Intelligent water affair internet of things online monitoring system

Abstract

The application provides a kind of wisdom water affair internet of things online monitoring system, including multi-source data acquisition module, edge time calibration module, time sequence alignment processing module, abnormality collaborative discrimination module and data transmission and platform processing module;Through the unified calibration of the acquisition time of multi-source monitoring data, and based on the unified time axis, different categories of monitoring data are merged and aligned, and then the aligned multi-class monitoring data is associated with the change discrimination, and the abnormal identification result is output;The system can improve the problem of non-uniform time of multi-source data in existing wisdom water online monitoring, time sequence is easy to dislocation, which is beneficial to improve the correlation analysis accuracy and abnormal identification reliability between different categories of monitoring data.

Description

Technical Field

[0001] This invention relates to the field of smart water management online monitoring technology, and in particular to a smart water management Internet of Things (IoT) online monitoring system. Background Technology

[0002] As urban water supply, drainage, and pipeline network operation and management gradually develop towards informatization and intelligence, smart water systems typically set up pressure, flow, water level, water quality, and equipment status monitoring terminals in water supply networks, drainage networks, pumping stations, valve wells, water tanks, and related treatment nodes. The data collected by each monitoring terminal is then uploaded to the platform for centralized analysis and management via communication networks, in order to achieve online monitoring, anomaly warning, and remote supervision of the water system's operating status.

[0003] However, in practical applications, the above-mentioned online monitoring methods still have certain shortcomings. Because different monitoring terminals correspond to different monitoring objects and detection methods, the sampling periods for various types of data differ. Furthermore, the upload process is affected by factors such as communication delays, buffering and forwarding, and differences in platform reception rhythms. This can easily lead to inconsistent timestamps, inconsistent arrival times, and misaligned data sequences in the multi-source monitoring data received by the platform. Consequently, when comprehensively analyzing data such as pressure, flow rate, water level, water quality, and equipment status, it is often difficult to make corresponding judgments for different parameters under the same time reference. This can easily result in unclear parameter correlations and inaccurate correspondence of abnormal events, thus affecting the anomaly identification results and the accuracy of online monitoring.

[0004] Therefore, a smart water affairs IoT online monitoring system is provided. Summary of the Invention

[0005] In view of this, the present invention provides a smart water affairs IoT online monitoring system to solve the problem that the time of multi-source monitoring data in the existing smart water affairs IoT online monitoring system is inconsistent and the time sequence is easily misaligned, which makes it difficult to accurately correlate and analyze different types of monitoring data, thereby affecting the anomaly identification results and the accuracy of online monitoring.

[0006] The technical solution of the present invention is implemented as follows: a smart water affairs Internet of Things online monitoring system, including a multi-source data acquisition module, an edge time calibration module, a time sequence alignment processing module, an anomaly collaborative discrimination module, and a data transmission and platform processing module; The multi-source data acquisition module is used to acquire various types of monitoring data from the smart water system and generate corresponding original monitoring data. The edge time calibration module is connected to the multi-source data acquisition module and is used to uniformly calibrate the acquisition time corresponding to the original monitoring data to obtain calibrated monitoring data. The time-series alignment processing module is connected to the edge time calibration module and is used to construct a unified time axis based on the calibrated monitoring data and map different types of calibrated monitoring data to the unified time axis to obtain aligned monitoring data. The anomaly collaborative discrimination module is connected to the time-series alignment processing module and is used to discriminate the correlation and change relationships between different types of monitoring data based on the aligned monitoring data to obtain anomaly identification results. The data transmission and platform processing module is connected to the time-series alignment processing module and the anomaly collaborative discrimination module respectively and is used to receive the aligned monitoring data and the anomaly identification results and perform platform processing.

[0007] Furthermore, the monitoring data collected by the multi-source data acquisition module includes at least two of the following: pressure data, flow data, water level data, water quality data, and equipment status data. By incorporating different categories of operating parameters into a unified monitoring scope, a multi-source data foundation can be provided for subsequent time-series alignment and correlation determination.

[0008] Furthermore, the edge time calibration module is used to synchronize the local time of each acquisition terminal based on a unified time source, and to recalibrate the time identifier of the original monitoring data according to the synchronized time reference.

[0009] Furthermore, the unified time source is any one or more of the following: network time protocol time source, satellite time source, and platform standard time source.

