Water supply equipment state monitoring method and system based on internet of things
By monitoring the status of water supply equipment through the Internet of Things and combining a phased switching strategy of static and dynamic thresholds, the reliability and interpretability issues of traditional water supply network equipment monitoring have been solved, enabling refined parameter adjustment and real-time monitoring.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- TIANJIN JINGHONG SMART CITY OPERATION MANAGEMENT CO LTD
- Filing Date
- 2026-03-10
- Publication Date
- 2026-06-05
Smart Images
Figure CN122148901A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of water supply system monitoring technology, and in particular to a method and system for monitoring the status of water supply equipment based on the Internet of Things. Background Technology
[0002] Water supply networks are a crucial component of urban infrastructure, and their safe and stable operation directly impacts residents' lives and industrial production. Traditional water supply network equipment status monitoring primarily relies on static threshold alarms, which cannot track long-term drift caused by equipment aging, topological changes, etc.; the alarm logic is simple and lacks interpretability, making it difficult for maintenance personnel to determine the true cause of the alarm.
[0003] With the development of IoT and big data technologies, dynamic threshold methods are increasingly being applied to water supply monitoring. Dynamic thresholding establishes a baseline model by analyzing historical data and generates alarm thresholds that change over time. However, existing dynamic thresholding methods still have the following shortcomings: a lack of historical data during the cold start phase prevents the model from working effectively; slow response to sudden changes in network topology (such as valve switching or pipeline maintenance); difficulty in distinguishing between gradual changes in water consumption and sudden topological changes, leading to a lack of basis for parameter adjustments; and an opaque adjustment process, making it difficult for maintenance personnel to understand and trust the model's behavior.
[0004] Therefore, there is a need for a monitoring scheme for the operational status of water supply network equipment that can adapt to dynamic environments and provide interpretable evidence. Summary of the Invention
[0005] The purpose of this invention is to solve at least one of the problems mentioned in the background art.
[0006] To achieve the above objectives, the technical solution proposed by this invention is: a method for monitoring the status of water supply equipment based on the Internet of Things, the method comprising:
[0007] Acquire real-time operational data of the target monitoring point; the real-time operational data includes flow data and pressure data;
[0008] Determine the static threshold of the target monitoring point;
[0009] Construct a dynamic baseline model for the target monitoring points, and use the dynamic baseline model to generate dynamic thresholds that change over time;
[0010] A phased switching strategy is adopted for status alarm based on static and dynamic thresholds;
[0011] The system detects changes in pipeline topology and water consumption, and adjusts the parameters of the dynamic baseline model based on these changes.
[0012] Preferably, the phased switching strategy includes:
[0013] Phase 1: Static thresholds are used as the basis for state judgment; the static thresholds are set according to the water supply network design specifications; the static thresholds are updated according to a preset update frequency.
[0014] Phase Two: The dynamic threshold is used as the basis for state determination, and the static threshold is used as a backup.
[0015] The switching between Phase 1 and Phase 2 is performed according to preset switching conditions, which include one or more of the following: data volume conditions, model stability conditions, and model accuracy conditions.
[0016] When the switching conditions are met, switch from Phase 1 to Phase 2.
[0017] Preferred options also include:
[0018] Determine the confidence levels for topology changes and water consumption changes, respectively;
[0019] Based on the confidence levels of the topology changes and water consumption changes, the parameters of the dynamic baseline model are adjusted and the process information of the parameter adjustment is recorded; the process information includes the basis for adjustment and the adjustment results;
[0020] The adjustment criteria include one or more of the topology change confidence level and water consumption change confidence level; the adjustment results include the parameters of the adjusted dynamic baseline model.
[0021] Preferably, the method further includes: the dynamic baseline model updates the statistical characteristics of the real-time operating data of each monitoring point in a recursive manner, and calculates the dynamic threshold based on the statistical characteristics;
[0022] The statistical features include mean estimation and variance estimation. The dynamic threshold consists of a dynamic lower limit and a dynamic upper limit, which are determined based on the mean estimation, variance estimation, and adaptive tolerance width coefficient.
