A cloud-edge data collaboration system and method for sewage treatment

Abstract

The present invention relates to the technical field of sewage treatment cloud-edge data collaborative management, and specifically provides a cloud-edge data collaborative system and method for sewage treatment. In the system, the abnormal risk assessment feedback module extracts the abnormal monitoring sources of the edge devices belonging to the sewage treatment data based on the risk monitoring items of the obtained sewage treatment data and the risk assessment values of the corresponding risk monitoring items, and generates the transmission feedback results of the corresponding edge devices. During the cloud-edge data collaboration process of the present invention, through feature extraction and risk assessment of the sewage treatment data transmission set, the determination of the abnormal monitoring sources of the edge devices belonging to the sewage treatment data is realized, and according to the generated transmission feedback results of the corresponding edge devices, the collaborative optimization of the sewage treatment data transmission set integrated at the current time is realized, ensuring the efficiency of cloud-edge data collaboration; this method realizes the efficient processing and real-time response of data through the collaborative work of the cloud server and the edge devices.

Description

Technical Field

[0001] The present invention relates to the technical field of sewage treatment cloud-edge data collaborative management, and specifically provides a cloud-edge data collaborative system and method for sewage treatment. Background Technique

[0002] With the rapid development of Internet of Things, big data and artificial intelligence technologies, the sewage treatment field has higher and higher requirements for data processing efficiency and real-time performance. Although the traditional cloud computing model has powerful data processing capabilities, due to data transmission delay and bandwidth limitations, it is difficult to meet application scenarios with high real-time requirements; therefore, the cloud-edge data collaborative system has emerged as the times require.

[0003] In the existing cloud-edge data collaborative system for sewage treatment, usually during the sewage treatment process, edge devices are responsible for real-time collection and processing of water quality data, while the cloud server is responsible for storage and analysis functions. Although it improves the processing efficiency of sewage treatment data and reduces data transmission delay; however, the existing technology cannot dynamically adjust the detailed degree of local data sampling in the data to be transmitted by edge devices according to the analysis feedback results of cloud data, making it impossible to quickly and effectively lock and warn of abnormal faults in sewage treatment equipment. Therefore, the existing technology has relatively large defects. Summary of the Invention

[0004] The purpose of the present invention is to provide a cloud-edge data collaborative system and method for sewage treatment to solve the problems raised in the above background technique.

[0005] To solve the above technical problems, the present invention provides the following technical solution: A cloud-edge data collaborative method for sewage treatment, the method includes the following steps:

[0006] S1. Edge devices collect data in the sewage treatment process in real time, preprocess the collected sewage treatment data, and integrate it into a sewage treatment data transmission set and transmit it to the cloud server;

[0007] S2. The cloud server stores and extracts features from the sewage treatment data transmission set transmitted by the edge device, analyzes the sewage treatment status based on the feature extraction results of the sewage treatment data transmission set, and obtains the risk monitoring items of the sewage treatment data and the risk assessment values of the corresponding risk monitoring items;

[0008] S3. Based on the obtained risk monitoring items of the sewage treatment data and the risk assessment values of the corresponding risk monitoring items, extract the abnormal monitoring sources of the edge devices belonging to the sewage treatment data, and generate the transmission feedback results of the corresponding edge devices;

[0009] S4. According to the transmission feedback result received from the cloud server, the edge device collaboratively optimizes the sewage treatment data transmission set integrated at the current time, and replaces the original sewage treatment data transmission set with the optimized sewage treatment data transmission set and transmits it to the cloud server.

[0010] Further, the preprocessing process of the collected sewage treatment data in S1 includes supplementing the missing collected data with the average value of each collected data of the same sensor in the most recent preset time period; the sewage treatment data includes the monitoring results respectively corresponding to different sensors in each sewage treatment device connected to the corresponding edge device, and the same sewage treatment device includes one or more sensors; the sewage treatment data transmission set is a summary set of the sewage treatment data corresponding to each time point to be transmitted in the order of collection time.

[0011] The edge device in the present invention represents an edge data processor, which may receive the monitoring data of each sensor in a sewage treatment device or multiple bound sewage treatment devices at different time points; the sensor transmits the monitoring data to the corresponding edge device once every preset time (tg), and the edge device transmits it to the cloud server after integrating the monitoring data of each received sensor (sewage treatment data transmission set).

[0012] Further, the features extracted by the cloud server from the sewage treatment data transmission set transmitted by the edge device in S2 include abnormal monitoring data items, abnormal data items of trend change, and abnormal items of data collaborative association; each element item in the obtained feature extraction result corresponds to a sensor.

[0013] The abnormal monitoring data item indicates that the monitoring data of the corresponding sensor has a sensor that does not belong to the preset monitoring interval of the corresponding sensor.