[0010] Furthermore, the time-series alignment processing module includes a time axis construction unit and a window alignment unit. The time axis construction unit is used to generate a unified time axis based on the calibrated acquisition time, and the window alignment unit is used to map calibration monitoring data of different sampling periods to the unified time axis according to a preset time window.

[0011] Furthermore, the timing alignment processing module also includes a compensation processing unit, which is used to perform interpolation compensation, resampling processing, or truncation processing on data that does not fall within the preset time window.

[0012] Furthermore, the preset time window is a dynamic time window, and the timing alignment processing module is used to adjust the window width of the dynamic time window according to the sampling period differences, transmission delays, or data arrival intervals of different types of monitoring data.

[0013] Furthermore, the anomaly collaborative discrimination module includes a multi-parameter correlation analysis unit and an anomaly confirmation unit. The multi-parameter correlation analysis unit is used to establish the correlation and change relationship between different categories of monitoring data, and the anomaly confirmation unit is used to confirm the anomaly event based on the correlation and change relationship.

[0014] Furthermore, the anomaly collaborative discrimination module is used to output the anomaly identification result when at least two types of monitoring data simultaneously meet the corresponding anomaly conditions.

[0015] Furthermore, the system also includes an edge caching module, which is connected to the multi-source data acquisition module, the edge time calibration module and the data transmission and platform processing module, respectively. The edge caching module is used to cache the original monitoring data or calibration monitoring data locally when communication is abnormal, and to retransmit it in chronological order after communication is restored.

[0016] The embodiments of the present invention have the following advantages due to the adoption of the above technical solutions: I. This invention improves the problem of inconsistent time and misaligned time sequence of multi-source data in existing smart water management online monitoring systems by performing unified time calibration and unified time axis alignment on multi-source monitoring data, which is conducive to improving the correspondence accuracy between different types of monitoring data.

[0017] Second, this invention performs correlation discrimination based on aligned multi-class monitoring data, and outputs anomaly identification results when at least two classes of monitoring data simultaneously meet the corresponding anomaly conditions. This helps to reduce the interference of single parameter fluctuations on anomaly judgment and improve the stability of anomaly identification results.

[0018] Third, by setting up an edge caching module, this invention enables data generated during communication anomalies to be cached and retransmitted in chronological order, which helps maintain the continuity of data records on the platform side.

[0019] The above overview is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features of the invention will become readily apparent from the accompanying drawings and the following detailed description. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a block diagram of the system structure of the present invention. Detailed Implementation

[0022] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the following embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the scope of protection of the present invention. For those skilled in the art, conventional adjustments, equivalent substitutions, or simple modifications made to the technical solutions of the present invention without departing from the technical concept of the present invention should all be included within the scope of protection of the present invention.

[0023] like Figure 1 As shown, this embodiment provides a smart water affairs IoT online monitoring system, including a multi-source data acquisition module, an edge time calibration module, a time sequence alignment processing module, an anomaly collaborative discrimination module, a data transmission and platform processing module, and an edge caching module.

[0024] The multi-source data acquisition module is used to collect various types of monitoring data from the smart water system and generate corresponding raw monitoring data. The edge time calibration module is connected to the multi-source data acquisition module and is used to uniformly calibrate the acquisition time corresponding to the raw monitoring data to obtain calibrated monitoring data. The time sequence alignment processing module is connected to the edge time calibration module and is used to construct a unified time axis based on the calibrated monitoring data and map different types of calibrated monitoring data to the unified time axis to obtain aligned monitoring data. The anomaly collaborative discrimination module is connected to the time sequence alignment processing module and is used to discriminate the correlation and change relationship between different types of monitoring data based on the aligned monitoring data to obtain anomaly identification results. The data transmission and platform processing module is connected to the time sequence alignment processing module and the anomaly collaborative discrimination module respectively and is used to receive aligned monitoring data and anomaly identification results and perform platform processing. The edge caching module is connected to the multi-source data acquisition module, the edge time calibration module and the data transmission and platform processing module respectively and is used to cache the raw monitoring data or calibrated monitoring data locally when communication is abnormal and retransmit it in chronological order after communication is restored.

