Edge computing assisted internet of things sewage monitoring real-time early warning system and method

Abstract

The application discloses an edge computing auxiliary-based real-time early warning system and method for Internet of Things pollution monitoring, and belongs to the technical field of pollution monitoring and early warning. The system comprises an edge node configuration module, a monitoring behavior processing module, a delay overlap analysis module and an early warning analysis module. The method sets an edge node at the end of a pollution device and records interaction logs, generates a monitoring behavior set based on data transmission delay duration and maps the monitoring behavior set to a one-dimensional time axis; captures a delay overlap period to generate a period interaction feature set, constructs a two-dimensional coordinate system to obtain an interaction feature curve function; and realizes real-time early warning of pollution monitoring events by analyzing the Internet of Things connection fusion degree between edge nodes. When edge computing is used to reduce data transmission delay, the time axis mapping and fusion degree analysis can improve the accuracy of Internet of Things pollution monitoring and early warning, and the application is suitable for various industrial real-time pollution monitoring scenes.

Description

Technical Field

[0001] This invention relates to the field of sewage discharge monitoring and early warning technology, specifically to an IoT-based real-time sewage discharge monitoring and early warning system and method assisted by edge computing. Background Technology

[0002] In the fields of industrial production and environmental protection, pollution discharge monitoring is a crucial link in preventing environmental pollution and ensuring ecological security. Traditional pollution discharge monitoring systems mostly adopt a centralized data processing architecture, in which all data collected by front-end monitoring equipment is uploaded to a remote cloud or central server for analysis and processing. However, this architecture has significant drawbacks: on the one hand, pollution discharge equipment is often distributed in a relatively dispersed manner, and the data transmission distance is long, which can easily lead to high transmission latency and poor real-time performance, making it difficult to meet the needs of rapid early warning for sudden pollution discharge events; on the other hand, centralized processing has high network bandwidth requirements, and when the number of monitoring nodes increases, network congestion is likely to occur, leading to data loss or analysis delays, affecting the reliability of monitoring.

[0003] In existing technologies, some sewage discharge monitoring solutions attempt to introduce Internet of Things (IoT) technology to achieve device interconnection. However, they lack effective analysis of the coordination of data transmission between nodes, cannot accurately identify the correlation of command transmission and reception status between devices based on the sewage discharge process, and are prone to false alarms or missed alarms. They are difficult to adapt to the dynamic monitoring needs of complex sewage discharge scenarios.

[0004] The rise of edge computing technology offers a new approach to solving these problems. By pushing data processing capabilities down to edge nodes closer to monitoring equipment, it can significantly reduce transmission latency. However, current edge computing-based sewage monitoring solutions lack a robust collaborative analysis mechanism, making it impossible to quantify connectivity and integration through inter-node interaction characteristics, thus hindering accurate real-time early warning. Summary of the Invention

[0005] The purpose of this invention is to provide an IoT-based real-time early warning system and method for monitoring sewage discharge with edge computing assistance, so as to solve the problems mentioned in the background art.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0007] This IoT-based sewage monitoring and early warning system, assisted by edge computing, includes: an edge node configuration module, a monitoring behavior processing module, a delay overlap analysis module, and an early warning analysis module.

[0008] The edge node configuration module is used to set edge nodes and record interaction logs;

[0009] The monitoring behavior processing module is used to generate monitoring status labels, generate monitoring behavior sets, and construct a one-dimensional time axis;

[0010] The delay overlap analysis module is used to project the data transmission delay duration, capture the delay overlap period, and generate a period interaction feature set;

[0011] The early warning analysis module is used to construct a two-dimensional coordinate system of interactive features, generate interactive feature curve functions, analyze the degree of IoT connectivity integration, and perform real-time early warning marking.

[0012] Furthermore, the edge node configuration module includes a node setting unit and a log recording unit;

[0013] The node setting unit is used to set edge nodes at the sending or receiving end of the sewage discharge equipment and to manage the edge nodes in a unified manner.

[0014] The log recording unit is used to establish an edge data warehouse to store monitoring data and interaction logs of each edge node. The interaction logs include the data transmission delay of sewage monitoring events and monitoring instructions.

[0015] Furthermore, the monitoring behavior processing module includes a status tag unit and a time axis construction unit;

[0016] The status tag unit generates monitoring status tags based on edge nodes and data transmission delay duration, and generates a set of monitoring behaviors with edge nodes as the receiving end.

