Intelligent water affair monitoring method and system based on digital twinning

Abstract

The invention relates to the technical field of data analysis, in particular to an intelligent water affair monitoring method and system based on digital twinning, and the method comprises the steps: obtaining the abnormal degree of all kinds of water affair data at each moment according to the historical data of all kinds of water affair data, obtaining association degrees among the various water affair data and abnormal independence of the various water affair data at various moments; derived data of each device and cause data of various water affair data, direct influence devices and indirect influence devices are obtained, and the abnormal degree, the abnormal independence and the correlation degree between the water affair data of the water affair data are combined. And obtaining the fault factor of each direct influence device and the fault factor of each indirect influence device of the water affair data at each moment so as to obtain a fault device, and marking the fault device in the digital twinborn model of the water affair system. According to the invention, by analyzing the association between different water affair data in the water affair system, the fault in the water affair system is accurately monitored and positioned.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and particularly to a smart water monitoring method and system based on digital twin. Background Art

[0002] Traditional water monitoring methods mainly rely on distributed sensors, manual inspections, and data aggregation to process and monitor water data. In traditional water monitoring systems, data is often collected at a fixed sampling frequency, and there is a certain delay in data transmission and processing, resulting in the inability to promptly reflect the dynamic changes of the water system in case of emergencies. At the same time, traditional detection systems mainly focus on the recording and display of the current situation, making it difficult to achieve homomorphic guidelines, fault prediction, and early warning responses based on real-time data, and difficult to meet the requirements of urban water environment safety and optimal water resource allocation. That is, the traditional method of monitoring and locating faults in the water system does not consider the interaction between various process links in the water system and cannot accurately monitor and locate faults in the water system. Summary of the Invention

[0003] The present invention provides a smart water monitoring method and system based on digital twin to solve the existing problems: the traditional method of monitoring and locating faults in the water system does not consider the interaction between various process links in the water system and cannot accurately monitor and locate faults in the water system.

[0004] The smart water monitoring method and system based on digital twin of the present invention adopt the following technical solutions: An embodiment of the present invention provides a smart water monitoring method based on digital twin, and the method includes the following steps: Obtain various water data in each module within the water system; According to the historical data of various water data in each module, obtain the degree of abnormality of various water data in each module at each moment, and obtain the degree of correlation between various water data in each module; according to the degree of abnormality of various water data in each module at each moment and the degree of correlation between various water data in each module, obtain the abnormal independence of various water data in each module at each moment; Obtain the derived data of each device in all modules, the cause data of various water data in all modules, the directly affected devices, and the indirectly affected devices, and combine the abnormal independence of various water data in each module at each moment, the degree of abnormality of various water data in each module at each moment, and the degree of correlation between various water data in each module to obtain the fault factors of each directly affected device and the fault factors of each indirectly affected device of various water data in each module at each moment; Based on the failure factors of the direct impact devices and the indirect impact devices for various water service data in each module at each moment, obtain the faulty devices in each module and mark the faulty devices in the digital twin model of the water service system.

[0005] Preferably, the specific method for obtaining the degree of abnormality of various water service data in each module at each moment includes: For the th moment, the th module, and the th type of water service data, obtain all the th type of water service data in the th module in history. Using all the th type of water service data in the th module in history and the th type of water service data in the th module at the th moment as the data set, obtain the LOF value of the th type of water service data in the th module at the th moment through the LOF outlier detection algorithm, and use it as the degree of abnormality of the th type of water service data in the th module at the th moment.

[0006] Preferably, the specific method for obtaining the correlation degree between various water service data in each module includes: Obtain the degree of abnormality of all types of water service data in all modules at all historical moments. For the th type of water service data in the th module and the th type of water service data in the th module; take the absolute value of the Pearson correlation coefficient between the degree of abnormality of all the th type of water service data in the th module at all historical moments and the degree of abnormality of all the th type of water service data in the th module at all historical moments as the correlation degree between the th type of water service data in the th module and the th type of water service data in the th module.