[0014] The abnormal data item of trend change indicates a sensor in which, within the monitoring data section formed by the maximum monitoring data and the minimum monitoring data among the monitoring data of the same sensor, the average value of the absolute values of the mutation coefficients corresponding to any two adjacent monitoring data is greater than the abnormal trend threshold; the absolute value of the mutation coefficient corresponding to two monitoring data is equal to the absolute value of the quotient obtained by dividing the difference between the corresponding two monitoring data by the time interval duration of the data collection time corresponding to the corresponding two monitoring data; the abnormal trend threshold is the average value of the absolute values of the mutation coefficients corresponding to any two adjacent monitoring data in the monitoring data section formed by the maximum monitoring data and the minimum monitoring data among the monitoring data of the same sensor in the preset time period before the monitoring data of each sensor in the historical database that does not belong to the preset monitoring interval of the corresponding sensor.

[0015] When the cloud server extracts the characteristics of the sewage treatment data transmission set transmitted by the edge device in the present invention, including abnormal monitoring data items, abnormal trend change data items, and abnormal data collaborative association items, it considers the sensors with abnormal monitoring status from three perspectives. In the first perspective, the abnormal monitoring data items correspond to the actual abnormal monitoring results of the sensors; in the second perspective, the abnormal trend change data items are considered by predicting the abnormal monitoring status of the sensors through the change trend of the monitoring data; in the third perspective, the abnormal data collaborative association items are considered from the comprehensive situation of the mutation characteristic coefficients corresponding to each sensor with an association relationship.

[0016] The abnormal data collaborative association item represents each sensor with an association relationship, where the maximum value of the similarity between the array composed of the mutation characteristic coefficients corresponding to each sensor and each preset array composed of the corresponding sensors in the historical data is greater than the preset similarity; the association relationship between the sensors is preset in the database;

[0017] The mutation characteristic coefficient corresponding to each sensor with an association relationship represents the average value of the absolute values of the mutation coefficients corresponding to any two adjacent monitoring data of each sensor in the intersection of the acquisition time intervals of the monitoring data sections corresponding to the maximum monitoring data and the minimum monitoring data of each sensor with an association relationship;

[0018] Within the preset time period before each sensor monitoring data in the historical database that does not belong to the preset monitoring interval of the corresponding sensor's monitoring, the array composed of taking the average value of the absolute values of the mutation coefficients corresponding to any two adjacent monitoring data of each sensor associated with the corresponding sensor as an element is used as a preset array composed of the corresponding sensors with an association relationship in the historical data;

[0019] The similarity between two arrays is equal to the average value of the similarities between the elements at the corresponding positions in the two arrays. The similarity between the elements at the corresponding positions is equal to the quotient of the minimum value in the corresponding position elements divided by the maximum value. When the maximum value of the corresponding position elements is 0, it is determined that the similarity between the corresponding position elements is 1.

[0020] Furthermore, the risk monitoring items of the sewage treatment data obtained in S2 include each element in the characteristics extracted from the sewage treatment data transmission set transmitted by the cloud server to the edge device;

[0021] The calculation formula for the corresponding risk assessment value of the risk monitoring items of the sewage treatment data is specifically:

[0022] ;

[0023] Among them, RV nRepresents the risk assessment value of the nth risk monitoring item of the sewage treatment data; E n Represents the abnormal factor corresponding to the nth risk monitoring item of the sewage treatment data; the E n The value is equal to the maximum value among the abnormal factors corresponding to the types of abnormal items to which the nth risk monitoring item of the sewage treatment data belongs during the generation process. The types of abnormal items include abnormal monitoring data items, trend change abnormal data items, and data collaborative association abnormal items, and different types of abnormal items correspond to different pre-set abnormal factors in the database, and the abnormal factor is a constant; P n Represents the ratio of the number of sensor monitoring data that does not belong to the pre-set monitoring interval of the corresponding sensor to the total number of sensor monitoring data of the nth risk monitoring item of the sewage treatment data in the most recent pre-set time period; PG （n，m） Represents the ratio of the number of sensor monitoring data that does not belong to the pre-set monitoring interval of the corresponding sensor to the total number of sensor monitoring data of the mth risk monitoring item associated with the nth risk monitoring item in the sewage treatment data in the most recent pre-set time period; Mn represents the number of risk monitoring items associated with the nth risk monitoring item in the sewage treatment data; μ represents the conversion weight coefficient, and μ is a pre-set constant; SCR represents the comparison and screening function. When Mn = 0, then it is determined that ; otherwise, it is determined that .

