormality identification model includes the following contents:

[0094] Arranging the equipment operation data according to the time dimension into an operation data time series matrix of the sewage treatment equipment;

[0095] A time series correlation feature extractor based on a deep neural network model performs feature extraction on the operation data time series matrix to obtain an operation time series feature graph;

[0096] Performing feature association enhancement processing on the running time feature graph to obtain enhanced running time features;

[0097] An operation anomaly recognition model is established based on the enhanced operation timing characteristics.

[0098] In an embodiment provided in the present application, obtaining the enhanced running timing characteristics includes the following contents:

[0099] Passing the runtime feature graph through a channel attention module to obtain a channel explicit runtime feature graph;

[0100] Passing the channel explicit runtime feature map through a first convolutional layer of the deep neural network model to obtain a first feature map, and passing the first feature map through a second convolutional layer to obtain a second feature map;

[0101] Expanding each feature matrix of the second feature map along the channel dimension into feature vectors to obtain a sequence of first feature vectors, and calculating the cosine similarity between any two first feature vectors in the sequence of the first feature vectors to obtain a cosine similarity feature map;

[0102] Normalizing the cosine similarity feature map to obtain a normalized cosine similarity feature map and multiplying the normalized cosine similarity feature map by position points with the cosine similarity feature map to obtain a similarity mapping optimization feature map;

[0103] Passing the similarity map optimization feature map through a first deconvolution layer of the deep neural network model to obtain a first deconvolution feature map, and calculating an element-by-element sum of the first deconvolution feature map and the first feature map to obtain a first fused feature map;

[0104] Passing the first fused feature map through a second deconvolution layer of the deep neural network model to obtain a second deconvolution feature map, and calculating an element-by-element sum of the second deconvolution feature map and the channel-manifested runtime feature map to obtain a re-enhanced runtime feature map;

[0105] The enhanced operation timing characteristics are extracted from the re-enhanced operation timing characteristics graph.

[0106] Specifically, this embodiment uses the above steps and contents to pass the operation timing characteristic diagram of the sewage treatment equipment through the channel attention module to obtain a channel-manifested operation timing characteristic diagram. The channel-manifested operation timing characteristic diagram can further highlight the key information in the operation of the equipment, so that the operation of the equipment can be more intuitively observed and analyzed, which helps to improve the system's understanding and judgment of the equipment's operating status, thereby facilitating the rapid identification of the equipment's operating mode, key features and abnormal behavior.

[0107] like Figure 4 As shown, in one embodiment provided in the present application, the water quality abnormality recognition model is constructed, including the following contents:

[0108] Performing correlation analysis and dimensionality reduction processing on the water quality data of the equipment to select abnormal water quality features;

[0109] Inputting the abnormal water quality features into a convolutional neural network model to construct a feature space;

[0110] In the feature space, a long short-term memory neural network model is used to express the equipment water quality time series characteristics of the equipment water quality data;

[0111] A training data set and a test data set are established based on the water quality time series characteristics of the equipment, and a water quality anomaly recognition model is generated based on them.

[0112] Specifically, this embodiment establishes the above-mentioned water quality anomaly recognition model based on correlation analysis (PCA), convolutional neural network model (CNN) and long short-term memory neural network model (LSTM), which can accurately and effectively obtain the prediction results of equipment water quality, which is helpful to assist in improving the management effect of sewage treatment equipment.

[0113] In an embodiment provided in the present application, the operation of the sewage treatment equipment is controlled, including: controlling the operating power of the sewage treatment equipment, controlling the water flow in and out of the equipment, controlling the dissolved oxygen of the equipment, controlling the sludge return, adjusting water quality parameters when the water quality changes, selecting and switching the equipment operating status, and controlling the switch start and stop status and operating time of the corresponding control equipment through current signals.

[0114] Example 2

[0115] See also Figure 5 The present application provides a method for managing the operation of a sewage treatment plant, comprising the following steps:

[0116] Regularly monitor sewage treatment equipment to obtain monitoring data;

[0117] Processing and analyzing the monitoring data to obtain analysis results;

[0118] Generate a control decision based on the analysis result and use it to control the operation of the sewage treatment equipment;

[0119] The sewage treatment equipment is regularly maintained according to the analysis results; it is also used for emergency response to emergencies;

[0120] The monitoring data includes historical monitoring data and real-time monitoring data.

[0121] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0122] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0123] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0124] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention without departing from the content of the technical solution of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. A sewage treatment equipment operation management system, characterized in that: include: Equipment monitoring module, used to regularly monitor sewage treatment equipment to obtain monitoring data; A processing and analysis module, used for processing and analyzing the monitoring data to obtain analysis results; An operation control module, used to generate a control decision based on the analysis result and thereby perform operation control on the sewage treatment equipment; A maintenance management module is used to perform regular maintenance on the sewage treatment equipment according to the analysis results; and is also used to handle emergency events; The monitoring data includes historical monitoring data and real-time monitoring data.