[0007] Preferably, the specific method for obtaining the anomaly independence of various water service data in each module at each moment includes: Preset an anomaly degree threshold and the influence time range For the th moment, for the th module, for the th type of water service data, if the abnormal degree of the th type of water service data in the th module at the th moment is greater than or equal to , then all the moments within the first minutes before the th moment are recorded as the influence moments of the th moment, and all types of water service data in the modules before the th module are recorded as the cause data of the th type of water service data in the th module; According to the correlation degree between the th type of water service data in the th module and its cause data, combined with the abnormal degrees of the th type of water service data in the th module at the influence moments of the th moment and its cause data, obtain the abnormal independence of the th type of water service data in the th module at the th moment. Its specific calculation formula is: In the formula, represents the abnormal independence of the th type of water service data in the th module at the th moment; represents the abnormal degree of the th type of water service data in the th module at the th moment; represents the number of types of cause data of the th type of water service data in the th module; represents the number of influence moments of the th moment; represents the correlation degree between the th type of water service data in the th module and its th type of cause data; represents the th influence moment of the th moment, for the th type of water service data in the th module, for the The abnormality degree of various cause data; Represents the absolute value function; Represents the linear normalization function.

[0008] Preferably, the specific method for obtaining the derived data of each device in all modules, the cause data of various water service data in all modules, the directly affected devices, and the indirectly affected devices includes: Obtain the water service data affected by each device in all modules in the water service system; For the th device in the th module, record the water service data affected by the th device in the th module as the derived data of the th device in the th module; For the th water service data in the th module, record the device in the th module that affects the th water service data as the directly affected device of the th water service data in the th module; and record the directly affected device of the cause data of the th water service data in the th module as the indirectly affected device of the th water service data in the th module.

[0009] Preferably, the specific method for obtaining the failure factors of the directly affected devices and the indirectly affected devices of various water service data in each module at each moment includes: For any water service data in any module at any moment, if the abnormality degree of the water service data in the module at the moment is greater than or equal to , then according to the abnormality degree of the water service data and its cause data in the module at the moment, the correlation degree between the water service data and its cause data in the module at the moment, and combining the abnormality independence of the water service data in the module at the moment, obtain the failure factors of each directly affected device of the water service data in the module at the moment; According to the abnormality degree of the derived data of the indirectly affected device of the water service data in the module at the moment, the correlation degree between the derived data of the indirectly affected device and the water service data in the module at the moment, and combining the abnormality independence of the water service data in the module at the moment, obtain the failure factors of each indirectly affected device of the water service data in the module at the moment.

[0010] Preferably, the specific calculation formula for obtaining the failure factors of each directly influencing device in the water service data in the module at the moment includes: In the formula, represents the th failure factor of the directly influencing device in the water service data in the module at the moment; represents the anomaly independence of the water service data in the module at the moment; represents the number of derivative data of the th directly influencing device in the water service data in the module; represents the anomaly degree of the th derivative data of the th directly influencing device in the water service data in the module at the moment; represents the number of types of cause data of the water service data in the module; represents the number of influencing moments at the moment; represents the th module, the correlation degree between the th type of water service data and its th type of cause data; represents the anomaly degree of the th cause data of the water service data in the module at the th influencing moment at the moment; represents the linear normalization function.

[0011] Preferably, the specific calculation formula for obtaining the failure factors of each indirectly influencing device in the water service data in the module at the moment includes: In the formula, represents the th failure factor of the indirectly influencing device in the water service data in the module at the moment; represents the anomaly independence of the water service data in the module at the moment; represents the number of derivative data of the th indirectly influencing device in the water service data in the module at the moment; represents the number of influencing moments at the moment; represents the th influencing moment at the moment, the correlation degree between the water service data in the module and its th derivative data of the th indirectly influencing device; indicating the th influencing moment of the water service data in the module at the moment, the th indirectly influencing device, and the abnormality degree of the derived data; indicating a linear normalization function.

[0012] Preferably, the specific method for obtaining the faulty devices in each module includes: Presetting a fault factor threshold , when the abnormality degree of any water service data in any module at any moment is greater than or equal to , obtaining the fault factors of each direct device and indirect device of the water service data in the module at the moment, and recording the device with the largest fault factor and the device with a fault factor greater than or equal to as faulty devices.

[0013] Another embodiment of the present invention provides a digital twin-based intelligent water service monitoring system, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of any one of the above digital twin-based intelligent water service monitoring methods are implemented.

