Secondary pressurization domestic water supply remote early warning method and system based on artificial intelligence

By setting up sensors in the secondary pressurized water supply pipeline network and using support vector machines and decision tree models, accurate prediction and fault detection of water supply pressure and flow are achieved, and the problem of insufficient fault detection accuracy in the existing technology is solved, and the problem of improved System security and user experience.

CN118982097APending Publication Date: 2024-11-19HAINAN YUZHI INVESTMENT CO LTD

Patent Information

Application Number
CN202410974821.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-19
Publication Date
2024-11-19

AI Technical Summary

Technical Problem

The existing secondary pressurized water supply management system has insufficient accuracy in fault detection and early warning, and cannot detect and locate pipeline faults in time, and lacks an automated pressure regulation mechanism, which affects user water use experience and system safety.

Method used

Set up a multi-point sensor in the secondary pressurized water supply pipeline network to collect data in real time and perform pre-processing. Use the support vector machine model to establish a water supply pressure prediction model, build an early warning mechanism and a fault detection mechanism, detect faults through the decision tree model, and Fault diagnosis and pressure adjustment are performed by actively applying disturbing pressure.

Benefits of technology

Accurate prediction of water supply pressure and flow rate, timely warnings are issued to managers, improving the efficiency and accuracy of fault detection, ensuring that water supply pressure is within a reasonable range, and improving the safety and user experience of the system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118982097A_ABST
    Figure CN118982097A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of water affair management, in particular to a secondary pressurization domestic water supply remote early warning method and system based on artificial intelligence, and the method comprises the steps: setting a sensor in a water supply network, obtaining the operation data of the number and working frequency of variable frequency water pumps, carrying out the preprocessing, building a secondary water supply pressure prediction model through a support vector machine (SVM) model, and carrying out the early warning. Predicting the water supply pressure in the future time period; when the predicted value deviates from the actual value, early warning information is sent to a manager, and a water supply fault detection mechanism is started; pressure disturbance is applied to the pipe network, pressure response data of all measuring points of the pipe network are detected, and fault diagnosis is conducted through a decision tree model; and according to the diagnosis result, the fault is processed or the water supply pressure is adjusted. According to the method, technologies such as the Internet of Things and machine learning are fused, intelligent and precise management of the secondary pressurization water supply system is achieved, and the method has a very good application prospect.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of water management, and in particular to an artificial intelligence-based remote early warning method and system for secondary pressurized domestic water supply. Background Art

[0002] The secondary pressurized water supply system is widely used in high-rise buildings and large communities. It sets up a secondary pressurized pump room in the building or community to further pressurize the municipal pipe network water and deliver it to the user end to meet the water needs of high-rise buildings and remote users. However, due to the large scale, complex pipe network, and large fluctuations in water consumption of the secondary pressurized water supply system, abnormal water supply pressure, pipe network leakage and other faults often occur during its operation, affecting the user's water experience and safety.

[0003] Traditional secondary pressurized water supply management mainly relies on manual inspections and passive repairs, which have problems such as slow response and untimely detection. In recent years, with the development of the Internet of Things and artificial intelligence technologies, intelligent water supply management solutions have begun to gain attention and application. These solutions deploy sensors in the pipe network to collect data such as pressure and flow in real time, and use machine learning algorithms to analyze and predict the data to achieve real-time monitoring and early warning of water supply status.

[0004] However, the existing intelligent water supply management scheme still has some shortcomings: first, the modeling and prediction accuracy of the water supply system needs to be improved, and it is difficult to accurately predict the future water supply pressure and flow; second, there is a lack of effective fault detection and diagnosis mechanism, and it is impossible to timely discover and locate pipe network faults; third, there is a lack of automated pressure regulation mechanism, and it is difficult to achieve optimal control of water supply pressure. Therefore, a more intelligent and accurate secondary pressurized water supply remote early warning method is urgently needed.