[0024] Further, the S3 includes:

[0025] Obtain the risk monitoring items of the sewage treatment data and the risk assessment values of the corresponding risk monitoring items, and record each risk monitoring item with a corresponding risk assessment value greater than the pre-set risk value as a monitoring risk source; record each risk monitoring item associated with the monitoring risk source in the sewage treatment data as a collaborative monitoring source; the abnormal monitoring sources of the edge devices to which the sewage treatment data belongs include the monitoring risk sources and collaborative monitoring sources of the corresponding sewage treatment data;

[0026] During the process of generating the transmission feedback result of the corresponding edge device, record the transmission feedback result corresponding to the jth sensor in the ith edge device as F （i，j） , and the specific calculation formula is as follows:

[0027] ;

[0028] Among them, T （i，j） Represents the data acquisition interval duration corresponding to the jth sensor in the ith edge device before transmission feedback; BL （i，j） Represents the bias coefficient corresponding to the jth sensor in the ith edge device when it received the previous transmission feedback result; BD （i，j）Denote the current bias coefficient of the j-th sensor in the i-th edge device; the bias coefficient is equal to the quotient obtained by dividing the bias factor of the corresponding sensor by the sum of the bias factors of all sensors in the corresponding edge device; when the sensor belongs to the abnormal monitoring source of the corresponding edge device, the bias factor of the corresponding sensor is equal to the risk assessment value of the corresponding sensor; when the sensor does not belong to the abnormal monitoring source of the corresponding edge device, the bias factor of the corresponding sensor is a preset constant.

[0029] Further, when performing collaborative optimization on the sewage treatment data transmission set integrated at the current time in S4, obtain the sewage treatment data transmission set integrated at the current time, and denote the set obtained by sequentially summarizing the monitoring results corresponding to the same sensor at different times in the sewage treatment data transmission set integrated at the current time in chronological order as the first optimization alternative set of the corresponding sensor; obtain the acquisition time corresponding to each element in the first optimization alternative set of each sensor; denote the time interval between the acquisition times corresponding to any two adjacent elements in the first optimization alternative set of each sensor as tg, and tg is a preset constant in the database; denote the integer multiple value of tg whose absolute value of the difference from the transmission feedback result corresponding to the k-th sensor is the smallest as the optimization time feedback value of the k-th sensor;

[0030] Mark the elements in the first optimization alternative set of the k-th sensor whose time interval between the acquisition time corresponding to them and the acquisition time corresponding to the first element is an integer multiple of the optimization time feedback value of the k-th sensor;

[0031] After deleting the data that does not belong to the marked elements in the first optimization alternative sets of each sensor from the sewage treatment data transmission set integrated at the current time, the obtained result is used as the collaborative optimization result of the sewage treatment data transmission set integrated at the current time.

[0032] A cloud-edge data collaboration system for sewage treatment, the system includes the following modules:

[0033] Edge-end data integration module, the edge-end data integration module controls the edge devices to collect data in the sewage treatment process in real time, preprocess the collected sewage treatment data, and integrate it into a sewage treatment data transmission set for transmission to the cloud server;

[0034] Cloud data risk analysis module, the cloud data risk analysis module controls the cloud server to store and extract features from the sewage treatment data transmission set transmitted by the edge devices, performs sewage treatment status analysis based on the feature extraction results of the sewage treatment data transmission set, and obtains the risk monitoring items of the sewage treatment data and the risk assessment values of the corresponding risk monitoring items;

[0035] Anomaly risk assessment feedback module. The anomaly risk assessment feedback module extracts the anomaly monitoring sources of the edge devices belonging to the sewage treatment data based on the risk monitoring items of the obtained sewage treatment data and the risk assessment values of the corresponding risk monitoring items, and generates the transmission feedback results of the corresponding edge devices.

[0036] Cloud-edge collaborative transmission optimization module. The cloud-edge collaborative transmission optimization module controls the edge devices to perform collaborative optimization on the sewage treatment data transmission set integrated at the current time according to the transmission feedback results received from the cloud server, and replaces the original sewage treatment data transmission set with the optimized sewage treatment data transmission set and transmits it to the cloud server.

[0037] Furthermore, the cloud data risk analysis module includes a feature extraction unit and a risk assessment unit.

[0038] The feature extraction unit controls the cloud server to store and extract features from the sewage treatment data transmission set transmitted by the edge devices.

[0039] The risk assessment unit performs sewage treatment status analysis based on the feature extraction results of the sewage treatment data transmission set, and obtains the risk monitoring items of the sewage treatment data and the risk assessment values of the corresponding risk monitoring items.

[0040] Furthermore, the anomaly risk assessment feedback module includes an anomaly monitoring source extraction unit and a transmission feedback generation unit.

[0041] The anomaly monitoring source extraction unit extracts the anomaly monitoring sources of the edge devices belonging to the sewage treatment data based on the risk monitoring items of the obtained sewage treatment data and the risk assessment values of the corresponding risk monitoring items.