[0017] The time axis construction unit is used to construct a one-dimensional time axis and map the start and end times of data transmission delay to the one-dimensional time axis.

[0018] Furthermore, the delay overlap analysis module includes a duration projection unit and a feature set generation unit;

[0019] The duration projection unit is used to project the data transmission delay duration of each data transmission in the monitoring behavior set onto a one-dimensional time axis, and capture the delay overlap period of each projection segment.

[0020] The feature set generation unit acquires all delay overlap periods and generates a time-period interaction feature set containing the total number of each projection segment, based on the monitoring behavior set and the delay overlap period.

[0021] Furthermore, the early warning analysis module includes a curve function unit and a fusion degree analysis unit;

[0022] The curve function unit is used to construct a two-dimensional coordinate system for interactive features, map the coordinate points of the time-period interactive feature set to the coordinate system, and generate interactive feature curve functions.

[0023] The integration analysis unit analyzes the integration degree of IoT connections between edge nodes based on the interaction feature curve function, presets the integration degree threshold, and performs real-time early warning marking for sewage monitoring events.

[0024] A real-time early warning method for IoT-based sewage monitoring with edge computing assistance, comprising the following steps:

[0025] Step S1: Based on the sewage discharge equipment transmitter or receiver, set up edge nodes and record the interaction logs of the edge nodes. The interaction logs include the data transmission delay of sewage discharge monitoring events and monitoring commands.

[0026] Step S2: Based on edge nodes and data transmission delay duration, generate monitoring status tags. In sewage discharge monitoring events, the monitoring center with edge nodes as the receiving end is used, and a set of monitoring behaviors is generated based on the monitoring status tags. Construct a one-dimensional time axis and map the data transmission delay duration onto the one-dimensional time axis.

[0027] Step S3: Project the data transmission delay duration of each data transmission delay duration in the monitoring behavior set onto the one-dimensional time axis, and capture the delay overlap period of the projection segment of each data transmission delay duration on the one-dimensional time axis; based on the monitoring behavior set and the delay overlap period, in the sewage discharge monitoring event, obtain all the delay overlap periods locked by the monitoring center with the edge node as the receiving end, and generate a period interaction feature set;

[0028] Step S4: Construct a two-dimensional coordinate system for interaction features, and map the interaction feature coordinate points, which are composed of the total number of each projection segment in the time period interaction feature set, to the two-dimensional coordinate system for interaction features to obtain the interaction feature curve function of the edge node when the monitoring center is the edge node as the receiving end; based on the interaction feature curve function, analyze the degree of IoT connection integration between edge nodes, and mark the sewage monitoring events in real time.

[0029] Furthermore, the specific implementation process of step S1 includes:

[0030] In the sewage discharge process, edge nodes are set and uniformly coded. The i-th edge node is denoted as... Establish an edge data warehouse, which stores monitoring data from each edge node. This monitoring data is transmitted via monitoring commands from a wastewater discharge equipment sender and receiver. Each edge node corresponds to one wastewater discharge equipment sender or receiver. If the receiver is an edge node... Then the sending end is excluding edge nodes. At least one edge node or a combination of multiple edge nodes other than the one mentioned above;

[0031] The edge data warehouse also stores interaction logs for each edge node. These logs record pollution monitoring events, each containing the data transmission delay of a monitoring command. This delay is the time elapsed from when the sending end issues the monitoring command to when the receiving end receives it. Therefore, the edge node... As the receiving end, and the j-th edge node When acting as the sender, the resulting data transmission delay is denoted as... ;

[0032] It should be noted that data transmission latency is a core indicator reflecting the communication efficiency and collaborative status between edge nodes, including:

[0033] The core objective of wastewater discharge monitoring is to promptly detect abnormal wastewater discharge events. Data transmission delay directly affects the timeliness of early warnings. If the delay is too long, abnormal data may not be analyzed in a timely manner, leading to missed intervention opportunities. By recording the delay between the receiving end (such as the edge node of the monitoring center) and the sending end (such as the edge node of the wastewater discharge equipment), the real-time performance of the communication link can be directly quantified, thereby meeting the basic requirements of real-time monitoring.