[0023] Preferably, the detection of changes in pipeline network topology and water consumption includes:
[0024] Topological changes can be determined based on external event signals or by the abrupt changes in real-time operational data.
[0025] The real-time operating data is decomposed into trends to extract trend components; the trend components are determined based on the average of the mean of the operating status data of the target detection point within one collection cycle and the average of the mean of the operating status data within multiple collection cycles.
[0026] The degree of change in water consumption is determined based on the rate of change of the trend component.
[0027] Preferably, determining the confidence levels for topological changes and water consumption changes respectively includes:
[0028] Determining the confidence level of the topological change based on the significance of the external event signal or the mutation feature; including:
[0029] Receive external event signals from the data acquisition and monitoring control system SCADA or geographic information system GIS of the water supply system; the external event signals include pipeline operation event signals;
[0030] Determine whether the difference between the mean values of the running status data within two sliding time windows exceeds a preset change threshold; if so, determine that a sudden change in the mean has occurred.
[0031] If a mean abrupt change occurs, the confidence level for the topological change is: Otherwise, the confidence level for topological change is ;
[0032] in, The difference represents the statistical characteristics of the operational status data. This represents the initial value of the confidence level for topology changes.
[0033] Determining the confidence level of water consumption change based on the water consumption change rate includes:
[0034] The STL decomposition algorithm is used to extract trend components from the historical operational data of the target detection points;
[0035] Calculate the linear slope of the trend component over a preset time period;
[0036] The linear slope is normalized to obtain the relative rate of change, i.e. the degree of change in water consumption.
[0037] Determining the confidence level of water consumption change based on the degree of water consumption change ;in, To represent the degree of change in water consumption, This is the activation function.
[0038] Preferably, the parameters for adjusting the dynamic baseline model include:
[0039] Based on the confidence levels of the topology change and water consumption change, corresponding adjustment weights are determined, including:
[0040] The overall confidence score is calculated by combining the confidence scores of topology change and water consumption change; the overall confidence score is compared with the confidence score threshold, and the adjustment weight is determined based on the comparison result;
[0041] Based on the adjusted weights, the target parameters of the dynamic baseline model are fused and calculated to obtain the target parameter values; the target parameters include the learning rate or tolerance width coefficient.
[0042] The parameters of the dynamic baseline model are updated using a first-order low-pass filtering algorithm, so that the current parameter values of the dynamic baseline model smoothly transition to the target parameter values.
[0043] Preferably, the process information includes:
[0044] Adjust one or more of the following: trigger cause, confidence level and evidence information of trigger cause, weight adjustment, and numerical comparison of parameters before and after adjustment; the trigger cause includes topology change and water consumption change.
[0045] An IoT-based water supply equipment status monitoring system, wherein the system is used to execute the IoT-based water supply equipment status monitoring method.
[0046] A computer-readable storage medium storing a computer program that is executed by a processor to implement the IoT-based water supply equipment status monitoring method.
[0047] The beneficial effects of this invention are:
[0048] 1. This invention solves the problem of difficult cold start of dynamic models by adopting a phased switching strategy and combining static and dynamic thresholds, thus ensuring the reliability of equipment operation status monitoring throughout the entire system lifecycle.
[0049] 2. This invention achieves refined parameter adjustment by distinguishing between two different types of disturbances: topological changes and water consumption changes, and calculating confidence levels for each separately, thus avoiding blind adjustments. Through a confidence-weighted parameter fusion method, the model can reasonably respond to mixed-type changes while maintaining the stability of parameter adjustments.
[0050] 3. This invention provides interpretable descriptions of model behavior by recording parameter adjustment process information, enhancing maintenance personnel's understanding and trust in the system. The dynamic baseline model uses a recursive update method, which is computationally efficient and suitable for online real-time monitoring scenarios. Attached Figure Description
[0051] Figure 1 This is a flowchart of the IoT-based water supply equipment status monitoring method of the present invention. Detailed Implementation
[0052] The following description is intended to disclose the present invention and enable those skilled in the art to implement it. The preferred embodiments described below are merely examples, and other obvious modifications will occur to those skilled in the art. The basic principles of the invention defined in the following description can be applied to other embodiments, modifications, improvements, equivalents, and other technical solutions that do not depart from the spirit and scope of the invention.