[0042] The transmission feedback generation unit generates the transmission feedback results of the corresponding edge devices according to the anomaly monitoring sources extracted by the anomaly monitoring source extraction unit.

[0043] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: In the process of cloud-edge data collaboration, the present invention realizes the determination of the anomaly monitoring sources of the edge devices belonging to the sewage treatment data by extracting features and performing risk assessment on the sewage treatment data transmission set, and realizes the collaborative optimization of the sewage treatment data transmission set integrated at the current time according to the generated transmission feedback results of the corresponding edge devices, ensuring the efficiency of cloud-edge data collaboration; this method realizes the efficient processing and real-time response of data through the collaborative work of the cloud server and the edge devices. Description of the Drawings

[0044] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention, and do not constitute a limitation to the present invention. In the drawings:

[0045] Figure 1 is a schematic structural diagram of a cloud-edge data collaboration system for sewage treatment according to the present invention;

[0046] Figure 2 is a schematic flowchart of a cloud-edge data collaboration method for sewage treatment according to the present invention. Specific embodiments

[0047] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0048] Please refer to Figure 1 , the present invention provides a technical solution: a cloud-edge data collaboration system for sewage treatment, and the system includes the following modules:

[0049] An edge-side data integration module, which controls edge-side devices to collect data in real time during the sewage treatment process, preprocesses the collected sewage treatment data, and integrates it into a sewage treatment data transmission set for transmission to the cloud server;

[0050] A cloud data risk analysis module, which includes a feature extraction unit and a risk assessment unit,

[0051] The feature extraction unit controls the cloud server to store and extract features from the sewage treatment data transmission set transmitted by the edge-side devices;

[0052] The risk assessment unit analyzes the sewage treatment status based on the feature extraction results of the sewage treatment data transmission set to obtain the risk monitoring items of the sewage treatment data and the risk assessment values of the corresponding risk monitoring items;

[0053] An abnormal risk assessment feedback module, which includes an abnormal monitoring source extraction unit and a transmission feedback generation unit,

[0054] The abnormal monitoring source extraction unit extracts the abnormal monitoring sources of the edge-side devices belonging to the sewage treatment data based on the risk monitoring items of the obtained sewage treatment data and the risk assessment values of the corresponding risk monitoring items;

[0055] The transmission feedback generation unit generates a transmission feedback result for the corresponding edge-side device according to the abnormal monitoring sources extracted by the abnormal monitoring source extraction unit;

[0056] The cloud-edge collaborative transmission optimization module controls the edge device to perform collaborative optimization on the sewage treatment data transmission set integrated at the current time according to the transmission feedback result received from the cloud server, and replaces the original sewage treatment data transmission set with the optimized sewage treatment data transmission set and transmits it to the cloud server.

[0057] As Figure 2 shown, a cloud-edge data collaboration method for sewage treatment, the method includes the following steps:

[0058] S1. The edge device collects data in the sewage treatment process in real time, preprocesses the collected sewage treatment data, and integrates it into a sewage treatment data transmission set and transmits it to the cloud server;

[0059] The preprocessing process of the collected sewage treatment data in S1 includes supplementing the missing collected data with the average value of each collected data in the most recent preset time period by the same sensor; the sewage treatment data includes the monitoring results corresponding to different sensors in each sewage treatment device connected to the corresponding edge device, and the same sewage treatment device includes one or more sensors; the sewage treatment data transmission set is a summary set of the sewage treatment data corresponding to each time point to be transmitted in the order of collection time.

[0060] S2. The cloud server stores and extracts features from the sewage treatment data transmission set transmitted by the edge device, analyzes the sewage treatment status based on the feature extraction result of the sewage treatment data transmission set, and obtains the risk monitoring items of the sewage treatment data and the risk assessment values of the corresponding risk monitoring items;

[0061] The features extracted by the cloud server from the sewage treatment data transmission set transmitted by the edge device in S2 include abnormal monitoring data items, abnormal trend change data items, and abnormal data collaboration association items; each element item in the obtained feature extraction result corresponds to a sensor;

[0062] The abnormal monitoring data item indicates that the sensor corresponding to the monitoring data exists outside the preset monitoring interval of the corresponding sensor;

[0063] The abnormal data item of the trend change represents a sensor in which the average value of the absolute values of the mutation coefficients corresponding to any two adjacent monitoring data in the monitoring data section formed by the maximum monitoring data and the minimum monitoring data among the monitoring data of the same sensor is greater than the abnormal trend threshold; the absolute value of the mutation coefficient corresponding to two monitoring data is the absolute value of the quotient obtained by dividing the difference between the corresponding two monitoring data by the length of the data acquisition time interval corresponding to the two monitoring data; the abnormal trend threshold is the average value of the absolute values of the mutation coefficients corresponding to any two adjacent monitoring data in the monitoring data section formed by the maximum monitoring data and the minimum monitoring data among the monitoring data of the same sensor within a preset time period before the monitoring data of each sensor in the historical database that does not belong to the preset monitoring interval of the corresponding sensor's monitoring.

