Real-time data management system of sewage treatment plant

Abstract

A real-time data management system for a sewage treatment plant comprises a data acquisition module, a communication data transmission module, a real-time transmission module, a data preprocessing module, a data storage system module, a data feature analysis module and a management control module. According to the real-time data management system of the sewage treatment plant, the real-time performance of the data transmission process in the data management process is improved by proposing a low-delay transmission algorithm, and data characteristics are analyzed, abnormal data are judged in real time and data management and control are performed through a clustering characteristic analysis algorithm.

Description

Technical Field

[0001] The invention relates to the field of data management, and in particular to a real-time data management system for a sewage treatment plant. Background Art

[0002] With the continuous development of science and technology and the continuous progress of social economy, environmental protection and resource utilization have become important issues worldwide. In this context, sewage treatment technology, as one of the important means of environmental protection and resource recycling, has attracted much attention and attention. With the acceleration of urbanization and the improvement of industrialization, sewage treatment plants play an increasingly important role in cities and industrial parks, and their operating efficiency and management level directly affect environmental quality and social stability.

[0003] Traditional sewage treatment plants usually use manual operation and simple equipment, which have problems such as limited processing capacity, high operating costs, and inconvenient data management, making it difficult to meet the requirements of today's society for environmental protection and resource utilization. Therefore, there is an urgent need for a system that can realize real-time management of sewage treatment plant data to improve the operating efficiency and management level of sewage treatment plants and promote the sustainable development of environmental protection and resource utilization.

[0004] In the past few decades, with the rapid development of information technology and the continuous maturity of intelligent technology, the data management system of sewage treatment plants has been greatly improved and upgraded. The application of advanced technologies such as sensor technology, wireless communication technology, and big data analysis technology has provided strong support and impetus for the development of real-time data management systems in sewage treatment plants.

[0005] First, the development of sensor technology provides a technical basis for data collection. Traditional sewage treatment plants usually rely on manual inspections and manual data recording, which leads to problems such as untimely data collection and low data accuracy. With the advancement of sensor technology, the widespread application of various intelligent sensors has enabled the automatic collection and real-time monitoring of various data in sewage treatment plants, greatly improving the efficiency and accuracy of data collection.

[0006] Secondly, the application of communication technology provides convenient conditions for data transmission in sewage treatment plants. Traditional data transmission methods have problems such as slow data transmission speed and limited transmission distance.

[0007] In addition, the maturity of big data analysis technology provides a powerful analysis tool for sewage treatment plant data management. Traditional data management methods usually rely on manual analysis and simple statistics, which have problems such as low data processing efficiency and inaccurate analysis results. The application of big data analysis technology, such as data mining, machine learning, artificial intelligence, etc., enables in-depth analysis and mining of various data of sewage treatment plants, discovers potential connections and rules between data, and provides a scientific basis for the optimized management of sewage treatment plants.

[0008] In summary, with the continuous development and application of sensor technology, communication technology and big data analysis technology, the real-time data management system of sewage treatment plants has been greatly improved and enhanced, bringing revolutionary changes to the operation efficiency and management level of sewage treatment plants. However, there are still problems such as untimely data collection, unstable data transmission, and inaccurate data analysis. It is necessary to further develop and apply a more efficient and reliable real-time data management system for sewage treatment plants to meet the needs of social and economic development and environmental protection requirements. Summary of the invention

[0009] The object of the present invention is to provide a real-time data management system for a sewage treatment plant, aiming to solve the problems mentioned in the above background.

[0010] In order to achieve the above-mentioned purpose, the present invention proposes a real-time data management system for a sewage treatment plant, comprising a data acquisition module, a communication data transmission module, a real-time transmission module, a data preprocessing module, a data storage system module, a data feature analysis module, and a management and control module; the data acquisition module collects working data in the sewage treatment process by installing sensors; the communication data transmission module transmits the collected data to a data processing center through a TCP / IP protocol; the real-time transmission module proposes a low-latency transmission algorithm to ensure the real-time performance of data transmission; the data preprocessing module optimizes the quality of the collected data by preprocessing the collected data; the data storage system module securely stores the data through a distributed server; the data feature analysis module proposes a clustering feature analysis algorithm to calculate the feature correlation between the data and the cluster center and analyze the data features; the management and control module manages and controls the abnormal data and performs corresponding processing based on the data analysis results.