[0053] It is understood that the term "a" should be understood as "at least one" or "one or more", that is, in one embodiment, the number of an element can be one, while in another embodiment, the number of the element can be multiple, and the term "a" should not be understood as a limitation on the number.
[0054] refer to Figure 1 The technical solution provided by this invention is: a method for monitoring the status of water supply equipment based on the Internet of Things, the method comprising:
[0055] Step 1: Acquire real-time operational data from the target monitoring point; the real-time operational data includes flow rate data and pressure data. Specifically, this is achieved by collecting flow rate and pressure data through sensors deployed at the inlets and outlets of key water supply equipment in the water supply network, and uploading the collected data in real time via the Internet of Things (IoT). In this embodiment, the data collection frequency is designed to be once per minute.
[0056] Step 2: Determine the static threshold of the target monitoring point; the static threshold is set according to the design specifications. This embodiment uses pressure as an example. For instance, if the secondary water supply pressure is 0.2-0.5 MPa, then the lower limit of the static threshold is set to 0.2 MPa, and the upper limit is set to 0.5 MPa.
[0057] Static thresholds require periodic maintenance during system operation. In this embodiment, the quantile method is used for updating: every 30 days, fault-free data from the past 30 days is extracted, and the 0.1% quantile of these data is used as the new lower limit of the static threshold, and 99.9% is used as the new upper limit.
[0058] Step 3: Construct a dynamic baseline model for the target monitoring points, and use the dynamic baseline model to generate dynamic thresholds that change over time;
[0059] Specifically, the statistical characteristics of the real-time operational data of each monitoring point are updated recursively, and the dynamic threshold is calculated based on the statistical characteristics. This includes:
[0060] The sampling period is set to 24 hours, with one phase per minute.
[0061] For each phase Maintain the mean and variance of real-time operating data of the target monitoring points.
[0062] For time Its phase The collected real-time running status value is The for Divide by 1440 and take the remainder.
[0063] Update statistical features according to the following formula:
[0064] mean ,variance . The adaptive learning rate is initially set to 0.02. and The phase of the previous sampling period The mean and variance of the real-time running status values.
[0065] Based on the updated statistical features, a dynamic threshold is calculated, including:
[0066] Calculate and obtain dynamic threshold The lower limit is ;
[0067] The upper limit of the calculated dynamic threshold is: ;in, For adaptive tolerance width. , , The adaptive tolerance width coefficient is initially set to 2 and 1; For phase The absolute median difference of the real-time running status values.
[0068] Step 4: Based on static and dynamic thresholds, a phased switching strategy is adopted for status alarms, specifically as follows:
[0069] The system is divided into two phases: Phase 1 (cold start period) and Phase 2 (data accumulation and normal operation period).
[0070] When the system collects more than 30 days of data (data volume condition), and the width of the dynamic threshold for the previous 7 days at the current moment (2... If the rate of change is less than 2% (stability condition) and the alarm accuracy is greater than 90% (accuracy condition), then the system is deemed to meet the switching conditions and switches from stage one to stage two. In this embodiment, three conditions are met simultaneously to determine whether the system meets the switching conditions. In some embodiments, any two conditions can be selected to be met based on the water supply level requirements.
[0071] In Phase 1, static thresholds are used as the basis for status judgment. If the collected operational status data of the target monitoring point in this phase exceeds the upper and lower limits of the static threshold, the water supply equipment at the target monitoring point is judged to be in abnormal status, and an alarm for abnormal water supply equipment status is issued.