[0064] The abnormal item of data collaborative association represents each sensor with an association relationship, where the maximum value of the similarity between the array formed by the corresponding mutation feature coefficients of each sensor and each preset array formed by the corresponding sensors in the historical data is greater than the preset similarity; the association relationship between the sensors is preset in the database.

[0065] The corresponding mutation feature coefficient of each sensor with an association relationship represents the average value of the absolute values of the mutation coefficients corresponding to any two adjacent monitoring data of each sensor in the intersection of the acquisition time intervals of the monitoring data sections corresponding to the maximum monitoring data and the minimum monitoring data of each sensor with an association relationship.

[0066] Within the preset time period before the monitoring data of each sensor in the historical database that does not belong to the preset monitoring interval of the corresponding sensor's monitoring, an array formed by taking the average value of the absolute values of the mutation coefficients corresponding to any two adjacent monitoring data of each sensor associated with the corresponding sensor as an element is used as a preset array formed by the corresponding sensors with an association relationship in the historical data.

[0067] The similarity between two arrays is equal to the average value of the similarities between the elements at the corresponding positions in the two arrays. The similarity between the elements at the corresponding positions is equal to the quotient of the minimum value in the corresponding position elements divided by the maximum value. When the maximum value of the corresponding position elements is 0, it is determined that the similarity between the corresponding position elements is 1.

[0068] The risk monitoring items of the sewage treatment data obtained in S2 include each element in the features extracted from the sewage treatment data transmission set transmitted by the edge device to the cloud server.

[0069] The calculation formula for the corresponding risk assessment value of the risk monitoring items of the sewage treatment data is specifically:

[0070] ;

[0071] Among them, RV n represents the risk assessment value of the nth risk monitoring item of the sewage treatment data; E n represents the abnormal factor corresponding to the nth risk monitoring item of the sewage treatment data; the E n value is equal to the maximum value among the abnormal factors corresponding to the types of abnormal items to which the nth risk monitoring item of the sewage treatment data belongs during the generation process. The types of abnormal items include abnormal monitoring data items, trend change abnormal data items, and data collaborative association abnormal items, and different types of abnormal items correspond to different preset abnormal factors in the database. The abnormal factor is a constant; P n represents the ratio of the number of sensor monitoring data that does not belong to the preset monitoring interval of the corresponding sensor to the total number of sensor monitoring data of the nth risk monitoring item of the sewage treatment data within the most recent preset time period; PG （n，m） represents the ratio of the number of sensor monitoring data that does not belong to the preset monitoring interval of the corresponding sensor to the total number of sensor monitoring data of the mth risk monitoring item associated with the nth risk monitoring item of the sewage treatment data within the most recent preset time period; Mn represents the number of risk monitoring items associated with the nth risk monitoring item in the sewage treatment data; μ represents the conversion weight coefficient, and μ is a preset constant; SCR represents the comparison and screening function. When Mn = 0, then it is determined that ; otherwise, it is determined that .

[0072] S3. Based on the risk monitoring items of the obtained sewage treatment data and the risk assessment values of the corresponding risk monitoring items, extract the abnormal monitoring sources of the edge devices to which the sewage treatment data belongs, and generate the transmission feedback results of the corresponding edge devices;

[0073] The S3 includes:

[0074] Obtain the risk monitoring items of the sewage treatment data and the risk assessment values of the corresponding risk monitoring items, and record each risk monitoring item with a corresponding risk assessment value greater than the preset risk value as a monitoring risk source; record each risk monitoring item associated with the monitoring risk source in the sewage treatment data as a collaborative monitoring source; the abnormal monitoring sources of the edge devices to which the sewage treatment data belongs include the monitoring risk sources and collaborative monitoring sources of the corresponding sewage treatment data;

[0075] During the process of generating the transmission feedback results of the corresponding edge devices, record the transmission feedback result corresponding to the jth sensor in the ith edge device as F （i，j） , and the specific calculation formula is as follows:

[0076] ;

[0077] Among them, T（i，j） Denote the data acquisition interval duration corresponding to the j-th sensor in the i-th edge device before transmission feedback; BL （i，j） Denote the bias coefficient corresponding to the j-th sensor in the i-th edge device when it last received the transmission feedback result; BD （i，j） Denote the current bias coefficient of the j-th sensor in the i-th edge device; the bias coefficient is equal to the quotient obtained by dividing the bias factor of the corresponding sensor by the sum of the bias factors of all sensors in the corresponding edge device; when the sensor belongs to the abnormal monitoring source of the corresponding edge device, the bias factor of the corresponding sensor is equal to the risk assessment value of the corresponding sensor; when the sensor does not belong to the abnormal monitoring source of the corresponding edge device, the bias factor of the corresponding sensor is a preset constant.