[0011] Furthermore, the data acquisition module collects working data by installing sensors during the sewage treatment operation. The working data is relevant data in the sewage treatment process, including sewage treatment volume, organic matter content in water, inorganic matter content in water, microbial content in water, working power of the sewage treatment unit, and working power consumption of the sewage treatment unit.

[0012] Furthermore, the communication data transmission module, during the transmission process of collected data, performs data transmission by wired transmission, adopts TCP / IP protocol, establishes and maintains data communication channels between sensors and data processing center, and performs data transmission between sensors and data processing center through data communication channels.

[0013] Furthermore, the low-latency transmission algorithm constructs a data delay vector, calculates the transmission channel allowed window, performs channel estimation, improves channel utilization, reduces delay, and improves data transmission real-time performance.

[0014] Furthermore, the channel estimation process is as follows:

[0015] During the data transmission process, the data delay generated during the data transmission process is used to construct a data delay vector , which is expressed as follows: ; in, Respectively represent the first data delay, the second data delay, and the Data delay, The data delay is based on all data delays and the average of the transmission data size to obtain the transmission start value. The calculation formula is as follows: ; in, Indicates the transfer start value, Indicates the size of the transmitted data. Indicates the total amount of transmission, It represents the data delay parameter. Based on the transmission start value, the data transmission window is set to the transmission start value. During the data transmission process, the data is sent from the sensor end transmission channel to the data processing center end transmission channel. Based on the data transmission window, according to the transmission time interval, the data processing center end transmission channel allowed window is calculated. The calculation formula is as follows: ; in, express The window value allowed by the transmission channel of the data processing center at the moment, express The amount of data sent by the sensor transmission channel at the moment, express The amount of data received by the transmission channel at the data processing center at the moment, express The transmission channel at the data processing center end confirms the size of the received data. Indicates the current The transmission channel at the moment data processing center confirms the received data time. express The transmission channel at the moment data processing center confirms the received data time. Indicates the current The data transmission channel data delay at the moment data processing center, express The data delay of the transmission channel at the data processing center at the moment is less than the data confirmation time of the transmission channel. Based on the allowed window value of the transmission channel at the data processing center, the channel estimation is performed through smoothing processing. The channel estimation parameters are calculated first. The calculation formula is as follows: ; in, express Channel estimation parameters at time instant, represents the sampling period, express The time when the sensor end transmission channel sends data, where the data sending and data receiving at each moment meet Based on the channel estimation parameters, the channel estimation is performed using the historical channel allowed window. The calculation formula is as follows: ; in, express The channel estimate at time t, express Channel estimation at time instant, express Channel estimation parameters at time instant, Represents the total time, optimizes the transmission channel through channel estimation, improves channel utilization, and reduces delay. The low-delay transmission algorithm proposed in the present invention constructs a data delay vector, averages the transmission data size, obtains a transmission start value, sets the data transmission window to the transmission start value, calculates the transmission channel allowed window based on the data transmission window and the transmission time interval, and performs channel estimation based on the input channel allowed window value through smoothing. The low-delay transmission algorithm proposed in the present invention performs channel estimation, optimizes the transmission channel, improves channel utilization, reduces delay, and improves the real-time performance of data transmission.

[0016] Furthermore, the data preprocessing module removes noise data and erroneous data through data cleaning, realizes data standardization conversion through data conversion operations, and confirms data integrity and consistency.

[0017] Furthermore, the storage system module performs distributed encrypted storage of data through distributed servers, performs multi-party data backup operations, and adopts data encryption operations to ensure the security and reliability of the data storage process.

[0018] Furthermore, the clustering feature analysis algorithm calculates the correlation between the data items and the cluster centers, clusters the data items, updates the initial cluster centers, iterates the data item clustering process, and performs data feature analysis.