[0034] In IoT-based sewage monitoring, multiple edge nodes need to achieve collaborative monitoring through command interaction (such as device status synchronization and data cross-verification). Fluctuations or anomalies in latency (such as a sudden increase) may reflect node failure, network congestion, or device malfunction (data-driven representation through interactive characteristic curve functions). Thus, latency can objectively determine whether the nodes are "effectively cooperating".

[0035] Furthermore, the specific implementation process of step S2 includes:

[0036] The pollution discharge monitoring events are compiled in a unified manner, and the r-th pollution discharge monitoring event is denoted as... , with edge nodes It serves as the monitoring center at the receiving end and statistically analyzes sewage monitoring events based on data transmission delay. All sending ends under the following generate a set of monitoring behaviors, denoted as Where n represents the total number of edge nodes, Indicates the monitoring status label;

[0037] The data transmission delay is mapped to a one-dimensional time axis as follows:

[0038] The start and end times of the data transmission delay are plotted on the one-dimensional time axis, and the coordinates of the start and end times of the data transmission delay are connected on the one-dimensional time axis. The data transmission delay is then mapped on the one-dimensional time axis. The start time of the data transmission delay is the time when the sending end issues the monitoring command, and the end time of the data transmission delay is the time when the receiving end receives the monitoring command issued by the sending end.

[0039] Furthermore, the specific implementation process of step S3 includes:

[0040] On a one-dimensional time axis, the monitoring behavior set Each data transmission delay duration is projected onto the one-dimensional time axis, and the overlapping delay period of the projected segments of each data transmission delay duration on the one-dimensional time axis is captured. The overlapping delay period consists of at least two overlapping projection segments of data transmission delay durations on the one-dimensional time axis. If the data transmission delay duration... With data transmission delay If there are overlapping projection segments on the one-dimensional time axis, then the data transmission delay duration is locked. With data transmission delay The time interval with delay overlap on a one-dimensional time axis is denoted as ,in, This represents the x-th delayed overlapping period on a one-dimensional time axis;

[0041] Based on the monitoring behavior set and the overlapping time period of the delay, in the pollution monitoring event Next, obtain edge nodes. For the monitoring center at the receiving end, all overlapping delay time periods are locked, and a time period interaction feature set is generated, denoted as... Where y represents the total number of overlapping delay periods, Represented by edge nodes The time period of delay overlap locked when the monitoring center of the receiving end is used. The total number of projection segments included, and In the formula, if the data transmission delay time is With data transmission delay Overlapping projection segments exist on a one-dimensional time axis. and overlapping projection segments During the delay overlap period Within the interval, let Otherwise .

[0042] Furthermore, the specific implementation process of step S4 includes:

[0043] A two-dimensional coordinate system for interactive features is constructed, wherein the horizontal and vertical coordinates of the two-dimensional coordinate system correspond, respectively, to the sequence number x of the delayed overlapping time period and the total number of projection segments. The coordinate points constituting the interactive features are denoted as Time-based interaction feature set The interactive feature coordinate points, composed of the total number of each projection segment, are mapped to the interactive feature two-dimensional coordinate system, and the interactive feature coordinate points are sequentially and smoothly connected to obtain edge nodes. When the monitoring center of the receiving end is an edge node The interaction characteristic curve function, denoted as ;

[0044] Based on the interaction characteristic curve function, analyze the degree of IoT connectivity integration between edge nodes:

[0045] ;

[0046] In the formula, Represented by edge nodes When the monitoring center of the receiving end is an edge node The interactive characteristic curve function;

[0047] A preset threshold for IoT connectivity integration will be set. If the value is less than or equal to the IoT connectivity integration threshold, then the pollution monitoring event... Real-time early warning markers should be displayed; otherwise, no sewage discharge monitoring events should be monitored. Real-time early warning marking;

[0048] It should be noted that the degree of IoT connectivity integration between edge nodes is essentially a quantitative indicator of the communication coordination and correlation between nodes. Overlapping projection segments, delayed overlap periods, and the total number of projection segments can reflect this coordination from both time and interaction intensity dimensions, including:

[0049] The data transmission delay duration is projected onto a one-dimensional time axis to form a "projection segment" (corresponding to a communication process within a certain period of time). If multiple projection segments overlap on the time axis (i.e., the delay overlap period), it indicates that multiple edge nodes are communicating and interacting within the same time period. The higher the overlap frequency, the stronger the business correlation between nodes. Thus, the overlapping projection segments reflect the temporal correlation of node communication.