[0005] In view of this, the present invention proposes a remote early warning method and system for secondary pressurized domestic water supply based on artificial intelligence. Summary of the invention

[0006] To achieve the above purpose, the present invention provides the following technical solution: A remote early warning method for secondary pressurized domestic water supply based on artificial intelligence, comprising:

[0007] Setting up multi-point sensors in the secondary pressurized water supply network and collecting the operation data of the water supply network in real time, the operation data including the number and working frequency of the variable frequency water pumps, and pre-processing the collected data;

[0008] Based on the preprocessed data, a secondary pressurized water supply operation database is established, and a water supply pressure prediction model is established using the support vector machine (SVM) model.

[0009] Use the water supply pressure prediction model to predict the water supply pressure and flow in the future time period; and build an early warning mechanism. When there is a deviation between the predicted value and the actual value, it will send a warning message to the management personnel and perform water supply fault detection;

[0010] A water supply fault detection mechanism is constructed to apply pressure disturbance to the secondary pressurized water supply network, detect the pressure response data of each measuring point in the network, and use a decision tree model to detect whether the secondary pressurized water supply network has a fault;

[0011] When the water supply fault detection mechanism detects a secondary pressurized water supply network fault, the fault is handled; when the water supply fault detection mechanism does not detect a secondary pressurized water supply network fault, the current secondary pressurized water supply pressure is adjusted to adjust the water supply pressure value to a normal range.

[0012] Preferably, the sensor includes a pressure sensor and a flow sensor, which are used to collect the pressure P and instantaneous flow Q of the secondary water supply pressure pipe network respectively;

[0013] The collected data are preprocessed to remove outliers and noise, time synchronize and normalize.

[0014] Preferably, the secondary pressurized water supply operation database includes a real-time data table, a historical data table, an equipment ledger table and an operation log table;

[0015] The support vector machine (SVM) model is used to construct a water supply pressure prediction model. The input data set is set to x = {P, Q, S, F}, and the constructed water supply pressure prediction model is:

[0016]

[0017] in, represents the predicted pressure value, N represents the number of data sets, S is the number of variable frequency water pumps, and F is the average operating frequency of the variable frequency water pumps; α i and is the Lagrange multiplier, K(·) is the kernel function, is the support vector, x i represents the input feature vector, and b is the bias term;

[0018] Solve for the model parameters by minimizing the objective function:

[0019]

[0020] Among them, w is the weight vector, w T represents the transpose of the weight vector, φ(·) is the feature mapping function, C is the penalty factor, ε is the error tolerance, ξ i and is the slack variable, y iis the output value of the i-th data sample.

[0021] Preferably, based on the established water supply pressure prediction model, the parameters of water supply pressure and flow rate in the future time period are predicted; and a warning threshold θ is set. w and the severity threshold θ s , where θ w <θ s ;

[0022] When the predicted pressure value The actual pressure value P t The deviation is greater than or equal to the warning threshold θ w and is less than the severe threshold θ s When Send warning information about changes in secondary pressurized water supply pressure to management personnel;

[0023] When the predicted pressure value The actual pressure value P t The deviation is greater than or equal to the severe threshold θ s When Send warning information about changes in secondary pressurized water supply pressure to management personnel and activate the water supply fault detection mechanism.

[0024] Preferably, when the water supply fault detection mechanism is triggered, the response characteristics of the water supply network are tested by actively applying disturbance pressure, and the response data of the water supply network are collected and calculated to detect whether the water supply network has a fault;

[0025] The disturbance pressure ΔP is applied by adjusting the working frequency f of the variable frequency water pump:

[0026] f=f 0 ±Δf,ΔP=kΔf

[0027] Among them, f 0 is the initial operating frequency of the variable frequency water pump, Δf is the frequency adjustment step, and k is the pressure-frequency coefficient of the variable frequency water pump;

[0028] In the process of applying disturbed water supply, the response data of each measuring point in the pipe network is collected in real time through the pressure sensor, a response curve is constructed based on the response data, and the characteristic parameters of the response curve are extracted. The characteristic parameters include response time Δt, peak value Steady-state value and the decay rate λ i , the decay rate λ i The calculation formula is as follows:

[0029]

[0030] Among them, P i(t) is the pressure value measured by the i-th pressure sensor at time t, the steady-state value Represents the steady-state value of the pressure of the i-th pressure sensor, the peak value Represents the peak pressure value of the i-th pressure sensor.