[0019] Furthermore, the data feature analysis is described in detail as follows:

[0020] For the collected data, all data items are formed into a data vector , which is expressed as follows: ; in, Represents data vectors The first data item, data vector The second data item, data vector No. data items, data vectors No. data items, define the initial cluster centers, and the initial cluster center set is expressed as: ; in, represents the initial cluster center set, Represent the initial cluster center set The first type of initial cluster center and initial cluster center set No. Initial cluster centers, initial cluster center sets No. The initial cluster center is selected, and the correlation between all data items and the initial cluster center is calculated. The data items are clustered based on the correlation. The calculation formula is as follows: ; in, Represents data vector No. data items and the initial cluster center set No. The correlation between the initial cluster centers, Represents the dimension of the data item, Represents the bi-norm. Based on the correlation between the data item and the initial cluster center, the data items are clustered by minimizing the correlation calculation. The clustering process is as follows: ; in, Indicates the value of the minimum value in brackets After the data items are clustered, the initial cluster center is updated, and the next step of data item clustering iteration is performed. , process its correlation with all data items, and then update the initial cluster center through the initial cluster center of the previous iteration stage. The process is expressed as follows: ; in, Indicates The first iteration The initial cluster centers, Indicates The first iteration The initial cluster centers, Indicates The iteration data items, Representing the weight of the data item, the iterative process is continuously performed until the initial cluster center no longer changes, the data item clustering process is completed, and the deep characteristics of the data are obtained. The clustering feature analysis algorithm proposed in the present invention defines the initial cluster center, calculates the correlation between the data item and the initial cluster center, minimizes the correlation, clusters the data items, and updates the initial cluster center based on the iterative process. The iterative data item clustering process is continuously performed to perform data feature analysis. The clustering feature analysis algorithm proposed in the present invention uses the cluster center to mine deep-level data characteristics and improve the analysis sensitivity of abnormal data.

[0021] Furthermore, the management and control module, through the results of deep data feature analysis, issues corresponding alarm reminders for abnormal data, performs corresponding processing on the sewage treatment operation steps related to the abnormal data, analyzes the causes of the abnormal data, and performs corresponding processing according to the causes.

[0022] The beneficial effects of the present invention are as follows:

[0023] 1. The real-time transmission module of the present invention proposes a low-latency transmission algorithm. By constructing a data delay vector, the transmission data size is averaged to obtain a transmission start value, and the data transmission window is set to the transmission start value. Based on the data transmission window and the transmission time interval, the transmission channel allowed window is calculated. Based on the input channel allowed window value, channel estimation is performed through smoothing processing to optimize the transmission channel, improve channel utilization, reduce delays, and improve the real-time performance of data transmission.

[0024] 2. The data feature analysis module of the present invention proposes a clustering feature analysis algorithm, defines the initial cluster center, calculates the correlation between the data item and the initial cluster center, minimizes the correlation, clusters the data items, updates the initial cluster center based on an iterative process, continuously iterates the data item clustering process, performs data feature analysis, utilizes the cluster center, mines deep-level data features, and improves the analysis sensitivity of abnormal data.

[0025] 3. The real-time data management system for sewage treatment plants proposed in the present invention enables real-time monitoring and management of the operating data of sewage treatment plants, so that operating personnel can timely understand the operating status and water quality of various equipment in the sewage treatment plant, and make timely adjustments and processing, thereby improving the operating efficiency and processing capacity of the sewage treatment plant; through real-time monitoring and management, equipment failures and abnormal conditions can be discovered in time, and corresponding maintenance and repair measures can be taken to avoid downtime losses and repair costs caused by equipment failures, thereby reducing operating costs; the real-time data management system can discover problems and bottlenecks in the sewage treatment process by real-time monitoring and analysis of key parameters in the sewage treatment process, and propose corresponding optimization plans and improvement measures, thereby optimizing the sewage treatment process, improving treatment efficiency and water quality stability, enhancing environmental protection capabilities, improving management levels and reducing safety risks, and providing important support and guarantee for the stable operation and sustainable development of sewage treatment plants. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings in the following description are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0027] Figure 1 This is a system diagram of the present invention. DETAILED DESCRIPTION

[0028] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0029] See also Figure 1In order to achieve the above-mentioned purpose, the present invention proposes a real-time data management system for a sewage treatment plant, comprising a data acquisition module, a communication data transmission module, a real-time transmission module, a data preprocessing module, a data storage system module, a data feature analysis module, and a management control module; the data acquisition module collects working data in the sewage treatment process by installing sensors; the communication data transmission module transmits the collected data to the data processing center through the TCP / IP protocol; the real-time transmission module proposes a low-latency transmission algorithm to ensure the real-time performance of data transmission; the data preprocessing module performs quality optimization operations on the collected data by preprocessing the collected data; the data storage system module stores the data securely through a distributed server; the data feature analysis module proposes a cluster feature analysis algorithm to calculate the feature correlation between the data and the cluster center and analyze the data features; the management control module manages and controls the abnormal data and performs corresponding processing based on the data analysis results.