[0050] The number and duration of the delay overlap period directly reflect the frequency of interaction between nodes. For example, the more overlapping projection segments in a certain period (i.e., more nodes communicate at the same time), the higher the node collaboration demand and the stronger the business coupling in that period. Thus, the density of collaborative interaction can be characterized by the delay overlap period.

[0051] The "total number of projection segments" (i.e. the number of projection segments contained in a certain delayed overlapping period) in the time-period interaction feature set is a direct quantification of the interaction intensity between nodes. The larger the total number, the denser the data exchange between nodes in that period and the closer the collaborative relationship. Thus, the interaction intensity is quantified by the total number of projection segments.

[0052] By mapping the "delayed overlapping period number" and the "total number of projected segments" to a two-dimensional coordinate system, the generated interaction feature curve function can intuitively reflect the dynamic change trend of node interaction. The more similar the curve shape of the nodes, the more consistent their communication rules and collaborative modes are, and the higher the degree of connection integration. Conversely, the degree of integration is low. The degree of integration is calculated by the difference of curve function. In essence, it is to evaluate the node collaboration by quantifying the curve similarity, so as to realize the correlation between interaction feature curve and degree of integration.

[0053] Compared with existing technologies, the beneficial effects achieved by this invention are as follows: This invention sets edge nodes at the sewage discharge equipment end and records interaction logs, generates a set of monitoring behaviors based on data transmission delay duration and maps it to a one-dimensional time axis; captures overlapping delay periods to generate a time period interaction feature set, constructs a two-dimensional coordinate system to obtain the interaction feature curve function; and realizes real-time early warning of sewage discharge monitoring events by analyzing the IoT connectivity fusion degree between edge nodes. Furthermore, while using edge computing to reduce data transmission delay, it improves the accuracy of IoT sewage discharge monitoring and early warning through time axis mapping and fusion degree analysis, making it suitable for various industrial sewage discharge real-time monitoring scenarios. Attached Figure Description

[0054] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used together with the embodiments of the invention to explain the invention and do not constitute a limitation thereof.

[0055] Figure 1 This is a schematic diagram illustrating the steps of the IoT-based real-time early warning method for sewage monitoring based on edge computing, as described in this invention. Detailed Implementation

[0056] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0057] In this first embodiment: an IoT sewage monitoring real-time early warning system based on edge computing is provided. The system includes: an edge node configuration module, a monitoring behavior processing module, a delay overlap analysis module, and an early warning analysis module.

[0058] The edge node configuration module is used to set up edge nodes and record interaction logs;

[0059] The edge node configuration module includes a node setting unit and a log recording unit.

[0060] The node setting unit is used to set edge nodes at the sending or receiving end of the sewage discharge equipment and to manage the edge nodes in a unified manner.

[0061] The log recording unit is used to establish an edge data warehouse to store monitoring data and interaction logs of each edge node. The interaction logs include the data transmission delay of sewage monitoring events and monitoring instructions.

[0062] The monitoring behavior processing module is used to generate monitoring status labels, generate monitoring behavior sets, and construct a one-dimensional time axis;

[0063] The monitoring behavior processing module includes a status label unit and a time axis construction unit;

[0064] The status tag unit generates monitoring status tags based on edge nodes and data transmission delay duration, and generates a set of monitoring behaviors with edge nodes as the receiving end.

[0065] The time axis construction unit is used to construct a one-dimensional time axis and map the start and end times of data transmission delay to the one-dimensional time axis.

[0066] The delay overlap analysis module is used to project data transmission delay duration, capture delay overlap periods, and generate a period interaction feature set.

[0067] The delay overlap analysis module includes a duration projection unit and a feature set generation unit.

[0068] The duration projection unit is used to project the data transmission delay duration of each data transmission in the monitoring behavior set onto a one-dimensional time axis, and capture the delay overlap period of each projection segment;

[0069] The feature set generation unit, based on the monitoring behavior set and the delay overlap period, obtains all delay overlap periods and generates a time period interaction feature set containing the total number of each projection segment;

[0070] The early warning analysis module is used to construct a two-dimensional coordinate system of interaction features, generate interaction feature curve functions, analyze the degree of IoT connectivity integration, and perform real-time early warning marking.

[0071] The early warning analysis module includes a curve function unit and a fusion degree analysis unit.