[0014] The beneficial effects of the technical solution of the present invention are as follows: Through the historical data of various water service data, the present application obtains the abnormality degree of various water service data at each moment, and obtains the correlation degree between various water service data and the abnormality independence of various water service data at each moment. Since when a certain water service data in a certain module in the water service system is abnormal, the more likely it is to cause other water service data in all modules to be abnormal, it indicates that the correlation degree between various water service data in each module of the water service system is stronger. After obtaining the correlation degree between water service data, it is possible to evaluate whether the deviation of water service data from the normal value in the module is affected by the water service data in other modules or the devices in this module, so as to obtain the abnormality independence of water service data; Obtaining the derived data of each device, the cause data of various water service data, the direct influencing devices, and the indirect influencing devices. When a device fails, all the derived data of the faulty device will be affected. Therefore, further combining the abnormality degree, abnormality independence, and correlation degree between water service data, the fault factors of each direct influencing device and each indirect influencing device of water service data at each moment can be obtained, so as to obtain the faulty devices and mark the faulty devices in the digital twin model of the water service system. The present application analyzes the correlation between different water service data in the water service system to improve the accuracy of locating faulty devices in the water service system. Description of the Drawings

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0016] Figure 1 It is a flowchart of the steps of the intelligent water service monitoring method based on digital twin of the present invention. Specific implementation manners

[0017] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following will, in conjunction with the accompanying drawings and preferred embodiments, describe in detail the specific implementation manners, structures, features, and effects of the intelligent water service monitoring method and system based on digital twin proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0018] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0019] The following will specifically describe the specific solutions of the intelligent water service monitoring method and system based on digital twin provided by the present invention in conjunction with the accompanying drawings.

[0020] Please refer to Figure 1 , which shows a flowchart of the steps of the intelligent water service monitoring method based on digital twin provided by an embodiment of the present invention. The method includes the following steps: Step S001: Obtain various water service data in each module within the water service system.

[0021] It should be noted that the water service system, as a complete water treatment system, includes but is not limited to a water intake module, a coagulation module, a sedimentation module, a filtration module, a disinfection module, and a water supply module; a failure in each module will affect the subsequent modules, resulting in abnormal water service data in the subsequent modules. Therefore, it is not possible to accurately obtain the location of the failure in the water service system simply by whether the water service data at each location is abnormal. Therefore, the present invention proposes an intelligent water service monitoring method based on digital twin.

[0022] It should be further noted that the digital twin model of the water service system can comprehensively and accurately reflect the physical state of the water service system by collecting and integrating multi-dimensional data in real time. Through the digital twin model of the water service system, the water flow movement, water quality change, equipment operation status, etc. in the water service system can be simulated to reflect the current state and operation trend of the system in real time. Further, through the deep learning analysis and tracing of real-time data and historical data, the fault location in the water service system can be accurately located, so as to promote the water service system to achieve digital, intelligent and efficient monitoring and management. Therefore, it is first necessary to collect water service data in each module of the water service system.

[0023] Specifically, various water service data sensors are installed in each module of the water service system to collect various water service data in each module at each moment.

[0024] It should be noted that in this embodiment, various water service data are collected at intervals of 0.1 second, and the various water service data sensors include, but are not limited to, flow data, water pressure data, pH value, turbidity and other data.

[0025] Thus, various water service data in each module of the water service system are obtained.

[0026] Step S002: According to the historical data of various water service data in each module, obtain the degree of abnormality of various water service data in each module at each moment, and obtain the degree of correlation between various water service data in each module; according to the degree of abnormality of various water service data in each module at each moment and the degree of correlation between various water service data in each module, obtain the abnormal independence of various water service data in each module at each moment.

[0027] It should be noted that after the water service data in each module of the water service system are obtained, the water service data in each module of the water service system can be input into the digital twin model of the water service system to monitor whether there is a fault in the water service system and accurately locate the position where the fault occurs in the water service system; and this embodiment, as a smart water service monitoring method based on digital twins, specifically refers to the method of monitoring and locating the fault position of the water service system through the digital twin model of the water service system after the water service data in each module of the water service system are input into the digital twin model of the water service system.