[0025] Example 1 In this embodiment, multi-source data acquisition modules are installed at water supply networks, pumping stations, valve wells, water tanks, and treatment nodes to collect pressure data, flow data, water level data, water quality data, and equipment status data. Equipment status data refers to the operational status data of pumping station equipment, valve equipment, or pressurizing equipment. Various monitoring terminals generate raw monitoring data according to their respective sampling cycles and record the corresponding acquisition time locally.

[0026] In this embodiment, the sampling period for pressure data, flow data, and equipment status data is 1–5 seconds, the sampling period for water level data is 5–30 seconds, and the sampling period for water quality data is 30–300 seconds. Because the sampling cycles of different monitoring terminals vary, and the data upload process is affected by communication delays, buffer forwarding, and link congestion, the raw monitoring data generated by the multi-source data acquisition module is not directly entered into unified analysis. Instead, it is first processed for time unification by the edge time calibration module.

[0027] The edge time calibration module is located near the monitoring terminal and is used to synchronize the local time of each acquisition terminal based on a unified time source. It then recalibrates the time signatures of the original monitoring data according to the synchronized time reference to obtain calibrated monitoring data. In this embodiment, the unified time source is a network time protocol (NTP) time source, but it can also be replaced with a satellite time source or a platform standard time source depending on the deployment scenario. After synchronization, the edge time calibration module rewrites the time signatures of the data generated by each acquisition terminal, ensuring that the calibrated monitoring data are under the same time reference. After edge time calibration, the time deviation between the acquisition terminals is controlled within ±1 to 3 seconds.

[0028] The calibration monitoring data, processed by the edge time calibration module, enters the time alignment processing module. The time alignment processing module includes a time axis construction unit, a window alignment unit, and a compensation processing unit. The time axis construction unit generates a unified time axis based on the calibrated acquisition time. The unified time axis can be continuously expanded according to a preset time step, and its nth time window is denoted as: in, Indicates the first A time window, Indicates the start time of the unified timeline. Indicates the width of the time window.

[0029] The window alignment unit is used to map calibration monitoring data from different sampling periods to a unified time axis according to a preset time window. When the sampling time of a certain calibration monitoring data is... And satisfy When this happens, the calibration monitoring data will be classified into the first... One time window; Using the above methods, pressure data, flow data, water level data, water quality data, and equipment status data from different sources and with different sampling periods can all be merged into the corresponding time window under a unified time axis, forming aligned monitoring data.

[0030] In this embodiment, the preset time window is a dynamic time window, and the window width is... The time window width ranges from 3 to 60 seconds. The time alignment processing module adjusts the dynamic time window width based on the differences in sampling periods, transmission delays, or data arrival intervals of different types of monitoring data. When the arrival intervals of various types of monitoring data are small, the time window width is set to a smaller value; when there is a significant upload lag or fluctuation in arrival intervals, the time window width is appropriately increased.

[0031] For data that does not fall within the target time window, the compensation processing unit performs compensation processing. This unit performs interpolation compensation, resampling, or truncation processing on the data that does not fall within the preset time window. For continuously changing data with relatively regular intervals between adjacent time points, linear interpolation compensation is used; for frequently generated data, resampling processing is used; and for locally repetitive or redundant data, truncation processing is used. After compensation processing, the calibration monitoring data of each category are re-categorized into the time window corresponding to the unified time axis to form complete aligned monitoring data.

[0032] After time-series alignment is completed, the aligned monitoring data enters the anomaly collaborative discrimination module. This module includes a multi-parameter correlation analysis unit and an anomaly confirmation unit. The multi-parameter correlation analysis unit establishes the correlation and change relationships between different categories of monitoring data, based on the correspondence of data within the same time window. Specifically, the multi-parameter correlation analysis unit correlates pressure data, flow data, water level data, water quality data, and equipment status data within the same time window with corresponding data from the previous time window or several previous time windows to obtain the correlation and change relationships between different categories of monitoring data.

[0033] The anomaly confirmation unit confirms the abnormal event based on the aforementioned correlation and change relationship. In this embodiment, the anomaly confirmation unit does not directly output the anomaly identification result based on a single category of monitoring data. Instead, it outputs the anomaly identification result when at least two categories of monitoring data simultaneously meet the corresponding anomaly conditions. For example, when pressure data and flow data simultaneously meet the corresponding anomaly conditions within the same time window, anomaly identification results are output; similarly, when water level data and equipment status data simultaneously meet the corresponding anomaly conditions within the same time window, anomaly identification results are also output. If only one type of monitoring data experiences local fluctuations within the current time window, while other categories of monitoring data do not show corresponding changes, no anomaly identification result is output within that time window, and the process continues in subsequent time windows for continuous discrimination.