[0072] The curve function unit is used to construct a two-dimensional coordinate system for interactive features, mapping the coordinate points of the time-segment interactive feature set to the coordinate system and generating interactive feature curve functions;

[0073] The integration analysis unit analyzes the integration degree of IoT connections between edge nodes based on the interaction feature curve function, presets the integration degree threshold, and marks pollution monitoring events in real time.

[0074] Please see Figure 1 In this second embodiment: a real-time early warning method for IoT sewage monitoring based on edge computing is provided, applicable to the first embodiment above. The method includes the following steps:

[0075] Step S1: Based on the sewage discharge equipment transmitter or receiver, set up edge nodes and record the interaction logs of the edge nodes. The interaction logs include the data transmission delay of sewage discharge monitoring events and monitoring commands.

[0076] For example, in the sewage discharge process, edge nodes are set and uniformly coded, with the i-th edge node denoted as... Establish an edge data warehouse, which stores monitoring data from each edge node. This monitoring data is transmitted via monitoring commands from the wastewater discharge equipment's sending and receiving ends. Each edge node corresponds to either a wastewater discharge equipment sending end or a wastewater discharge equipment receiving end. If the receiving end is an edge node... Then the sending end is excluding edge nodes. At least one edge node or a combination of multiple edge nodes other than the one mentioned above;

[0077] The edge data warehouse also stores interaction logs for each edge node. These logs record pollution monitoring events, each containing the data transmission delay of the monitoring command. This delay is the time from when the sending end issues the monitoring command to when the receiving end receives it. Therefore, the edge node... As the receiving end, and the j-th edge node When acting as the sender, the resulting data transmission delay is denoted as... ;

[0078] For example, taking the sewage discharge monitoring scenario of a chemical industrial park as an example, the park contains 5 sewage discharge outlets (corresponding to 5 sewage discharge equipment transmitters) and 1 central monitoring center (corresponding to the receiver). It is necessary to monitor parameters such as sewage flow and pollutant concentration at each sewage discharge outlet in real time and issue timely warnings when the equipment malfunctions.

[0079] When configuring and logging edge nodes, edge nodes N1-N5 were deployed at the five sewage outlets. The monitoring center, acting as the receiving edge node N0, recorded interaction logs through the edge data warehouse. After 72 hours of continuous monitoring, the data collection frequency of each node was stable at 1 time / second, and the data transmission delay ranged from 0.2 to 1.5 seconds.

[0080] Step S2: Based on edge nodes and data transmission delay duration, generate monitoring status tags. In sewage discharge monitoring events, the monitoring center with edge nodes as the receiving end is used, and a set of monitoring behaviors is generated based on the monitoring status tags. Construct a one-dimensional time axis and map the data transmission delay duration onto the one-dimensional time axis.

[0081] For example, pollution discharge monitoring events are uniformly compiled, and the r-th pollution discharge monitoring event is denoted as... , with edge nodes It serves as the monitoring center at the receiving end and statistically analyzes sewage monitoring events based on data transmission delay. All sending ends under the following generate a set of monitoring behaviors, denoted as Where n represents the total number of edge nodes, Indicates the monitoring status label;

[0082] The data transmission delay is mapped to a one-dimensional time axis as follows:

[0083] The start and end times of the data transmission delay are plotted on a one-dimensional time axis, and the coordinates of the start and end times of the data transmission delay are connected on the one-dimensional time axis. The data transmission delay is then mapped on the one-dimensional time axis. The start time of the data transmission delay is the time when the sending end issues the monitoring command, and the end time of the data transmission delay is the time when the receiving end receives the monitoring command issued by the sending end.

[0084] For example, when processing monitoring behavior and constructing the timeline, for a certain pollution discharge monitoring event M1 (monitoring pollutant concentration), with N0 as the receiving end, the transmitted data of N1-N5 are counted to generate a monitoring behavior set. The generated monitoring status labels need to be accurately associated with each node and the corresponding delay duration.