[0028] It should be further noted that as a complete water treatment system, each module of the water service system jointly constitutes a complete water treatment process: from the water intake module to the coagulation module, from the coagulation module to the sedimentation module, from the sedimentation module to the filtration module, from the filtration module to the disinfection module, and from the disinfection module to the water supply module. When any fault occurs in any module, it will cause some water service data in the subsequent modules of that module to change. For example, if the dosage of the coagulant in the coagulation module of the water service system is insufficient, it will lead to too high turbidity of the water body in the subsequent sedimentation module, and further cause too large differential pressure of the filter in the subsequent filtration module. At this time, although there is no fault in the filtration module, abnormal water service data is collected by the filtration module. Therefore, simply based on the location of the sensor collecting abnormal data, the fault location cannot be accurately determined. It is necessary to analyze the correlation degree between various water service data in each module to accurately locate the fault location in the water service system.

[0029] Specifically, for the th moment, the th module, and the th type of water service data, obtain all the th type of water service data in the th module in history. Using all the th type of water service data in the th module in history and the th moment, the th module, and the th type of water service data as a data set, use the LOF outlier detection algorithm to obtain the LOF value of the th moment, the th module, and the th type of water service data, which is used as the outlier degree of the th moment, the th module, and the th type of water service data. Since the LOF outlier detection algorithm is a well-known existing technology, it will not be elaborated in this embodiment; Similarly, obtain the outlier degree of all water service data in all modules at all historical moments. For the th module, the th type of water service data and the th module, the th type of water service data (where and can be equal, and and can be equal); compare the outlier degree of all the th type of water service data in the th module at all historical moments with the outlier degree of all the th type of water service data in the The absolute value of the Pearson correlation coefficient between the degrees of abnormality of various water service data is used as the degree of association between the th type of water service data in the th module and the th type of water service data in the

[0030] th module. Since the Pearson correlation coefficient is a well-known existing technology, it will not be elaborated in this embodiment.

[0031] It should be noted that when a certain type of water service data in a module of the water service system is abnormal, the more likely it is to cause abnormalities in other water service data in all modules, indicating that the degree of association between various water service data in each module of the water service system is stronger. Therefore, in this embodiment, the Pearson correlation coefficient of various water service data in each module in terms of the degree of abnormality is used as the degree of association between various water service data in each module.

[0032] Preferably, in a specific embodiment of the present invention, an abnormality degree threshold and an influence time range are preset. The specific values of the and can be set according to the actual situation, and there are no strict requirements in this embodiment. In this embodiment, and are taken as examples for description. For the th moment, the th type of water service data in the th module, if the abnormality degree of the th moment, the th type of water service data in the th module is greater than or equal to , then all the moments within the first th moment are recorded as the influence moments of the th moment, and all types of water service data in the modules before the th module are recorded as the cause data of the th type of water service data in the th module; According to the th type of water service data in the th module, the The degree of association between a certain water service data and its cause data, combined with the th moment of the influencing moment, in the th module, for the th water service data and the degree of abnormality of its cause data, to obtain the th moment, in the th module, for the th water service data, the abnormal independence, and its specific calculation formula is: In the formula, represents the abnormal independence of the th water service data in the th module at the th moment; represents the degree of abnormality of the th water service data in the th module at the th moment; represents the number of types of cause data of the th water service data in the th module; represents the number of influencing moments at the th moment; represents the degree of association between the th water service data and its th cause data in the th module; represents the degree of abnormality of the th cause data of the th influencing moment at the th moment, in the th water service data in the th module; represents the absolute value function; represents the linear normalization function, and its specific normalization range is for all abnormal data .

[0033] It should be noted that the abnormal independence of water service data indicates whether the abnormality of the water service data is caused by the influence of other water service data. The greater the abnormal independence of the water service data, the less the abnormality of the water service data is caused by the influence of other water service data; cause data refers to the data that can affect the th water service data in the th module; and the degree of association between cause data and the th water service data in the th module is the degree to which cause data can affect the th water service data in the The degree of water service data; and since it takes a certain amount of time for the cause data to affect the water service data in the subsequent modules, this embodiment presets an influence time range, and evaluates the anomaly independence of the water service data according to the anomaly degree of the cause data within the influence time range.

[0034] It should be further noted that when the th water service data in the th module deviates from the normal data at the influence moment of the th moment, the more it can affect the cause data of the th water service data in the th module, and the smaller the difference in anomaly degree between the cause data and the th water service data in the th module at the th moment, the more likely it is that the water service data in the module before the th module causes the th water service data in the th module to be abnormal.