[0031] Preferably, the extracted characteristic parameters are input into a decision tree model, and the fault type of the water supply network is determined by the recognition and classification algorithms in the model;

[0032] The decision tree model is used to perform multi-classification of secondary pressurized water supply network faults. For each fault sample j, its feature vector is The corresponding label is y j ∈0,1,2,...,M, where M is the number of fault types and 0 means no fault;

[0033] The training process of the decision tree model is as follows:

[0034] Step a: Collect historical fault data, extract features and label each fault sample; divide the feature data and corresponding labels into a data set, and randomly divide the data set into a training set and a test set;

[0035] Step b: For each feature data, calculate the information gain and Gini index between the feature data and the label, and use the feature with the largest index value as the split feature; select the feature with the largest index value as the split feature of the current node, and for continuous features, find the optimal split threshold through enumeration or optimization algorithm;

[0036] Step c: Divide the training set samples into left and right child nodes according to the selected split features and optimal split threshold;

[0037] Recursively repeat steps b and c for the left and right child nodes until the stopping condition is met;

[0038] Step d: Mark the nodes that meet the stopping condition as leaf nodes, and set the leaf node category label to the majority category of the samples in the node.

[0039] Preferably, the trained decision tree model is used for new fault diagnosis;

[0040] For a new input feature vector, starting from the root node of the decision tree model, the tree is recursively traversed according to the split features and the optimal split threshold until a leaf node is reached, and the corresponding fault type is output;

[0041] When the decision tree model detects a fault in the secondary pressurized water supply network, the fault in the secondary pressurized water supply network is processed;

[0042] When the decision tree model does not detect a secondary pressurized water supply network fault, the current secondary pressurized water supply pressure is adjusted to a normal range by adjusting the number and operating frequency of the variable frequency water pumps. t Adjust to range, η is the error parameter.

[0043] A secondary pressurized domestic water supply remote early warning system based on artificial intelligence, which is used to implement a secondary pressurized domestic water supply remote early warning method based on artificial intelligence, including: a data acquisition and processing module, a secondary water supply pressure prediction module, a secondary water supply pressure early warning module, a water supply fault detection module, and a fault processing and pressure adjustment module;

[0044] The data acquisition and processing module sets up multi-point sensors in the secondary pressurized water supply network, collects the operation data of the water supply network in real time, the operation data includes the number and working frequency of the variable frequency water pumps, and pre-processes the collected data;

[0045] The secondary water supply pressure prediction module establishes a secondary pressurized water supply operation database based on the preprocessed data, and establishes a secondary water supply pressure prediction model using a support vector machine (SVM) model;

[0046] The secondary water supply pressure warning module uses the water supply pressure prediction model to predict the water supply pressure and flow rate in the future time period; and builds an early warning mechanism. When the predicted value deviates from the actual value, it sends a warning message to the management personnel and performs water supply fault detection;

[0047] The water supply fault detection module constructs a water supply fault detection mechanism to apply pressure disturbance to the secondary pressurized water supply network, detect the pressure response data of each measuring point in the network, and use a decision tree model to detect whether the secondary pressurized water supply network has a fault;

[0048] The fault handling and pressure adjustment module handles the fault when the water supply fault detection mechanism detects a secondary pressurized water supply network fault; when the water supply fault detection mechanism does not detect a secondary pressurized water supply network fault, it adjusts the current secondary pressurized water supply pressure and adjusts the water supply pressure value to a normal range.