[0085] Step S3: Project the data transmission delay duration of each data transmission delay duration in the monitoring behavior set onto a one-dimensional time axis, and capture the delay overlap period of the projection segment of each data transmission delay duration on the one-dimensional time axis; based on the monitoring behavior set and the delay overlap period, in the sewage discharge monitoring event, obtain all the delay overlap periods locked by the monitoring center with the edge node as the receiving end, and generate a period interaction feature set;

[0086] For example, on a one-dimensional time axis, the set of monitored behaviors is... Each data transmission delay duration is projected onto a one-dimensional time axis, and the overlapping delay periods of the projected segments of each data transmission delay duration on the one-dimensional time axis are captured. Each overlapping delay period consists of at least two overlapping projection segments of data transmission delay durations on the one-dimensional time axis. If the data transmission delay duration... With data transmission delay If there are overlapping projection segments on the one-dimensional time axis, then the data transmission delay duration is locked. With data transmission delay The time interval with delay overlap on a one-dimensional time axis is denoted as ,in, This represents the x-th delayed overlapping period on a one-dimensional time axis;

[0087] Based on the monitoring behavior set and the overlapping time period of the delay, in the pollution monitoring event Next, obtain edge nodes. For the monitoring center at the receiving end, all overlapping delay time periods are locked, and a time period interaction feature set is generated, denoted as... Where y represents the total number of overlapping delay periods, Represented by edge nodes The time period of delay overlap locked when the monitoring center of the receiving end is used. The total number of projection segments included, and In the formula, if the data transmission delay time is With data transmission delay Overlapping projection segments exist on a one-dimensional time axis. and overlapping projection segments During the delay overlap period Within the interval, let Otherwise ;

[0088] For example, during delay overlap analysis and feature set generation, the delay durations of N1-N5 in event M1 are projected onto the time axis to capture overlapping time periods. A total of 3 delay overlap time periods O1-O3 are identified, where O1 contains 3 projection segments (N1, N2, N3), O2 contains 2 projection segments (N3, N4), and O3 contains 2 projection segments (N4, N5).

[0089] Step S4: Construct a two-dimensional coordinate system for interaction features. Map the interaction feature coordinate points, which are composed of the total number of each projection segment in the time period interaction feature set, to the two-dimensional coordinate system for interaction features to obtain the interaction feature curve function of the edge node when the edge node is the monitoring center with the edge node as the receiving end. Based on the interaction feature curve function, analyze the degree of IoT connection integration between edge nodes and mark the sewage discharge monitoring events in real time.

[0090] For example, a two-dimensional coordinate system for interactive features is constructed, where the horizontal and vertical coordinates correspond, respectively, to the sequence number x of the delayed overlapping time period and the total number of projection segments. The coordinate points constituting the interactive features are denoted as Time-based interaction feature set The interactive feature coordinate points, composed of the total number of projection segments, are mapped to the interactive feature two-dimensional coordinate system, and then the interactive feature coordinate points are smoothly connected sequentially to obtain the edge nodes. When the monitoring center of the receiving end is an edge node The interaction characteristic curve function, denoted as ;

[0091] Based on the interaction characteristic curve function, analyze the degree of IoT connectivity integration among edge nodes. In the formula, Represented by edge nodes When the monitoring center of the receiving end is an edge node The interactive characteristic curve function;

[0092] A preset threshold for IoT connectivity integration will be set. If the value is less than or equal to the IoT connectivity integration threshold, then the pollution monitoring event... Real-time early warning markers should be displayed; otherwise, no sewage discharge monitoring events should be monitored. Real-time early warning marking;

[0093] For example, in the fusion degree analysis and early warning marking, a two-dimensional coordinate system is constructed (the horizontal axis is the overlapping time period number x, and the vertical axis is the total number of projected segments). The feature set is mapped to generate the interactive feature curve function H(N0). The preset fusion degree threshold is 0.6. If the calculated connection fusion degree between N1 and N2 is 0.75 (higher than the threshold, normal), and the connection fusion degree between N4 and N5 is 0.52 (lower than the threshold), an early warning mark is triggered. On-site investigation reveals that the transmission module of N5 has a fault.

[0094] It should be noted that low integration means asynchronous communication and failure of coordination between nodes, which may be a precursor to equipment failure, network interruption or abnormal sewage discharge. It is necessary to trigger an early warning. By analyzing the integration distribution, weak nodes or time periods can be identified, which can guide the optimization of edge node deployment (such as increasing node density) and network bandwidth adjustment. Since equipment is distributed in a dispersed manner and there are many interference factors in industrial sewage discharge scenarios, integration can quantify the system's anti-interference ability and ensure stable monitoring in dynamic environments.