[0072] In Phase Two, a dynamic threshold is used as the basis for state judgment, with the static threshold as a backup, i.e., the static threshold is used as a supplementary basis for state judgment. Specifically: if the operating status data of the target monitoring point in this phase exceeds the upper and lower limits of the dynamic threshold and simultaneously exceeds the upper and lower limits of the static threshold, the water supply equipment is judged to be in an abnormal state, and an alarm for abnormal water supply equipment status is issued;
[0073] If the operational status data at this stage only exceeds the upper and lower limits of the static threshold, but does not exceed the upper and lower limits of the dynamic threshold, an abnormal warning will be issued, and the statistical characteristics of the operational status data at that moment will be recorded.
[0074] Step 5: Detect changes in the pipeline network topology and water consumption, and adjust the parameters of the dynamic baseline model based on these changes; this includes the following steps:
[0075] Detecting changes in pipeline network topology and water consumption, specifically:
[0076] Topology change detection: Topology changes are determined based on external event signals or by abrupt changes in real-time operational data. The external event signals are received via a SCADA or GIS system, representing pipeline operation events such as valve switching and pipeline maintenance.
[0077] Based on the external event signal, the topology change confidence level is set to an initial value. .
[0078] Perform trend decomposition on real-time running data and extract trend components, including:
[0079] By collecting operational status data of the target monitoring area through a sliding time window, abrupt changes in the mean of pressure and flow data sequences are identified, i.e., the difference between the mean pressure and mean flow of two sliding time windows exceeds the preset pressure change threshold and flow change threshold.
[0080] If a mean abrupt change occurs, the confidence level for topological change is adjusted to... Among them, the activation function ). The difference in statistical characteristics of the operating status data, in this embodiment, is the difference in the average pressure or the difference in the average flow rate, used to indicate the significance of abrupt changes (the pressure and flow rate at which abrupt changes occur).
[0081] Perform water consumption change detection:
[0082] The degree of water consumption variation is determined based on the rate of change of the trend component. The specific steps are as follows:
[0083] For each phase, the STL decomposition algorithm is used to extract the trend component from the historical operating state data. The linear slope of the trend component over the past 30 days is calculated and normalized to a relative rate of change, i.e., the degree of change in water consumption. Among these, the long-term mean... For all phases The average value, It is a non-zero term.
[0084] Then phase The confidence level of the change in water consumption is ;in, This represents the relative rate of change.
[0085] The specific steps for adjusting the parameters of the dynamic baseline model are as follows:
[0086] Based on the confidence levels of topology change and water consumption change, corresponding adjustment weights are determined, specifically by calculating the overall confidence level. ,in , Indicates the fusion weights;
[0087] if Then adjust the weights. ;
[0088] if Then adjust the weights. ;
[0089] if Then adjust the weights. .
[0090] Based on the adjusted weights, the target parameters of the dynamic baseline model are fused and calculated to obtain target parameter values; the target parameters include the learning rate or tolerance width coefficient. The specific steps are as follows:
[0091] The target value of the learning rate is ;
[0092] Target value for tolerance width coefficient: ; .
[0093] This allows the current parameter values of the dynamic baseline model to smoothly transition to the target parameter values. Specifically, a first-order low-pass filtering algorithm is used to update the current parameters to their target values. The formula can be expressed as follows: ;in, This represents the smoothing factor, which is set to 0.1 in this embodiment. The current parameter value. For the target value of the parameter, This represents the parameter value at the previous time step.
[0094] Record the process information of the parameter adjustment, including:
[0095] The basis for record adjustments is: confidence level of topological change, confidence level of water volume change, and overall confidence level;
[0096] Record the adjustment results: target value for learning rate and target value for tolerance coefficient.
[0097] This invention also provides an Internet of Things (IoT)-based water supply equipment status monitoring system, which is used to execute the IoT-based water supply equipment status monitoring method described above. The system specifically includes:
[0098] Data Acquisition Module: Communicates with on-site IoT water supply equipment, collecting real-time data such as pressure, flow rate, and water quality via MQTT or Modbus TCP protocols. It then performs data cleaning (removing obvious outliers), interpolation, and time alignment. The processed data is then distributed to other modules.
[0099] Static threshold module: Stores and manages static thresholds for each monitoring point. Initial thresholds are manually configured, and subsequent updates are automatically suggested based on preset rules (e.g., every 30 days), taking effect after manual confirmation. The static threshold module provides a threshold query interface for use by the alarm module.