[0078] S4. The edge device performs collaborative optimization on the sewage treatment data transmission set integrated at the current time according to the transmission feedback result received from the cloud server, and replaces the original sewage treatment data transmission set with the optimized sewage treatment data transmission set and transmits it to the cloud server;

[0079] When performing collaborative optimization on the sewage treatment data transmission set integrated at the current time in S4, obtain the sewage treatment data transmission set integrated at the current time, and denote the set obtained by sequentially summarizing the monitoring results corresponding to the same sensor at different times in the sewage treatment data transmission set integrated at the current time in chronological order as the first optimization alternative set of the corresponding sensor; obtain the acquisition time corresponding to each element in the first optimization alternative set of each sensor; denote the interval duration between the acquisition times corresponding to any two adjacent elements in the first optimization alternative set of each sensor as tg, and tg is a preset constant in the database; denote the integer multiple value with the smallest absolute value of the difference between the transmission feedback result corresponding to the k-th sensor among the integer multiple values of tg as the optimization time feedback value of the k-th sensor;

[0080] Mark the elements in the first optimization alternative set of the k-th sensor whose interval duration between the acquisition time corresponding to them and the acquisition time corresponding to the first element is an integer multiple of the optimization time feedback value of the k-th sensor;

[0081] After deleting the data in the sewage treatment data transmission set integrated at the current time that does not belong to the marked elements in the first optimization alternative set of each sensor, the obtained result is used as the collaborative optimization result of the sewage treatment data transmission set integrated at the current time.

[0082] In this embodiment, if the first optimization alternative set of sensor A in the sewage treatment data transmission set integrated at the current time is {h1, h2, h3, h4, h5}, and the first optimization alternative set of sensor B is {u1, u2, u3, u4, u5};

[0083] If the time acquisition times corresponding to h1 and u1 are both tc1; if the time acquisition times corresponding to h2 and u2 are both tc2; if the time acquisition times corresponding to h3 and u3 are both tc3; if the time acquisition times corresponding to h4 and u4 are both tc4; if the time acquisition times corresponding to h5 and u5 are both tc5; and the interval between any two adjacent acquisition times among tc1, tc2, tc3, tc4, tc5 is always tg;

[0084] If the optimized time feedback value of sensor A is tg, and if the optimized time feedback value of sensor B is twice tg, i.e., 2·tg;

[0085] Then the marked objects in {h1, h2, h3, h4, h5} are h1, h2, h3, h4, h5;

[0086] The marked objects in {u1, u2, u3, u4, u5} are u1, u3, u5;

[0087] Then in the collaborative optimization result of the sewage treatment data transmission set integrated at the current time, the first optimized alternative set of sensor A is {h1, h2, h3, h4, h5}, and the first optimized alternative set of sensor B is {u1, u3, u5}, that is, u2 and u4 in {u1, u2, u3, u4, u5} are deleted.

[0088] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device.