[0030] See also Figure 1 Specifically, the data acquisition module collects working data by installing sensors during the sewage treatment operation. The working data is relevant data in the sewage treatment process, including sewage treatment volume, organic matter content in the water body, inorganic matter content in the water body, microbial content in the water body, working power of the sewage treatment unit, and working power consumption of the sewage treatment unit.

[0031] See also Figure 1 Specifically, the communication data transmission module, during the transmission process of collected data, performs data transmission by wired transmission, adopts TCP / IP protocol, establishes a data communication channel and maintains the data communication channel between the sensor and the data processing center, and performs data transmission between the sensor and the data processing center through the data communication channel.

[0032] See also Figure 1 Specifically, the low-latency transmission algorithm constructs a data delay vector, calculates the transmission channel allowed window, performs channel estimation, improves channel utilization, reduces delay, and improves data transmission real-time performance. The detailed process is as follows:

[0033] During the data transmission process, the data delay generated during the data transmission process is used to construct a data delay vector , which is expressed as follows: ; in, Respectively represent the first data delay, the second data delay, and the Data delay, The data delay is based on all data delays and the average of the transmission data size to obtain the transmission start value. The calculation formula is as follows: ; in, Indicates the transfer start value, Indicates the size of the transmitted data. Indicates the total amount of transmission, It represents the data delay parameter. Based on the transmission start value, the data transmission window is set to the transmission start value. During the data transmission process, the data is sent from the sensor end transmission channel to the data processing center end transmission channel. Based on the data transmission window, according to the transmission time interval, the data processing center end transmission channel allowed window is calculated. The calculation formula is as follows: ; in, express The window value allowed by the transmission channel of the data processing center at the moment, express The amount of data sent by the sensor transmission channel at the moment, express The amount of data received by the transmission channel at the data processing center at the moment, express The transmission channel at the data processing center end confirms the size of the received data. Indicates the current The transmission channel at the moment data processing center confirms the received data time. express The transmission channel at the moment data processing center confirms the received data time. Indicates the current The data transmission channel data delay at the moment data processing center, express The data delay of the transmission channel at the data processing center at the moment is less than the data confirmation time of the transmission channel. Based on the allowed window value of the transmission channel at the data processing center, the channel estimation is performed through smoothing processing. The channel estimation parameters are calculated first. The calculation formula is as follows: ; in, express Channel estimation parameters at time instant, represents the sampling period, express The time when the sensor end transmission channel sends data, where the data sending and data receiving at each moment meet Based on the channel estimation parameters, the channel estimation is performed using the historical channel allowed window. The calculation formula is as follows: ; in, express The channel estimate at time t, express Channel estimation at time instant, express Channel estimation parameters at time instant, Indicates the total time, through channel estimation, optimizes the transmission channel, improves channel utilization and reduces delay.

[0034] See also Figure 1 Specifically, the data preprocessing module removes noise data and erroneous data through data cleaning, realizes data standardization conversion through data conversion operations, and confirms data integrity and consistency.

[0035] See also Figure 1 Specifically, the storage system module performs distributed encrypted storage of data through distributed servers, performs multi-party data backup operations, and adopts data encryption operations to ensure the security and reliability of data storage.