[0100] Dynamic baseline module: Maintains a dynamic baseline model for each monitoring point. The model uses the recursive update method described above, storing the mean, variance, and absolute median difference for each period's phase. The dynamic baseline module calculates the dynamic threshold based on the current time and current parameter values and outputs it to the alarm module.
[0101] The switching control module manages the stage each monitoring point is in. It records system runtime, evaluates the stability and accuracy of the dynamic model, and automatically switches the monitoring point from stage one to stage two when switching conditions are met. The switching control module also supports manual forced switching.
[0102] The change detection module comprises two sub-modules: a topology change detection sub-module and a water consumption change detection sub-module. The topology change detection sub-module monitors the SCADA event bus and analyzes the real-time data stream to detect abrupt changes, outputting topology change confidence levels and evidence. The water consumption change detection sub-module performs trend decomposition on each phase and outputs water consumption change confidence levels.
[0103] Parameter Adjustment Module: Receives the confidence level output from the change detection module and dynamically adjusts the learning rate and tolerance width coefficient of the dynamic baseline module according to the described weight calculation, parameter fusion, and smoothing update methods. The parameter adjustment module maintains the parameter adjustment history for use by the recording module.
[0104] The logging module listens for each adjustment event from the parameter adjustment module, collects information such as parameter values, confidence levels, weights, and target values before and after the adjustment, generates structured explanatory logs, and stores them in the database. The logging module also provides a query interface, supporting log retrieval by time, parameter type, trigger reason, and other criteria.
[0105] Alarm module: Determines alarms based on the currently effective thresholds (primary and secondary thresholds determined by the switching control module). When an alarm is triggered, the alarm module queries the most recent relevant parameter adjustment logs from the recording module, associates the alarm with explanatory information, and pushes it to the monitoring interface or mobile app.
[0106] The present invention also provides a computer-readable storage medium storing a computer program, which is executed by a processor to implement the IoT-based water supply equipment status monitoring method.
[0107] The processes described above with reference to the flowcharts in the embodiments disclosed in this invention can be implemented as computer software programs. The embodiments disclosed in this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication component, and / or installed from a removable medium. When the computer program is executed by a central processing unit (CPU), it performs the functions defined in the methods of this application. It should be noted that the computer-readable medium described above in this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wire segments, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless segments, wire segments, optical fibers, RF, etc., or any suitable combination thereof.
[0108] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation that may be implemented in systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.
[0109] Those skilled in the art should understand that the embodiments of the present invention described above and shown in the accompanying drawings are merely examples and do not limit the present invention. The purpose of the present invention has been fully and effectively achieved, and the functions and structural principles of the present invention have been demonstrated and explained in the embodiments. Without departing from the stated principles, the implementation of the present invention may have any changes or modifications.
Claims
1. A method for monitoring the status of water supply equipment based on the Internet of Things, characterized in that, The method includes: Acquire real-time operational data of the target monitoring point; the real-time operational data includes flow data and pressure data; Determine the static threshold of the target monitoring point; Construct a dynamic baseline model for the target monitoring points, and use the dynamic baseline model to generate dynamic thresholds that change over time; A phased switching strategy is adopted for status alarm based on static and dynamic thresholds; The system detects changes in pipeline topology and water consumption, and adjusts the parameters of the dynamic baseline model based on these changes.
2. The method for monitoring the status of water supply equipment based on the Internet of Things according to claim 1, characterized in that, The phased switching strategy includes: Phase 1: Static thresholds are used as the basis for state judgment; the static thresholds are set according to the water supply network design specifications; the static thresholds are updated according to a preset update frequency. Phase Two: The dynamic threshold is used as the basis for state determination, and the static threshold is used as a backup. The switching between Phase 1 and Phase 2 is performed according to preset switching conditions, which include one or more of the following: data volume conditions, model stability conditions, and model accuracy conditions. When the switching conditions are met, switch from Phase 1 to Phase 2.