[0089] Finally, it should be noted that: The above are only preferred embodiments of the present invention and are not used to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A cloud-edge data collaboration method for sewage treatment, characterized in that: The method comprises the following steps: S1. The edge device collects data from the sewage treatment process in real time, pre-processes the collected sewage treatment data, integrates it into a sewage treatment data transmission set and transmits it to the cloud server; S2. The cloud server stores and extracts features from the sewage treatment data transmission set transmitted by the edge device, analyzes the sewage treatment status based on the feature extraction results of the sewage treatment data transmission set, and obtains the risk monitoring items of the sewage treatment data and the risk assessment values ​​of the corresponding risk monitoring items; S3. Based on the risk monitoring items of the obtained sewage treatment data and the risk assessment values ​​of the corresponding risk monitoring items, the abnormal monitoring sources of the edge devices in the sewage treatment data are extracted, and the transmission feedback results of the corresponding edge devices are generated; S4. The edge device collaboratively optimizes the sewage treatment data transmission set integrated at the current time according to the transmission feedback result received from the cloud server, and replaces the original sewage treatment data transmission set with the optimized sewage treatment data transmission set and transmits it to the cloud server; The risk monitoring items of the sewage treatment data obtained in S2 include each element in the features extracted from the sewage treatment data transmission set transmitted by the cloud server to the edge device; The calculation formula for the corresponding risk assessment value of the risk monitoring item of sewage treatment data is as follows: ； Among them, RV n represents the risk assessment value of the nth risk monitoring item of sewage treatment data; E n represents the abnormal factor corresponding to the nth risk monitoring item of sewage treatment data; the E n The value of is equal to the maximum value of the abnormal factors corresponding to the abnormal item types of the nth risk monitoring item of the sewage treatment data during the generation process, wherein the abnormal item types include abnormal monitoring data items, trend change abnormal data items and data collaborative association abnormal items, and different abnormal item types correspond to different preset abnormal factors in the database, and the abnormal factor is a constant; P n It indicates the ratio of the number of sensor monitoring data that does not belong to the preset monitoring interval of the corresponding sensor monitoring to the total number of corresponding sensor monitoring data in the latest preset time period for the nth risk monitoring item of sewage treatment data; PG （n，m） It indicates the ratio of the number of sensor monitoring data that does not belong to the preset monitoring interval of the corresponding sensor monitoring in the latest preset time period for the mth risk monitoring item in the sewage treatment data that is associated with the nth risk monitoring item to the total number of corresponding sensor monitoring data; Mn indicates the number of risk monitoring items that are associated with the nth risk monitoring item in the sewage treatment data; μ indicates the conversion weight coefficient, and μ is a preset constant; SCR indicates the comparison screening function, when Mn=0, it is determined Otherwise, it is judged ; The S3 includes: Obtain risk monitoring items of sewage treatment data and risk assessment values ​​of corresponding risk monitoring items, record each risk monitoring item whose corresponding risk assessment value is greater than a preset risk value as a monitoring risk source; record each risk monitoring item in the sewage treatment data that has an association relationship with the monitoring risk source as a collaborative monitoring source; the abnormal monitoring source of the edge equipment in the sewage treatment data includes the monitoring risk source and the collaborative monitoring source of the corresponding sewage treatment data; In the process of generating the transmission feedback result of the corresponding edge device, the transmission feedback result corresponding to the jth sensor in the i-th edge device is recorded as F （i，j） , the specific calculation formula is as follows: ； Among them, T （i，j） Indicates the data collection interval duration corresponding to the jth sensor in the i-th edge device before transmission feedback; BL （i，j） Indicates the bias coefficient corresponding to the previous transmission feedback result received by the jth sensor in the i-th edge device; BD （i，j） Represents the current bias coefficient of the jth sensor in the i-th edge device; the bias coefficient is equal to the quotient of the bias factor of the corresponding sensor divided by the sum of the bias factors of each sensor in the corresponding edge device; when the sensor belongs to the abnormal monitoring source of the corresponding edge device, the bias factor of the corresponding sensor is equal to the risk assessment value of the corresponding sensor; when the sensor does not belong to the abnormal monitoring source of the corresponding edge device, the bias factor of the corresponding sensor is a preset constant; When the integrated sewage treatment data transmission set at the current time is collaboratively optimized in S4, the integrated sewage treatment data transmission set at the current time is obtained, and the set of monitoring results corresponding to the same sensor at different times in the integrated sewage treatment data transmission set at the current time is summarized in chronological order as the first optimized candidate set of the corresponding sensor; the acquisition time corresponding to each element in the first optimized candidate set of each sensor is obtained; the interval between the acquisition times corresponding to any two adjacent elements in the first optimized candidate set of each sensor is recorded as tg, and tg is a constant preset in the database; the integer multiple value of the smallest absolute value of the difference between the transmission feedback result corresponding to the kth sensor among the integer multiple values ​​of tg is recorded as the optimized time feedback value of the kth sensor; Mark each element in the first optimization candidate set of the k-th sensor whose interval between the corresponding acquisition time and the corresponding acquisition time of the first element is an integer multiple of the optimization time feedback value of the k-th sensor; After deleting the data of the marked elements in the first optimization candidate set of each sensor that are not in the sewage treatment data transmission set integrated at the current time, the obtained result is used as the collaborative optimization result of the sewage treatment data transmission set integrated at the current time.

2. The cloud-edge data collaboration method for sewage treatment according to claim 1 is characterized by: The preprocessing process of the collected sewage treatment data in S1 includes supplementing the missing collected data by the average value of each collected data within the most recent preset time period of the same sensor; the sewage treatment data includes the monitoring results corresponding to different sensors in each sewage treatment equipment connected to the corresponding edge equipment, and the same sewage treatment equipment includes one or more sensors; the sewage treatment data transmission set is a summary set of sewage treatment data corresponding to each time point of the transmission in chronological order of collection time.