[0095] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0096] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended 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 make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. An edge computing assistance-based real-time early warning method for sewage monitoring of an Internet of Things, characterized in that, The method comprises the following steps: Step S1: based on the emission equipment sending end or the emission equipment receiving end, setting an edge node, and recording the interaction log of the edge node, and the interaction log contains the data transmission delay duration of the emission monitoring event and the monitoring instruction; Step S2: based on the edge node and the data transmission delay duration, generating a monitoring state label, in the emission monitoring event, taking the edge node as the receiving end of the monitoring center, and based on the monitoring state label, generating a monitoring behavior set; constructing a one-dimensional time axis, and mapping the data transmission delay duration to the one-dimensional time axis; Step S3: projecting each data transmission delay duration in the monitoring behavior set to the one-dimensional time axis, and capturing the delay overlap period of each projection segment on the one-dimensional time axis; based on the monitoring behavior set and the delay overlap period, in the emission monitoring event, acquiring all the delay overlap periods locked by the monitoring center taking the edge node as the receiving end, and generating a period interaction feature set; Step S4: constructing an interaction feature two-dimensional coordinate system, mapping the interaction feature coordinate points in the period interaction feature set composed of the total number of each projection segment to the interaction feature two-dimensional coordinate system, obtaining the interaction feature curve function of the edge node when the edge node is taken as the receiving end of the monitoring center; based on the interaction feature curve function, analyzing the Internet of Things connection fusion degree between the edge nodes, and marking the real-time early warning of the emission monitoring event. 2.The edge computing assistant based real-time warning method for sewage monitoring of Internet of Things according to claim 1, characterized in that, The specific implementation process of step S1 comprises: In the pollution discharge process, an edge node is set, and the edge node is uniformly coded, and the i-th edge node is denoted as ; an edge data warehouse is established, and monitoring data of each edge node is stored in the edge data warehouse, and the monitoring data is sent and received by a pollution discharge equipment; wherein one edge node corresponds to one pollution discharge equipment sending end or pollution discharge equipment receiving end; if the receiving end is an edge node , then the sending end is at least one edge node or a combination of multiple edge nodes other than the edge node . The edge data warehouse also stores interaction logs of each edge node, and the interaction logs record pollution monitoring events, and the pollution monitoring events contain data transmission delay time of monitoring instructions, the data transmission delay time is the length of time from the sending end issuing a monitoring instruction to the receiving end receiving the monitoring instruction, and the edge node As a receiving end, and the jth edge node As a sending end, the generated data transmission delay time is recorded as . 3.The edge computing assistant based real-time warning method for sewage monitoring of Internet of Things according to claim 2, characterized in that, The specific implementation process of step S2 comprises: A unified record is made for the pollution monitoring event, and the rth pollution monitoring event is recorded as The edge node is the monitoring center of the receiving end, and based on the data transmission delay duration, the total sending end of the pollution monitoring event is generated to generate a monitoring behavior set, recorded as , wherein n represents the total number of edge nodes, represents a monitoring state label; The data transmission delay duration is mapped to the one-dimensional time axis in the following manner: The start time and end time of the data transmission delay duration are respectively depicted on the one-dimensional time axis, and the coordinate points of the start time and end time of the data transmission delay duration are connected on the one-dimensional time axis, so that the data transmission delay duration is mapped on the one-dimensional time axis, wherein the start time of the data transmission delay duration is the time when the monitoring instruction is sent by the sending end, and the end time of the data transmission delay duration is the time when the monitoring instruction sent by the sending end is received by the receiving end. 4.The edge computing assistant based real-time warning method for sewage monitoring of Internet of Things according to claim 3, characterized in that, The specific implementation process of step S3 comprises: On a one-dimensional time axis, the monitoring behavior set Each data transmission delay duration is projected onto the one-dimensional time axis, and the overlapping delay period of the projected segments of each data transmission delay duration on the one-dimensional time axis is captured. The overlapping delay period consists of at least two overlapping projection segments of data transmission delay durations on the one-dimensional time axis. If the data transmission delay duration... With data transmission delay If there are overlapping projection segments on the one-dimensional time axis, then the data transmission delay duration is locked. With data transmission delay The time interval with delay overlap on a one-dimensional time axis is denoted as ,in, This represents the x-th delayed overlapping period on a one-dimensional time axis; Based on the monitoring behavior set and the delay overlap period, in the pollution monitoring event Next, all delay overlap periods are obtained when the edge node is locked by the monitoring center of the receiving end, and a period interaction feature set is generated, denoted as , wherein y represents the total number of delay overlap periods, wherein represents the total number of projection segments contained in the delay overlap period when the edge node is locked by the monitoring center of the receiving end . , wherein, if the data transmission delay duration is greater than the data transmission delay duration , the projection segment exists in the one-dimensional time axis , and the overlapping projection segment is in the delay overlap period , then , otherwise . 5.The edge computing assistant based real-time warning method for sewage monitoring of Internet of Things according to claim 4, characterized in that, The specific implementation process of step S4 comprises: A two-dimensional coordinate system for interactive features is constructed, wherein the horizontal and vertical coordinates of the two-dimensional coordinate system correspond, respectively, to the sequence number x of the delayed overlapping time period and the total number of projection segments. The coordinate points constituting the interactive features are denoted as Time-based interaction feature set The interactive feature coordinate points, composed of the total number of each projection segment, are mapped to the interactive feature two-dimensional coordinate system, and the interactive feature coordinate points are sequentially and smoothly connected to obtain edge nodes. When the monitoring center of the receiving end is an edge node The interaction characteristic curve function, denoted as ; Based on the interaction characteristic curve function, analyze the Internet of Things connection fusion degree between edge nodes , wherein, indicates the interaction characteristic curve function of the edge node when the edge node is a receiving end of a monitoring center A preset threshold for IoT connectivity integration will be set. If the value is less than or equal to the IoT connectivity integration threshold, then the pollution monitoring event... Real-time early warning markers should be displayed; otherwise, no sewage discharge monitoring events should be monitored. Real-time early warning marking.