[0035] Thus, the anomaly independence of various water service data in each module at each moment is obtained.

[0036] Step S003: Obtain the derived data of each device in all modules, the cause data of various water service data in all modules, the directly affected devices and the indirectly affected devices, and combine the anomaly independence of various water service data in each module at each moment, the anomaly degree of various water service data in each module at each moment, and the correlation degree between various water service data in each module to obtain the failure factors of each directly affected device and the failure factors of each indirectly affected device of various water service data in each module at each moment.

[0037] It should be noted that when a certain water service data in a certain module at a certain moment is abnormal data, it indicates that a failure has occurred in the water service system. And the smaller the anomaly independence of the water service data, the more likely the reason for the anomaly of the water service data is affected by the water service data in other modules, that is, the more likely the failure in the water service system is located in other modules. At the same time, since there are various devices in each module of the water service system, and each device can affect multiple water service data. For example, the dosing pump in the coagulation module will affect the turbidity and pH value of the water body in the coagulation module. Therefore, it is necessary to combine the water service data affected by each device in each module according to the anomaly independence of the abnormal water service data to accurately locate the failure location in the water service system.

[0038] Specifically, obtain the water service data affected by each device in all modules of the water service system; For the th device in the th module, the The water service data affected by the th device in the th module is recorded as the derived data of the th device in the th module; For the th type of water service data in the th module, the device in the th module that affects the th type of water service data is recorded as the direct influencing device of the th type of water service data in the th module; and the direct influencing device of the cause data of the th type of water service data in the th module is recorded as the indirect influencing device of the th type of water service data in the

[0039] It should be noted that the direct influencing device of water service data is the device that can directly affect the water service data, while the indirect influencing device of water service data is the device that indirectly affects the water service data through the technological process of the water service system. When a device fails, all the derived data of the faulty device will be affected, so the fault location in the water service system can be located based on this.

[0040] Preferably, in a specific embodiment of the present invention, for any water service data in any module at any moment, if the abnormal degree of the water service data in the module at the moment is greater than or equal to , then according to the abnormal degrees of the water service data and its cause data in the module at the moment, the correlation degree between the water service data and its cause data in the module at the moment, and combining with the abnormal independence of the water service data in the module at the moment, the fault factors of each direct influencing device of the water service data in the module at the moment are obtained, and its specific calculation formula is: In the formula, represents the fault factor of the th direct influencing device of the water service data in the module at the moment; represents the abnormal independence of the water service data in the module at the moment; represents the number of derived data of the th direct influencing device of the water service data in the module; represents the abnormal degree of the th derived data of the th direct influencing device of the water service data in the module at the moment; Indicates the number of types of cause data of the water service data in the module; Indicates the number of influencing moments at the said moment; Indicates the th module and the th type of water service data and the degree of association between it and its th type of cause data; Indicates the abnormality degree of the th type of cause data of the water service data in the module at the th influencing moment at the said moment; Indicates a linear normalization function, and its specific normalization range is all the directly influencing devices of the water service data in the module at the said moment .

[0041] It should be noted that the failure factor of the directly influencing device represents the possibility of the device malfunctioning. When the device malfunctions, all its derived data will be affected, resulting in a large abnormality degree of all its derived data, that is the larger the value of is, the more likely the device is to malfunction. Also, since the malfunction of the derived data of the device may be caused by the abnormality of the cause data of the derived data, it is necessary to perform constraints according to the degree of association between the derived data and its cause data, combined with the abnormality degree of the cause data of the derived data, that is the larger the value of

[0042] and the smaller the value of

[0043] the more likely the device is to malfunction. In the formula, indicates the failure factor of the th indirectly influencing device of the water service data in the module at the said moment; Indicates the abnormal independence of the water service data in the module at the time; Indicates the first water service data in the module at the time The number of derived data that indirectly affects the device; The number of moments of influence representing the said moment; Indicates the time The water affairs data in the module at the impact moment and its The first one that indirectly affects the equipment The degree of association between the derived data; Indicates the time The first water service data in the module at the impact moment The first one that indirectly affects the equipment The degree of abnormality of the derived data; represents a linear normalization function, and its specific normalization range is all the water service data in the module at the time that directly affects the equipment .