3. The cloud-edge data collaboration method for sewage treatment according to claim 1 is characterized in that: The features extracted by the cloud server in S2 from the sewage treatment data transmission set transmitted by the edge device include abnormal monitoring data items, trend change abnormal data items and data collaborative association abnormal items; each element item in the obtained feature extraction result corresponds to a sensor; The abnormal monitoring data item indicates that the corresponding sensor monitoring data contains a sensor that does not belong to the preset monitoring interval of the corresponding sensor monitoring; The trend change abnormal data item indicates a sensor in which the average value of the absolute value of the mutation coefficient corresponding to any two adjacent monitoring data in the monitoring data segment constituted by the maximum monitoring data and the minimum monitoring data among the various monitoring data of the same sensor is greater than the abnormal trend threshold; the absolute value of the mutation coefficient corresponding to the two monitoring data is equal to the absolute value of the quotient obtained by dividing the difference between the corresponding two monitoring data by the data collection time interval corresponding to the corresponding two monitoring data; the abnormal trend threshold is the average value of the absolute value of the mutation coefficient corresponding to any two adjacent monitoring data in the monitoring data segment constituted by the maximum monitoring data and the minimum monitoring data among the various monitoring data of the same sensor in the preset time period before the sensor monitoring data in the historical database does not belong to the preset monitoring interval of the corresponding sensor monitoring; The data collaborative association anomaly item represents an array consisting of mutation characteristic coefficients corresponding to each sensor with an associated relationship, and each sensor with an associated relationship whose maximum similarity with each preset array consisting of corresponding sensors in historical data is greater than a preset similarity; the association relationship between the sensors is preset in the database; The mutation characteristic coefficient corresponding to each sensor with an associated relationship represents the average value of the absolute value of the mutation coefficient corresponding to any two adjacent monitoring data corresponding to each sensor in the intersection of the acquisition time interval of the monitoring data segment corresponding to the maximum monitoring data and the minimum monitoring data of each sensor with an associated relationship; In the preset time period before each sensor monitoring data in the historical database that does not belong to the preset monitoring interval of the corresponding sensor monitoring, an array consisting of the average value of the absolute value of the mutation coefficient corresponding to any two adjacent monitoring data of each sensor that has an associated relationship with the corresponding sensor as an element is used as a preset array consisting of the corresponding sensors that have an associated relationship in the historical data; The similarity between two arrays is equal to the average similarity between the elements at corresponding positions in the two arrays. The similarity between the elements at corresponding positions is equal to the quotient of the minimum value divided by the maximum value of the elements at corresponding positions. When the maximum value of the elements at corresponding positions is 0, the similarity between the elements at corresponding positions is determined to be 1.

4. A cloud-edge data collaboration system for sewage treatment, applying a cloud-edge data collaboration method for sewage treatment as described in any one of claims 1-3, characterized in that: The system includes the following modules: An edge data integration module, which controls edge devices to collect data from the sewage treatment process in real time, pre-processes the collected sewage treatment data, integrates them into a sewage treatment data transmission set, and transmits them to the cloud server; A cloud data risk analysis module, which controls the cloud server to store and extract features of the sewage treatment data transmission set transmitted by the edge device, performs sewage treatment status analysis based on the feature extraction results of the sewage treatment data transmission set, and obtains risk monitoring items of the sewage treatment data and risk assessment values ​​of the corresponding risk monitoring items; An abnormal risk assessment feedback module, which extracts the abnormal monitoring source of the edge device in the sewage treatment data based on the risk monitoring items of the obtained sewage treatment data and the risk assessment values ​​of the corresponding risk monitoring items, and generates a transmission feedback result of the corresponding edge device; A cloud-edge collaborative transmission optimization module controls the edge device to collaboratively optimize the sewage treatment data transmission set integrated at the current time according to the transmission feedback results received from the cloud server, and replaces the original sewage treatment data transmission set with the optimized sewage treatment data transmission set and transmits it to the cloud server.

5. The cloud-edge data collaboration system for sewage treatment according to claim 4 is characterized by: The cloud data risk analysis module includes a feature extraction unit and a risk assessment unit. The feature extraction unit controls the cloud server to store and extract features from the sewage treatment data transmission set transmitted by the edge device; The risk assessment unit performs sewage treatment status analysis based on the feature extraction results of the sewage treatment data transmission set to obtain risk monitoring items of the sewage treatment data and risk assessment values ​​of the corresponding risk monitoring items.

6. The cloud-edge data collaboration system for sewage treatment according to claim 4 is characterized by: The abnormal risk assessment feedback module includes an abnormal monitoring source extraction unit and a transmission feedback generation unit. The abnormal monitoring source extraction unit extracts the abnormal monitoring source of the edge equipment in the sewage treatment data based on the risk monitoring items of the obtained sewage treatment data and the risk assessment values ​​of the corresponding risk monitoring items; The transmission feedback generation unit generates a transmission feedback result of the corresponding edge device according to the abnormal monitoring source extracted by the abnormal monitoring source extraction unit.

Images