6. The edge computing assisted Internet of Things sewage monitoring real-time early warning system according to any one of claims 1-5, characterized in that, The system comprises an edge node configuration module, a monitoring behavior processing module, a delay overlap analysis module, and a early warning analysis module; The edge node configuration module is used for setting an edge node and recording an interaction log; The monitoring behavior processing module is used for generating a monitoring state label, generating a monitoring behavior set, and constructing a one-dimensional time axis; The delay overlap analysis module is used for projecting a data transmission delay duration, capturing a delay overlap period, and generating a period interaction feature set; The early warning analysis module is used for constructing an interaction feature two-dimensional coordinate system, generating an interaction feature curve function, analyzing an Internet of Things connection fusion degree, and marking a real-time early warning. 7.The edge computing assistant based real-time warning system for sewage monitoring of Internet of Things according to claim 6, characterized in that: The edge node configuration module comprises a node setting unit and a log recording unit; The node setting unit is used for setting an edge node at the emission equipment sending end or receiving end, and uniformly managing the edge node; The log recording unit is configured to establish an edge data warehouse, store monitoring data and interaction logs of each edge node, and the interaction logs include data transmission delay duration of the pollution monitoring event and the monitoring instruction. 8.The edge computing assistant based real-time warning system for sewage monitoring of Internet of Things according to claim 6, characterized in that: The monitoring behavior processing module includes a state label unit and a time axis construction unit. The state label unit generates a monitoring state label based on the edge node and the data transmission delay duration, and generates a monitoring behavior set with the edge node as a receiving end. The time axis construction unit is configured to construct a one-dimensional time axis and map a start time and an end time of the data transmission delay duration to the one-dimensional time axis. 9.The edge computing assistant based real-time warning system for sewage monitoring of Internet of Things according to claim 6, characterized in that: The delay overlap analysis module includes a duration projection unit and a feature set generation unit. The duration projection unit is configured to project each data transmission delay duration in the monitoring behavior set to the one-dimensional time axis, and capture a delay overlap period of each projection segment. The feature set generation unit is configured to obtain all delay overlap periods based on the monitoring behavior set and the delay overlap period, and generate a period interaction feature set including a total number of each projection segment. 10.The edge computing assistant based real-time warning system for sewage monitoring of Internet of Things according to claim 6, characterized in that: The early warning analysis module includes a curve function unit and a fusion degree analysis unit. The curve function unit is configured to construct an interaction feature two-dimensional coordinate system, map coordinate points of the period interaction feature set to the coordinate system, and generate an interaction feature curve function. The fusion degree analysis unit is configured to analyze an Internet of Things connection fusion degree between the edge nodes based on the interaction feature curve function, preset a fusion degree threshold, and mark the pollution monitoring event for real-time early warning.

Images