[0034] In this embodiment, the alignment monitoring data and anomaly identification results are received by the data transmission and platform processing module and then processed by the platform. The data transmission and platform processing module includes data reception, data storage, data display, and alarm output processing. The platform receives and records the alignment monitoring data according to a unified timeline order, and simultaneously records and outputs the anomaly identification results. Since the data entering the platform has already undergone edge time calibration and unified timeline alignment, the platform no longer performs secondary time stitching on the original multi-source data, but directly completes the processing according to the unified timeline order.

[0035] In this embodiment, the edge caching module is used to maintain data retention during communication anomalies. When the communication link is normal, alignment monitoring data and anomaly identification results are uploaded to the data transmission and platform processing module in real time; when communication is abnormal, the edge caching module caches the original monitoring data or calibration monitoring data locally. The edge caching duration can be set from 10 minutes to 24 hours. The cached data is saved sequentially according to its corresponding time identifier. After communication is restored, the edge caching module retransmits the cached data to the data transmission and platform processing module in chronological order, thereby maintaining the consistency of the order in which the platform receives data before and after the communication anomaly.

[0036] Example 2 The difference between this embodiment and Embodiment 1 is that the edge time calibration module uses the platform standard time source and the network time protocol time source to synchronize time, and the dynamic time window in the time alignment processing module is adaptively adjusted according to the actual arrival interval of each type of monitoring data.

[0037] In this embodiment, the multi-source data acquisition module still collects pressure data, flow data, water level data, water quality data, and equipment status data. The edge time calibration module first receives the time reference from the platform's standard time source, and then uses the network time protocol time source as a calibration reference to synchronize the local time of each acquisition terminal. After synchronization is completed, the time stamp of the original monitoring data is recalibrated to obtain calibrated monitoring data.

[0038] The time-series alignment processing module adjusts the window width of the dynamic time window based on the arrival intervals of monitoring data of each category within multiple consecutive time windows. When a certain category of monitoring data experiences an arrival lag across multiple consecutive windows, the time window width is appropriately increased; when the arrival intervals of multiple categories of monitoring data return to a concentrated state, the time window width is correspondingly decreased. The window alignment unit works in conjunction with the compensation processing unit to complete the windowing and compensation processing of the calibration monitoring data, resulting in aligned monitoring data.

[0039] The anomaly collaborative discrimination module still establishes the correlation and change relationship between different categories of monitoring data based on aligned monitoring data, and outputs the anomaly identification result when at least two categories of monitoring data simultaneously meet the corresponding anomaly conditions. The processing methods of the data transmission and platform processing module and the edge caching module are the same as in Embodiment 1, and will not be repeated here.

[0040] Example 3 This embodiment illustrates the handling process of the edge caching module in communication anomaly scenarios.

[0041] In this embodiment, the multi-source data acquisition module continuously generates raw monitoring data, the edge time calibration module uniformly calibrates the acquisition time corresponding to the raw monitoring data, and the time alignment processing module uniformly aligns the calibrated monitoring data along the time axis. When the communication link is in normal condition, the aligned monitoring data and anomaly identification results are uploaded to the data transmission and platform processing module in real time.

[0042] When a communication anomaly occurs, the edge cache module switches to local cache mode. At this time, raw monitoring data generated by the multi-source data acquisition module or calibration monitoring data processed by the edge time calibration module is no longer directly uploaded, but instead written to the edge cache module. The edge cache module saves the data sequentially based on its corresponding timestamp. After communication is restored, the edge cache module retransmits the cached data to the data transmission and platform processing module according to the order of the timestamps. The platform receives and records the retransmitted data in a unified time order, thus maintaining the continuity of the data sequence during the anomaly and after recovery.