3. The method for monitoring the status of water supply equipment based on the Internet of Things according to claim 2, characterized in that, Also includes: Determine the confidence levels for topology changes and water consumption changes, respectively; Based on the confidence levels of the topology changes and water consumption changes, the parameters of the dynamic baseline model are adjusted and the process information of the parameter adjustment is recorded; the process information includes the basis for adjustment and the adjustment results; The adjustment criteria include one or more of the topology change confidence level and water consumption change confidence level; the adjustment results include the parameters of the adjusted dynamic baseline model.
4. The method for monitoring the status of water supply equipment based on the Internet of Things according to claim 3, characterized in that, Also includes: The dynamic baseline model updates the statistical characteristics of the real-time operating data of each monitoring point in a recursive manner, and calculates the dynamic threshold based on the statistical characteristics; The statistical features include mean estimation and variance estimation. The dynamic threshold consists of a dynamic lower limit and a dynamic upper limit, which are determined based on the mean estimation, variance estimation, and adaptive tolerance width coefficient.
5. The method for monitoring the status of water supply equipment based on the Internet of Things according to claim 4, characterized in that, The detection of changes in pipeline topology and water consumption includes: Topological changes can be determined based on external event signals or by the abrupt changes in real-time operational data. The real-time operating data is decomposed into trends to extract trend components; the trend components are determined based on the average of the mean of the operating status data of the target detection point within one collection cycle and the average of the mean of the operating status data within multiple collection cycles. The degree of change in water consumption is determined based on the rate of change of the trend component.
6. The method for monitoring the status of water supply equipment based on the Internet of Things according to claim 5, characterized in that, The determination of the confidence levels for topological changes and water consumption changes includes: Determining the confidence level of the topological change based on the significance of the external event signal or the mutation feature; including: Receive external event signals from the data acquisition and monitoring control system SCADA or geographic information system GIS of the water supply system; the external event signals include pipeline operation event signals; Determine whether the difference between the mean values of the running status data within two sliding time windows exceeds a preset change threshold; if so, determine that a sudden change in the mean has occurred. If a mean abrupt change occurs, the confidence level for the topological change is: Otherwise, the confidence level for topological change is ; in, The difference represents the statistical characteristics of the operational status data. This represents the initial value of the confidence level for topology changes. Determining the confidence level of water consumption change based on the water consumption change rate includes: The STL decomposition algorithm is used to extract trend components from the historical operational data of the target detection points; Calculate the linear slope of the trend component over a preset time period; The linear slope is normalized to obtain the relative rate of change, i.e. the degree of change in water consumption. Determining the confidence level of water consumption change based on the degree of water consumption change ;in, To represent the degree of change in water consumption, This is the activation function.
7. The method for monitoring the status of water supply equipment based on the Internet of Things according to claim 5, characterized in that, The parameters for adjusting the dynamic baseline model include: Based on the confidence levels of the topology change and water consumption change, corresponding adjustment weights are determined, including: The overall confidence score is calculated by combining the confidence scores of topology change and water consumption change; the overall confidence score is compared with the confidence score threshold, and the adjustment weight is determined based on the comparison result; Based on the adjusted weights, the target parameters of the dynamic baseline model are fused and calculated to obtain the target parameter values; the target parameters include the learning rate or tolerance width coefficient. The parameters of the dynamic baseline model are updated using a first-order low-pass filtering algorithm, so that the current parameter values of the dynamic baseline model smoothly transition to the target parameter values.
8. The method for monitoring the status of water supply equipment based on the Internet of Things according to claim 6, characterized in that, The process information includes: Adjust one or more of the following: trigger cause, confidence level and evidence information of trigger cause, weight adjustment, and numerical comparison of parameters before and after adjustment; the trigger cause includes topology change and water consumption change.
9. A water supply equipment status monitoring system based on the Internet of Things, characterized in that, The system is used to execute the IoT-based water supply equipment status monitoring method according to any one of claims 1-8.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that is executed by a processor to implement the Internet of Things-based water supply equipment status monitoring method according to any one of claims 1-8.