[0049] An electronic device comprises: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0050] The processor executes the artificial intelligence-based secondary pressurized domestic water supply remote early warning method by calling the computer program stored in the memory.

[0051] A computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the artificial intelligence-based secondary pressurized domestic water supply remote early warning method.

[0052] Beneficial effects of the present invention: The present invention establishes multi-point sensors in the secondary pressurized water supply network to collect data such as pressure and flow in real time and perform preprocessing to provide high-quality data support for subsequent modeling and analysis.

[0053] The present invention utilizes a support vector machine (SVM) model to establish an accurate water supply pressure prediction model, which can accurately predict the water supply pressure and flow rate in the future time period, providing a basis for early warning and regulation.

[0054] The present invention constructs an early warning mechanism based on the deviation between the predicted value and the actual value, which can send early warning information to management personnel in a timely manner to remind them to pay attention to abnormal water supply status and improve the safety and reliability of the system.

[0055] The present invention designs a water supply fault detection mechanism based on actively applying disturbance pressure. By analyzing the pressure response characteristics of the pipe network and using a decision tree model, rapid diagnosis and classification of pipe network faults are achieved, greatly improving the efficiency and accuracy of fault detection.

[0056] The present invention realizes automatic water supply pressure adjustment on the basis of early warning and fault detection. By adjusting the number and operating frequency of variable frequency water pumps, the water supply pressure is maintained within a reasonable range, thus ensuring the user's water use experience and the safe operation of the pipe network.

[0057] The method of the invention integrates multiple technologies such as the Internet of Things and machine learning, realizes the intelligent and precise management of the secondary pressurized water supply system, greatly improves the efficiency and level of water supply management, and provides new ideas and solutions for the development of smart water services.

[0058] The method of the present invention has strong versatility and scalability, can be promoted and applied in secondary pressurized water supply systems of different scales and types, and has broad application prospects and market value. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 This is a flow chart of a remote early warning method for secondary pressurized domestic water supply based on artificial intelligence of the present invention;

[0060] Figure 2 This is a schematic diagram of the structure of the artificial intelligence-based secondary pressurized domestic water supply remote early warning system of the present invention;

[0061] Figure 3 It is a schematic diagram of the structure of an electronic device provided by the present invention;

[0062] Figure 4It is a schematic diagram of the structure of the computer-readable storage medium provided by the present invention. DETAILED DESCRIPTION

[0063] In order to better understand the present application, a more detailed description will be made of various aspects of the present application with reference to the accompanying drawings. It should be understood that these detailed descriptions are only descriptions of exemplary embodiments of the present application, and are not intended to limit the scope of the present application in any way. Throughout the specification, the same reference numerals refer to the same elements. The expression "and / or" includes any and all combinations of one or more of the associated listed items.

[0064] In the accompanying drawings, the size, dimensions and shapes of the elements have been slightly adjusted for ease of illustration. The drawings are for illustration only and are not strictly drawn to scale. As used herein, the terms "substantially", "approximately" and similar terms are used as terms of approximation, not as terms of degree, and are intended to illustrate the inherent deviations in measurements or calculations that will be recognized by those of ordinary skill in the art. In addition, in this application, the order in which the steps are described does not necessarily represent the order in which these processes occur in actual operation, unless otherwise specified or can be derived from the context.

[0065] It should also be understood that expressions such as "include", "including", "have", "contain" and / or "comprising" are open rather than closed expressions in this specification, which indicate the presence of the stated features, elements and / or components, but do not exclude the presence of one or more other features, elements, components and / or combinations thereof. In addition, when expressions such as "at least one of..." appear after a list of listed features, they modify the entire list of features rather than just the individual elements in the list. In addition, when describing embodiments of the present application, "may" is used to mean "one or more embodiments of the present application". And, the term "exemplary" is intended to refer to an example or illustration.