[0043] In operation, the multi-source data acquisition module first collects various types of monitoring data from the smart water system and generates corresponding raw monitoring data. The edge time calibration module uniformly calibrates the acquisition time corresponding to the raw monitoring data to obtain calibrated monitoring data. The time alignment processing module constructs a unified time axis based on the calibrated monitoring data and maps different types of calibrated monitoring data to the unified time axis. If necessary, the compensation processing unit performs interpolation compensation, resampling processing, or truncation processing on data that does not fall within the preset time window to obtain aligned monitoring data. The anomaly collaborative discrimination module judges the correlation and change relationship between different types of monitoring data based on the aligned monitoring data and outputs the anomaly identification result when at least two types of monitoring data simultaneously meet the corresponding anomaly conditions. The data transmission and platform processing module receives the aligned monitoring data and the anomaly identification result and performs platform processing. When communication is abnormal, the edge caching module caches the raw monitoring data or calibrated monitoring data locally and retransmits them in chronological order after communication is restored.

[0044] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various variations or substitutions within the technical scope disclosed in the present invention, and these should all be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A smart water affairs IoT online monitoring system, characterized in that, include: Multi-source data acquisition module, edge time calibration module, time sequence alignment processing module, anomaly collaborative discrimination module, and data transmission and platform processing module; The multi-source data acquisition module is used to collect various types of monitoring data from the smart water system and generate corresponding raw monitoring data. The edge time calibration module is connected to the multi-source data acquisition module and is used to uniformly calibrate the acquisition time corresponding to the original monitoring data to obtain calibrated monitoring data. The timing alignment processing module is connected to the edge timing calibration module and is used to construct a unified time axis based on the calibration monitoring data, and map different categories of calibration monitoring data to the unified time axis to obtain aligned monitoring data; The anomaly collaborative discrimination module is connected to the time-series alignment processing module and is used to discriminate the correlation and change relationship between different categories of monitoring data based on the aligned monitoring data to obtain anomaly identification results; The data transmission and platform processing module is connected to the timing alignment processing module and the anomaly collaborative discrimination module, respectively, and is used to receive the alignment monitoring data and the anomaly identification results and perform platform processing.

2. The smart water affairs IoT online monitoring system according to claim 1, characterized in that: The monitoring data collected by the multi-source data acquisition module includes at least two of the following: pressure data, flow data, water level data, water quality data, and equipment status data.

3. The smart water affairs IoT online monitoring system according to claim 1, characterized in that: The edge time calibration module is used to synchronize the local time of each acquisition terminal based on a unified time source, and to recalibrate the time identifier of the original monitoring data according to the synchronized time reference.

4. The smart water affairs IoT online monitoring system according to claim 3, characterized in that: The unified time source is any one or more of the following: network time protocol time source, satellite time source, and platform standard time source.

5. The smart water affairs IoT online monitoring system according to claim 1, characterized in that: The timing alignment processing module includes a time axis construction unit and a window alignment unit. The time axis construction unit is used to generate a unified time axis based on the calibrated acquisition time, and the window alignment unit is used to map calibration monitoring data of different sampling periods to the unified time axis according to a preset time window.

6. The smart water affairs IoT online monitoring system according to claim 5, characterized in that: The timing alignment processing module further includes a compensation processing unit, which is used to perform interpolation compensation, resampling processing, or truncation processing on data that does not fall within the preset time window.

7. The smart water affairs IoT online monitoring system according to claim 5, characterized in that: The preset time window is a dynamic time window, and the timing alignment processing module is used to adjust the window width of the dynamic time window according to the sampling period differences, transmission delays or data arrival intervals of different types of monitoring data.

8. The smart water affairs IoT online monitoring system according to claim 1, characterized in that: The anomaly collaborative discrimination module includes a multi-parameter correlation analysis unit and an anomaly confirmation unit. The multi-parameter correlation analysis unit is used to establish the correlation and change relationship between different categories of monitoring data, and the anomaly confirmation unit is used to confirm the anomaly event based on the correlation and change relationship.

9. The smart water affairs IoT online monitoring system according to claim 8, characterized in that: The anomaly collaborative discrimination module is used to output the anomaly identification result when at least two types of monitoring data simultaneously meet the corresponding anomaly conditions.

10. The smart water affairs IoT online monitoring system according to claim 1, characterized in that: It also includes an edge caching module, which is connected to the multi-source data acquisition module, the edge time calibration module and the data transmission and platform processing module, respectively. The edge caching module is used to cache the original monitoring data or calibration monitoring data locally when communication is abnormal, and to retransmit it in chronological order after communication is restored.

Images