[0036] See also Figure 1 ,Specifically, the clustering feature analysis algorithm calculates the correlation between data items and cluster centers, ,clusters the data items, updates the initial cluster centers, iterates the data item clustering process, and ,performs data feature analysis. ,The detailed process is as follows: For the collected data, all data items are formed into a data vector , which is expressed as follows: ; in, Represents data vectors The first data item, data vector The second data item, data vector No. data items, data vectors No. data items, define the initial cluster centers, and the initial cluster center set is expressed as: ; in, represents the initial cluster center set, Represent the initial cluster center set The first type of initial cluster center and initial cluster center set No. Initial cluster centers, initial cluster center sets No. The initial cluster center is selected, and the correlation between all data items and the initial cluster center is calculated. The data items are clustered based on the correlation. The calculation formula is as follows: ; in, Represents data vector No. data items and the initial cluster center set No. The correlation between the initial cluster centers, Represents the dimension of the data item, Represents the bi-norm. Based on the correlation between the data item and the initial cluster center, the data items are clustered by minimizing the correlation calculation. The clustering process is as follows: ; in, The value of the minimum value in brackets After the data items are clustered, the initial cluster center is updated, and the next step of data item clustering iteration is performed. , process its correlation with all data items, and then update the initial cluster center through the initial cluster center of the previous iteration stage. The process is expressed as follows: ; in, Indicates The first iteration The initial cluster centers, Indicates The first iteration The initial cluster centers, Indicates The iteration data items, Represents the weight of the data item, and the iterative process is continuously performed until the initial cluster center no longer changes, completing the data item clustering process and obtaining the deep features of the data.

[0037] See also Figure 1 Specifically, the management and control module, through the results of deep data feature analysis, issues corresponding alarm reminders for abnormal data, performs corresponding processing on the sewage treatment operation steps related to the abnormal data, analyzes the causes of the abnormal data, and performs corresponding processing according to the causes.

[0038] In a specific embodiment, first, the user installs sensors to collect data on sewage treatment volume, water quality component content, and energy consumption indicators during sewage treatment; then, the TCP / IP protocol is used to establish and maintain a data communication channel between the sensor and the data processing center, and data is transmitted between the sensor and the data processing center through the data communication channel; then, a low-latency transmission algorithm is used to construct a data delay vector, calculate the transmission channel allowable window, perform channel estimation, improve channel utilization, reduce delays in the data transmission process, and improve data transmission real-time performance; then, data cleaning is performed to remove noise data and erroneous data, and data conversion operations are performed to standardize the data. Conversion, data integrity and consistency confirmation; then, through distributed servers, the data is distributed and encrypted for storage, multi-party data backup operations are performed, and data encryption operations are used to ensure data security and reliability; then, the clustering feature analysis algorithm is used to calculate the correlation between data items and cluster centers, cluster data items, complete data feature analysis, mine deep data features, and improve the analysis sensitivity of abnormal data; finally, through the results of deep data feature analysis, corresponding alarm reminders are issued for abnormal data, and corresponding processing is performed for sewage treatment operation steps related to abnormal data, the causes of abnormal data are analyzed, and corresponding processing is performed according to the causes.

[0039] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0040] Each embodiment in this specification is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0041] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.

Claims

1. A real-time data management system for a sewage treatment plant, comprising a data acquisition module, a communication data storage module, a real-time transmission module, a data preprocessing module, a data storage system module, a data feature analysis module, and a management control module; the data acquisition module collects working data in the sewage treatment process by installing sensors; the communication data transmission module transmits the collected data to a data processing center through the TCP / IP protocol; The real-time transmission module proposes a low-latency transmission algorithm to ensure the real-time nature of data transmission; the data preprocessing module optimizes the quality of collected data by preprocessing the collected data; The data storage system module stores data through distributed servers; The data feature analysis module proposes a cluster feature analysis algorithm, calculates the feature correlation between data and cluster centers, and analyzes data features; The management and control module manages and handles abnormal data based on data analysis results.

2. A real-time data management system for a sewage treatment plant according to claim 1, characterized in that: The data acquisition module collects working data by installing sensors during the sewage treatment operation. The working data is relevant data in the sewage treatment process, including sewage treatment volume, organic matter content in the water body, inorganic matter content in the water body, microbial content in the water body, working power of the sewage treatment unit, and working power consumption of the sewage treatment unit.

3. A real-time data management system for a sewage treatment plant according to claim 1, characterized in that: The communication data transmission module, during the transmission process of collected data, performs data transmission by wired transmission, adopts TCP / IP protocol, establishes a data communication channel and maintains the data communication channel between the sensor and the data processing center, and performs data transmission between the sensor and the data processing center through the data communication channel.

4. A real-time data management system for a sewage treatment plant according to claim 1, characterized in that: The low-delay transmission algorithm constructs a data delay vector, calculates the transmission channel allowed window, and performs channel estimation.