[0066] Unless otherwise specified, all words (including engineering terms and scientific and technological terms) used in this article have the same meaning as those commonly understood by ordinary technicians in the field to which this application belongs. It should also be understood that, unless clearly stated in this application, words defined in common dictionaries should be interpreted as having the same meaning as their meaning in the context of the relevant technology, and should not be interpreted in an idealized or overly formal sense.

[0067] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0068] Example 1

[0069] Reference Figure 1 The first embodiment of the present invention provides a remote early warning method for secondary pressurized domestic water supply based on artificial intelligence.

[0070] Multi-point sensors are set up in the secondary pressurized water supply network to collect the operation data of the water supply network in real time. The operation data includes the number and working frequency of the variable frequency water pumps, and the collected data is pre-processed.

[0071] The sensors include a pressure sensor and a flow sensor, which are used to collect the pressure P and instantaneous flow Q of the secondary water supply pressure pipe network respectively.

[0072] The pressure sensor is arranged at the water inlet, water outlet, main pipe and important branch pipe of the water supply network to monitor the change of the network pressure, with a measuring range of 0 to 2MPa, an accuracy of ±0.5%, and a sampling frequency of 1Hz.

[0073] The flow sensor is arranged at the outlet of the water supply pump and the main pipe of the pipe network to monitor the instantaneous flow and the cumulative flow, with a range of 0 to 500m 3 / h, accuracy ±1%, sampling frequency 1Hz.

[0074] The data collected by each sensor is gathered to the data acquisition unit, such as PLC or RTU, through bus or wireless communication. Considering the geographical distribution characteristics of the secondary water supply network, a multi-level networking architecture is adopted to gather data nearby and then transmit it to the central node. Data transmission should adopt mature and reliable communication protocols and encryption mechanisms, such as Modbus, MQTT, etc., to ensure the integrity, security and real-time performance of the data.

[0075] The collected data are preprocessed to remove outliers and noise, time synchronize and normalize.

[0076] The collected raw data is preprocessed. The main steps include:

[0077] Denoising: Use methods such as Kalman filtering and wavelet transform to remove high-frequency noise and random interference.

[0078] Outlier processing: Identify and eliminate outliers through 3σ principle, box plot and other methods.

[0079] Time synchronization: Align timestamps of data from different sources to ensure time consistency.

[0080] Normalization: Use methods such as maximum and minimum value normalization to map the data to the [0, 1] interval to eliminate the dimension effect:

[0081]

[0082] Among them, x *is the normalized data, x is the original data, and x min and x max are the minimum and maximum values ​​of this type of data respectively.

[0083] Based on the preprocessed data, a secondary pressurized water supply operation database is established, and a water supply pressure prediction model is established using the support vector machine (SVM) model.

[0084] The secondary pressurized water supply operation database includes a real-time data table, a historical data table, an equipment ledger table and an operation log table.

[0085] The real-time data table stores the real-time collected data of each measuring point, including pressure, flow, temperature and liquid level, etc., with a time granularity of seconds.

[0086] The historical data table stores historical archives of real-time data, and the time granularity can be downsampled to minutes, hours, and days for historical trend analysis.

[0087] The equipment inventory table stores basic information of equipment such as pumps, pipes, valves and pools, such as type, specification, installation location and activation time.

[0088] The operation log table stores the operation records of the system, such as equipment start and stop, control instructions and abnormal alarms, etc., to facilitate post-audit.

[0089] The database adopts a distributed storage and computing architecture, supports efficient reading, writing, query and analysis of massive data, and uses open source big data platforms such as Hadoop and Spark, or big data services provided by cloud service providers.

[0090] The support vector machine (SVM) model is used to construct a water supply pressure prediction model. The input data set is set to x = {P, Q, S, F}, and the constructed water supply pressure prediction model is:

[0091]

[0092] in, represents the predicted pressure value, N represents the number of data sets, S is the number of variable frequency water pumps, and F is the average operating frequency of the variable frequency water pumps; α i and is the Lagrange multiplier, K(·) is the kernel function, is the support vector, x i represents the input feature vector, and b is the bias term;

[0093] Solve for the model parameters by minimizing the objective function:

[0094]

[0095] Among them, w is the weight vector, wT represents the transpose of the weight vector, φ(·) is the feature mapping function, C is the penalty factor, ε is the error tolerance, ξ i and is the slack variable, y i is the output value of the i-th data sample.