[0044] It should be noted that the failure factor that indirectly affects the equipment indicates the possibility of failure of the equipment. When the equipment fails, all the derived data of the equipment will be affected, resulting in a large degree of abnormality in all the derived data of the equipment. At the same time, the derived data of the equipment must have a strong correlation with the abnormal data that deviates from the normal range. Therefore, The larger the value is, the more likely the device is to fail, and the smaller the abnormal independence of the water service data in the module at the moment is, the more likely it is that the indirect device causes the abnormal water service data. Therefore The smaller the value of, the more likely the indirect impact device is to fail.

[0045] At this point, the failure factors of each direct device and indirect device of each water service data in each module at each time are obtained.

[0046] Step S004: According to the failure factors of each directly affecting device and each indirectly affecting device of various water service data in each module at each moment, the faulty device in each module is obtained, and the faulty device is marked in the digital twin model of the water service system.

[0047] It should be noted that, by obtaining the fault factors of each direct device and indirect device of various water data in each module at each moment through step S003, the fault location in the water system can be accurately located according to the fault factors of each direct device and indirect device of various water data in each module at each moment.

[0048] Specifically, a fault factor threshold is preset , The specific value can be set according to the actual situation, and this embodiment does not make a rigid requirement. In this embodiment, is taken as an example for description. When the abnormality degree of any water service data in any module at any moment is greater than or equal to , obtain the failure factors of each direct device and indirect device of the water service data in the module at the moment, and record the device with the largest failure factor and the device with a failure factor greater than or equal to as the failed device, and mark the failed device in the digital twin model of the water service system.

[0049] Another embodiment of the present invention provides a smart water service monitoring system based on digital twins, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the digital twin-based smart water service monitoring method in steps S001 to S004.

[0050] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A smart water monitoring method based on digital twins, characterized in that, The method includes the following steps: Obtain various water service data in each module within the water service system; Based on the historical data of various water service data in each module, obtain the degree of abnormality of various water service data in each module at each moment, and obtain the degree of association between various water service data in each module; According to the degree of abnormality of various water service data in each module at each moment and the degree of association between various water service data in each module, obtain the abnormal independence of various water service data in each module at each moment; Obtain the derived data of each device in all modules, the cause data of various water service data in all modules, the directly affected devices, and the indirectly affected devices, and combine the abnormal independence of various water service data in each module at each moment, the degree of abnormality of various water service data in each module at each moment, and the degree of association between various water service data in each module to obtain the fault factors of each directly affected device and each indirectly affected device of various water service data in each module at each moment; Based on the fault factors of each directly affected device and each indirectly affected device of various water service data in each module at each moment, obtain the faulty devices in each module, and mark the faulty devices in the digital twin model of the water service system.

2. The intelligent water service monitoring method based on digital twin according to claim 1, characterized in that, The specific method for obtaining the degree of abnormality of various water service data in each module at each moment includes: For the th moment, for the th module, for the th type of water service data, obtain all the th type of water service data in the th module in history. Using all the th type of water service data in the th module in history, all the th type of water service data in the th module at the th moment as a data set, use the LOF outlier detection algorithm to obtain the LOF value of the th type of water service data in the th module at the th moment, as the degree of abnormality of the th type of water service data in the th module at the th moment.

3. The intelligent water service monitoring method based on digital twin according to claim 1, wherein The specific method for obtaining the degree of association between various water service data in each module includes: Obtain the abnormality levels of all types of water service data in all modules at all historical moments. For the th module, the th type of water service data and the th module, the th type of water service data; Take the absolute value of the Pearson correlation coefficient between the abnormality levels of the th module, the th type of water service data at all historical moments and the abnormality levels of the th module, the th type of water service data at all historical moments as the degree of association between the th module, the th type of water service data and the th module, the th type of water service data.