5. A real-time data management system for a sewage treatment plant according to claim 4, characterized in that: The detailed process of low-latency transmission is as follows: During the data transmission process, the data delay generated during the data transmission process is used to construct a data delay vector , which is expressed as follows: ； in, Respectively represent the first data delay, the second data delay, and the Data delay, The data delay is based on all data delays and the average of the transmission data size to obtain the transmission start value. The calculation formula is as follows: ； in, Indicates the transfer start value, Indicates the size of the transmitted data. Indicates the total amount of transmission, It represents the data delay parameter. Based on the transmission start value, the data transmission window is set to the transmission start value. During the data transmission process, the data is sent from the sensor end transmission channel to the data processing center end transmission channel. Based on the data transmission window, according to the transmission time interval, the data processing center end transmission channel allowed window is calculated. The calculation formula is as follows: ； in, express The window value allowed by the transmission channel of the data processing center at the moment, express The amount of data sent by the sensor transmission channel at the moment, express The amount of data received by the transmission channel at the data processing center end at the moment, express The transmission channel at the data processing center end confirms the size of the received data. Indicates the current The transmission channel at the moment data processing center confirms the received data time. express The transmission channel of the moment data processing center confirms the received data time. Indicates the current The data transmission channel data delay at the moment data processing center end, express The data delay of the transmission channel at the data processing center at the moment is less than the data confirmation time of the transmission channel. Based on the allowed window value of the transmission channel at the data processing center, the channel estimation is performed through smoothing processing. The channel estimation parameters are calculated first. The calculation formula is as follows: ； in, express Channel estimation parameters at time instant, represents the sampling period, express The time when the sensor end transmission channel sends data, where the data sending and data receiving at each moment meet , based on the channel estimation parameters, using the historical channel allowed window, channel estimation is performed, and the calculation formula is expressed as follows: ； in, express The channel estimate at time t, express The channel estimate at time express Channel estimation parameters at time instant, Indicates the total time, through channel estimation, optimizes the transmission channel, improves channel utilization and reduces delay.

6. A real-time data management system for a sewage treatment plant according to claim 1, characterized in that: The data preprocessing module removes noise data and erroneous data through data cleaning, and realizes data standardization conversion through data conversion operations.

7. A real-time data management system for a sewage treatment plant according to claim 1, characterized in that: The storage system module performs distributed encrypted storage of data through distributed servers and performs multi-party backup operations of the data.

8. A real-time data management system for a sewage treatment plant according to claim 7, characterized in that: The clustering feature analysis algorithm calculates the correlation between data items and cluster centers, clusters the data items, updates the initial cluster centers, iterates the data item clustering process, and performs data feature analysis.

9. A real-time data management system for a sewage treatment plant according to claim 8, characterized in that: The detailed process of data feature analysis is as follows: For the collected data, all data items are formed into a data vector , which is expressed as follows: ； in, Represents data vectors The first data item, data vector The second data item, data vector No. data items, data vectors No. data items, define the initial cluster centers, and the initial cluster center set is expressed as: ； in, represents the initial cluster center set, Represent the initial cluster center set The first type of initial cluster center and initial cluster center set No. Initial cluster centers, initial cluster center sets No. The initial cluster center is selected, and the correlation between all data items and the initial cluster center is calculated. The data items are clustered based on the correlation. The calculation formula is as follows: ； in, Represents data vector No. data items and the initial cluster center set No. The correlation between the initial cluster centers, Represents the dimension of the data item, Represents the bi-norm. Based on the correlation between the data item and the initial cluster center, the data items are clustered by minimizing the correlation calculation. The clustering process is as follows: ； in, The value of the minimum value in brackets After the data items are clustered, the initial cluster center is updated, and the next step of data item clustering iteration is performed. , average its correlation with all data items, and then update the initial cluster center through the initial cluster center of the previous iteration. The process is shown as follows: ； in, Indicates The first iteration The initial cluster centers, Indicates The first iteration The initial cluster centers, Indicates The first iteration data items, Represents the weight of the data item, and the iterative process is continuously performed until the initial cluster center no longer changes, completing the data item clustering process and obtaining the deep features of the data.

10. A real-time data management system for a sewage treatment plant according to claim 1, characterized in that: The management control module, through the results of deep data feature analysis, issues corresponding alarm reminders for abnormal data, performs corresponding processing on the sewage treatment operation steps related to the abnormal data, analyzes the causes of the abnormal data, and performs corresponding processing according to the causes.

Images