[0096] The water supply pressure prediction model is used to predict the water supply pressure and flow in the future time period; and an early warning mechanism is built. When there is a deviation between the predicted value and the actual value, a warning message is sent to the management personnel, and water supply fault detection is carried out.

[0097] Based on the established water supply pressure prediction model, the parameters of water supply pressure and flow in the future time period are predicted; the warning threshold θ is set w and the severity threshold θ s , where θ w <θ s ;

[0098] When the predicted pressure value The actual pressure value P t The deviation is greater than or equal to the warning threshold θ w and is less than the severe threshold θ s When Send warning information about changes in secondary pressurized water supply pressure to management personnel;

[0099] When the predicted pressure value The actual pressure value P t The deviation is greater than or equal to the severe threshold θ s When Send warning information about changes in secondary pressurized water supply pressure to management personnel and activate the water supply fault detection mechanism.

[0100] A water supply fault detection mechanism is constructed to impose pressure disturbance on the secondary pressurized water supply network, detect the pressure response data of each measuring point in the network, and use a decision tree model to detect whether the secondary pressurized water supply network has a fault.

[0101] When the water supply fault detection mechanism is triggered, the response characteristics of the water supply network are tested by actively applying disturbance pressure, and the response data of the water supply network is collected and calculated to detect whether there is a fault in the water supply network.

[0102] The disturbance pressure ΔP is applied by adjusting the working frequency f of the variable frequency water pump:

[0103] f=f 0 ±Δf,ΔP=kΔf

[0104] Among them, f 0is the initial operating frequency of the variable frequency water pump, Δf is the frequency adjustment step, and k is the pressure-frequency coefficient of the variable frequency water pump. By setting different Δf, different pressure disturbances can be generated in the water supply network.

[0105] In the process of applying disturbed water supply, the response data of each measuring point in the pipe network is collected in real time through the pressure sensor, a response curve is constructed based on the response data, and the characteristic parameters of the response curve are extracted. The characteristic parameters include response time Δt, peak value Steady-state value and the decay rate λ i .

[0106]

[0107] Among them, P i (t) is the pressure value measured by the i-th pressure sensor at time t, the steady-state value Represents the steady-state value of the pressure of the i-th pressure sensor, the peak value Represents the peak pressure value of the i-th pressure sensor.

[0108] The approximate area of ​​the fault is determined based on the similarity of the response curves of different measuring points; the distance to the fault point is inferred based on the attenuation rate parameter of the response time; the cause of the fault is analyzed based on the changing trend of pressure and flow before and after the fault, such as pipeline corrosion and valve aging.

[0109] The decay rate is closely related to the damping characteristics of the pipe network. Damping refers to the ability of the pipe network to attenuate pressure disturbances, which is mainly affected by factors such as pipe material, pipe diameter, and flow rate. The greater the decay rate, the stronger the damping of the pipe network, and the faster the pressure disturbance decays; conversely, the smaller the decay rate, the weaker the damping of the pipe network, and the slower the pressure disturbance decays. By comparing the decay rates of different measuring points, the damping characteristics of different parts of the pipe network can be determined, and then the pipeline status and fault location can be inferred.

[0110] The extracted characteristic parameters are input into the decision tree model, and the fault type of the water supply network is determined by the recognition and classification algorithms in the model. The fault types include pipe rupture, valve jamming and pump performance degradation.

[0111] The decision tree model is used to perform multi-classification of secondary pressurized water supply network faults. For each fault sample j, its feature vector is The corresponding label is y j ∈0,1,2,...,M, where M is the number of fault types and 0 means no fault.