4. The intelligent water monitoring method based on digital twin according to claim 1, characterized in that, The specific method for obtaining the abnormal independence of various water service data in each module at each moment includes: Preset an anomaly degree threshold And the influence time range , for the th moment, the th module, and the th type of water service data. If the anomaly degree of the th moment, the th module, and the th type of water service data is greater than or equal to , then record all the moments within the first minutes before the th moment as the influence moments of the th moment, and record all the water service data in the modules before the th module as the cause data of the th module and the th type of water service data; According to the degree of association between the th type of water service data and its cause data in the th module, combined with the degree of abnormality between the th type of water service data and its cause data in the th module at the th moment of influence, obtain the abnormal independence of the th type of water service data in the th module at the th moment. Its specific calculation formula is: Wherein, represents the abnormal independence of the th type of water service data in the th module at the th moment; represents the abnormal degree of the th type of water service data in the th module at the th moment; represents the number of types of cause data of the th type of water service data in the th module; represents the number of influencing moments at the th moment; represents the correlation degree between the th type of water service data and its th type of cause data in the th module; represents the abnormal degree of the th type of cause data of the th influencing moment at the th module for the th type of water service data at the th moment; represents the absolute value function; represents the linear normalization function.

5. The intelligent water monitoring method based on digital twin according to claim 1, wherein The specific method for obtaining the derived data of each device in all modules, the cause data of various water service data in all modules, the directly affected devices, and the indirectly affected devices includes: Obtain the water service data affected by each device in all modules within the water service system; For the th device in the th module, record the water service data affected by the th device in the th module as the derivative data of the th device in the th module; For the th module and the th type of water service data, the equipment in the th module that affects the th type of water service data is recorded as the direct impact equipment of the th module and the th type of water service data; and the direct impact equipment of the cause data of the th module and the th type of water service data is recorded as the indirect impact equipment of the th module and the th type of water service data.

6. The intelligent water service monitoring method based on digital twin according to claim 4, wherein, The specific method for obtaining the fault factors of each directly affected device and each indirectly affected device of various water service data in each module at each moment includes: For any water service data in any module at any moment, if the degree of abnormality of the water service data in the module at the said moment is greater than or equal to , then according to the degree of abnormality of the water service data and its cause data in the module at the said moment, the degree of association between the water service data and its cause data in the module at the said moment, and in combination with the abnormal independence of the water service data in the module at the said moment, obtain the failure factors of each directly affected device of the water service data in the module at the said moment; Based on the degree of abnormality of the derived data of the indirectly affected device of the water service data in the module at the moment, the degree of association between the derived data of the indirectly affected device and the water service data in the module at the moment, and combining the abnormal independence of the water service data in the module at the moment, obtain the fault factors of each indirectly affected device of the water service data in the module at the moment.

7. The intelligent water service monitoring method based on digital twin according to claim 6, characterized in that, The specific calculation formula for obtaining the fault factors of each directly affected device of the water service data in the module at the moment includes: Wherein, represents the th failure factor directly affecting the device in the water service data of the module at the said moment; represents the abnormal independence of the water service data in the module at the said moment; represents the number of derived data directly affecting the device in the water service data of the module; th; represents the th abnormal degree of the th derived data directly affecting the device in the water service data of the module at the said moment; represents the number of types of cause data of the water service data in the module; represents the number of influence moments at the said moment; represents the th degree of association between the th type of water service data and its th cause data in the th module; represents the abnormal degree of the th type of cause data of the water service data in the module at the th influence moment at the said moment; represents a linear normalization function.

8. The intelligent water service monitoring method based on digital twin according to claim 6, characterized in that, The specific calculation formula for obtaining the fault factors of each indirectly affected device of the water service data in the module at the moment includes: Wherein, represents the th failure factor of the water service data in the module at the said moment that indirectly affects the device; represents the abnormal independence of the water service data in the module at the said moment; represents the number of derived data of the water service data in the module at the said moment that indirectly affects the th device; represents the number of influence moments at the said moment; represents the th influence moment, and represents the correlation degree between the water service data in the module at the said influence moment and the th derived data of the th device that indirectly affects the module; represents the th influence moment, and represents the abnormal degree of the th derived data of the th device that indirectly affects the water service data in the module at the said influence moment; represents a linear normalization function.

9. The method for monitoring intelligent water service based on digital twin according to claim 4, wherein, The specific method for obtaining the faulty devices in each module includes: Preset a fault factor threshold , when the abnormality degree of any water service data in any module at any moment is greater than or equal to , obtain the fault factors of each direct device and indirect device of the water service data in the module at the moment, and record the device with the largest fault factor and the device with a fault factor greater than or equal to as faulty devices.

10. The intelligent water monitoring system based on digital twin includes a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the computer program is executed by a processor, it implements the steps of the digital twin-based intelligent water service monitoring method according to any one of claims 1-9.

Images