2. A sewage treatment equipment operation management system according to claim 1, characterized in that: The equipment monitoring module includes a data acquisition unit, a data classification unit and a data storage unit; The data collection unit is used to collect monitoring data of the sewage treatment equipment at multiple predetermined time points within a predetermined time period; The data classification unit uses the current time point as a time boundary to classify the monitoring data before the current time point into historical monitoring data, and classifies the monitoring data at the current time point into real-time monitoring data; The data storage unit uses a dual ring buffer for data storage, specifically: using a first ring buffer to store historical monitoring data, and using a second ring buffer to store real-time monitoring data.

3. A sewage treatment equipment operation management system according to claim 1, characterized in that: The processing and analysis module includes a data processing unit, a type classification unit, a model building unit, an anomaly identification unit and an anomaly analysis unit; The data processing unit is used to perform data preprocessing and data enhancement on the monitoring data; The type classification unit is used to classify the processed historical monitoring data into equipment water quality data and equipment operation data; The model building unit builds a water quality anomaly recognition model based on the equipment water quality data; and builds an operation anomaly recognition model based on the equipment operation data; The abnormality identification unit performs abnormality identification on the processed real-time monitoring data based on the water quality abnormality identification model and the operation abnormality identification model, and generates a first identification result and a second identification result respectively; The abnormality analysis unit performs abnormality analysis on the equipment water quality data based on the first recognition result to generate a first analysis result; Based on the second recognition result, an abnormality analysis is performed on the device operation data to generate a second analysis result.

4. A sewage treatment equipment operation management system according to claim 3, characterized in that: The data preprocessing includes data cleaning, data conversion, data integration and time series processing.

5. A sewage treatment equipment operation management system according to claim 3, characterized in that: The equipment water quality data includes water quality parameters of the equipment inlet water and water quality parameters of the equipment outlet water; the equipment operation data includes equipment operation status, equipment operation parameters and operation energy consumption data.

6. A sewage treatment equipment operation management system according to claim 3, characterized in that: Constructing the operation abnormality identification model includes the following contents: Arranging the equipment operation data according to the time dimension into an operation data time series matrix of the sewage treatment equipment; A time series correlation feature extractor based on a deep neural network model performs feature extraction on the operation data time series matrix to obtain an operation time series feature graph; Performing feature association enhancement processing on the running time feature graph to obtain enhanced running time features; An operation anomaly recognition model is established based on the enhanced operation timing characteristics.

7. A sewage treatment equipment operation management system according to claim 6, characterized in that: Obtaining the enhanced running timing characteristics includes the following: Passing the runtime feature graph through a channel attention module to obtain a channel explicit runtime feature graph; Passing the channel explicit runtime feature map through a first convolutional layer of the deep neural network model to obtain a first feature map, and passing the first feature map through a second convolutional layer to obtain a second feature map; Expanding each feature matrix of the second feature map along the channel dimension into feature vectors to obtain a sequence of first feature vectors, and calculating the cosine similarity between any two first feature vectors in the sequence of the first feature vectors to obtain a cosine similarity feature map; Normalizing the cosine similarity feature map to obtain a normalized cosine similarity feature map and multiplying the normalized cosine similarity feature map by position points with the cosine similarity feature map to obtain a similarity mapping optimization feature map; Passing the similarity map optimization feature map through a first deconvolution layer of the deep neural network model to obtain a first deconvolution feature map, and calculating an element-by-element sum of the first deconvolution feature map and the first feature map to obtain a first fused feature map; Passing the first fused feature map through a second deconvolution layer of the deep neural network model to obtain a second deconvolution feature map, and calculating an element-by-element sum of the second deconvolution feature map and the channel-manifested runtime feature map to obtain a re-enhanced runtime feature map; The enhanced operation timing characteristics are extracted from the re-enhanced operation timing characteristics graph.

8. A sewage treatment equipment operation management system according to claim 3, characterized in that: The water quality anomaly recognition model is constructed, including the following contents: Performing correlation analysis and dimensionality reduction processing on the water quality data of the equipment to select abnormal water quality features; Inputting the abnormal water quality features into a convolutional neural network model to construct a feature space; In the feature space, a long short-term memory neural network model is used to express the equipment water quality time series characteristics of the equipment water quality data; A training data set and a test data set are established based on the water quality time series characteristics of the equipment, and a water quality anomaly recognition model is generated based on them.

9. A sewage treatment equipment operation management system according to claim 1, characterized in that: The operation of the sewage treatment equipment is controlled, including: controlling the operating power of the sewage treatment equipment, controlling the water flow rate of the equipment, controlling the dissolved oxygen of the equipment, controlling the sludge return, adjusting water quality parameters when the water quality changes, selecting and switching the equipment operation status, and controlling the switch start and stop status and operation time of the corresponding control equipment through the current signal.

10. A method for operation and management of sewage treatment equipment, applied to the operation and management system of sewage treatment equipment according to any one of claims 1 to 9, characterized in that: The steps include: Regularly monitor sewage treatment equipment to obtain monitoring data; Processing and analyzing the monitoring data to obtain analysis results; Generate a control decision based on the analysis result and use it to control the operation of the sewage treatment equipment; The sewage treatment equipment is regularly maintained according to the analysis results; it is also used for emergency response to emergencies; The monitoring data includes historical monitoring data and real-time monitoring data.

Images