Cloud edge data collaboration system and method for sewage treatment

Abstract

The invention relates to the technical field of sewage treatment cloud-side data collaborative management, in particular to a cloud-side data collaborative system and method for sewage treatment, and in the system, an abnormal risk assessment feedback module is based on risk monitoring items of obtained sewage treatment data and risk assessment values of the corresponding risk monitoring items; and extracting an abnormal monitoring source of the edge end equipment in the sewage treatment data, and generating a transmission feedback result of the corresponding edge end equipment. In the cloud edge data collaboration process, feature extraction and risk assessment are carried out on the sewage treatment data transmission set, the judgment of an abnormal monitoring source of the edge end equipment in the sewage treatment data is realized, and according to the generated transmission feedback result of the corresponding edge end equipment, the cloud edge data collaboration is realized. Collaborative optimization of the sewage treatment data transmission set integrated at the current time is realized, and the cloud edge data collaboration efficiency is ensured; according to the mode, the cloud realizes efficient processing and real-time response of data through cooperative work of the end server and the edge device.

Description

Technical Field

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

[0002] With the rapid development of the 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, it is difficult to meet application scenarios with high real-time requirements due to data transmission delays and bandwidth limitations; therefore, the cloud-edge data collaboration system came into being.

[0003] In the existing cloud-edge data collaboration system for sewage treatment, usually during the sewage treatment process, the edge device is responsible for real-time collection and processing of water quality data, while the cloud server is responsible for storage and analysis functions. Although this improves the processing efficiency of sewage treatment data and reduces data transmission latency, the existing technology cannot dynamically adjust the level of detail of local data sampling in the data to be transmitted by the edge device based on the feedback results of cloud data analysis during the cloud-edge data collaboration process, making it impossible to quickly and effectively lock and warn of abnormal faults in the sewage treatment equipment. Therefore, the existing technology has major defects. Summary of the invention

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

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a cloud-edge data collaboration method for sewage treatment, the method comprising 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 based on 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.

[0006] Furthermore, 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 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.

[0007] The edge device of the present invention represents an edge data processor, which may receive monitoring data from various sensors in a sewage treatment device or multiple bound sewage treatment devices at different time points; the sensor transmits monitoring data to the corresponding edge device once every preset time (tg), and the edge device integrates the received monitoring data from each sensor (sewage treatment data transmission set) and then transmits it to the cloud server.

[0008] Furthermore, 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; In the present invention, when the features extracted by the cloud server 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, the sensors with abnormal monitoring status are considered from three angles. In the first angle, the abnormal monitoring data items correspond to the actual abnormal monitoring results of the sensor; in the second angle, the trend change abnormal data items are considered by predicting the abnormal monitoring status of the sensor through the changing trend of the monitoring data; in the third angle, the data collaborative association abnormal items are considered from the comprehensive situation of the corresponding mutation characteristic coefficients of each sensor with an associated relationship.

[0009] 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.

[0010] Further, the risk monitoring items of the sewage treatment data obtained in S2 include various elements 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 nThe 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 .

[0011] Further, 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） It represents the current bias coefficient of the jth sensor in the ith 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.

[0012] Further, 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.

[0013] A cloud-edge data collaboration system for sewage treatment, the system comprising 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.

[0014] Furthermore, 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.

[0015] Furthermore, 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.

[0016] 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 abnormal monitoring source of the edge device in the sewage treatment data by performing feature extraction and 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 based on the transmission feedback results generated by the corresponding edge device, thereby ensuring the efficiency of cloud-edge data collaboration; this method realizes efficient data processing and real-time response through the collaborative work of the cloud-end server and the edge device. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying 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 of the present invention. In the accompanying drawings: Figure 1 It is a structural schematic diagram of a cloud-edge data collaboration system for sewage treatment according to the present invention; Figure 2 It is a flow chart of a cloud-edge data collaboration method for sewage treatment according to the present invention. DETAILED DESCRIPTION

[0018] 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 only 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.

[0019] See also Figure 1The present invention provides a technical solution: a cloud-edge data collaboration system for sewage treatment, the system comprising 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, wherein 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; An abnormal risk assessment feedback module, 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; 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.

[0020] like Figure 2 As shown, a cloud-edge data collaboration method for sewage treatment includes 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; 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.

[0021] 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; 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.

[0022] 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 .

[0023] 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; 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） It 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.

[0024] 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; 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.

[0025] In this embodiment, if the first optimized candidate set of sensor A in the sewage treatment data transmission set integrated at the current time is {h1, h2, h3, h4, h5}, the first optimized candidate set of sensor B is {u1, u2, u3, u4, u5}; If the time acquisition time corresponding to h1 and u1 is tc1; if the time acquisition time corresponding to h2 and u2 is tc2; if the time acquisition time corresponding to h3 and u3 is tc3; if the time acquisition time corresponding to h4 and u4 is tc4; if the time acquisition time corresponding to h5 and u5 is tc5; and the interval between any two adjacent acquisition times in tc1, tc2, tc3, tc4, tc5 is always tg; If the optimized time feedback value of sensor A is tg, if the optimized time feedback value of sensor B is twice tg, that is, 2·tg; Then the tag objects in {h1, h2, h3, h4, h5} are h1, h2, h3, h4, h5; The labeled objects in {u1, u2, u3, u4, u5} are u1, u3, u5; In the collaborative optimization result of the sewage treatment data transmission set integrated at the current time, the first optimization candidate set of sensor A is {h1, h2, h3, h4, h5}, and the first optimization candidate set of sensor B is {u1, u3, u5}, that is, u2 and u4 in {u1, u2, u3, u4, u5} are deleted.

[0026] 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.

[0027] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in 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 based on 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.

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 2 is characterized in that: 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 .

4. The cloud-edge data collaboration method for sewage treatment according to claim 3 is characterized by: 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） It represents the current bias coefficient of the jth sensor in the ith 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.

5. The cloud-edge data collaboration method for sewage treatment according to claim 2 is characterized by: 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.

6. The cloud-edge data collaboration method for sewage treatment according to claim 1 is characterized by: 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.

7. 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 1-6, 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.

8. The cloud-edge data collaboration system for sewage treatment according to claim 7, characterized in that: 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.

9. The cloud-edge data collaboration system for sewage treatment according to claim 7, characterized in that: 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