[0112] The goal of the decision tree model is to construct a tree structure by recursively selecting the optimal features and their splitting thresholds so that each leaf node contains as pure samples of the same type as possible.

[0113] The training process of the decision tree model is as follows:

[0114] Step a: Collect historical fault data, extract features and label each fault sample; divide the feature data and corresponding labels into a data set, and randomly divide the data set into a training set and a test set;

[0115] Step b: For each feature data, calculate the information gain and Gini index between the feature data and the label, and use the feature with the largest index value as the split feature; select the feature with the largest index value as the split feature of the current node, and for continuous features, find the optimal split threshold through enumeration or optimization algorithm;

[0116] Step c: Divide the training set samples into left and right child nodes according to the selected split features and optimal split threshold;

[0117] Recursively repeat steps b and c for the left and right child nodes until the stopping condition is met;

[0118] The stopping conditions include the number of samples in the node being less than a preset threshold, the class purity of the samples in the node reaching a preset threshold, and the depth of the tree reaching a preset maximum value;

[0119] Step d: Mark the nodes that meet the stopping condition as leaf nodes, and set the leaf node category label to the majority category of the samples in the node.

[0120] Use the trained decision tree model for new fault diagnosis.

[0121] For a new input feature vector, starting from the root node of the decision tree model, the tree is recursively traversed according to the split features and the optimal split threshold until a leaf node is reached and the corresponding fault type is output.

[0122] When the decision tree model detects a fault in the secondary pressurized water supply network, the fault in the secondary pressurized water supply network is processed.

[0123] When the decision tree model does not detect a secondary pressurized water supply network fault, the current secondary pressurized water supply pressure is adjusted to a normal range by adjusting the number and operating frequency of the variable frequency water pumps. t Adjust to range, η is the error parameter.

[0124] Example 2

[0125] Reference Figure 2 The second embodiment of the present invention provides a secondary pressurized domestic water supply remote early warning system based on artificial intelligence.

[0126] The system comprises a data acquisition and processing module, a secondary water supply pressure prediction module, a secondary water supply pressure early warning module, a water supply fault detection module and a fault processing and pressure adjustment module.

[0127] The data acquisition and processing module sets up multi-point sensors in the secondary pressurized water supply network, and collects the operation data of the water supply network in real time. The operation data includes the number and working frequency of the variable frequency water pumps, and pre-processes the collected data.

[0128] The secondary water supply pressure prediction module establishes a secondary pressurized water supply operation database based on the preprocessed data, and establishes a water supply pressure prediction model using a support vector machine (SVM) model.

[0129] The secondary water supply pressure warning module uses a water supply pressure prediction model to predict the water supply pressure and flow in the future time period; and builds an early warning mechanism. When there is a deviation between the predicted value and the actual value, it sends a warning message to the management personnel and performs water supply fault detection.

[0130] The water supply fault detection module constructs a water supply fault detection mechanism to apply pressure disturbance to the secondary pressurized water supply network, detect the pressure response data of each measuring point in the network, and use a decision tree model to detect whether the secondary pressurized water supply network has a fault.

[0131] The fault handling and pressure adjustment module handles the fault when the water supply fault detection mechanism detects a secondary pressurized water supply network fault; when the water supply fault detection mechanism does not detect a secondary pressurized water supply network fault, it adjusts the current secondary pressurized water supply pressure and adjusts the water supply pressure value to a normal range.

[0132] Example 3

[0133] Figure 3 FIG. 1 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 3 As shown, according to another aspect of the present invention, an electronic device 500 is also provided. The electronic device 500 may include one or more processors and one or more memories. The memories store computer readable codes, and when the computer readable codes are executed by one or more processors, the secondary pressurized domestic water supply remote early warning method based on artificial intelligence as described above can be executed.

[0134] The method or system according to the embodiment of the present invention can also be used by Figure 3 The architecture of the electronic device shown is implemented.

[0135] like Figure 3As shown, the electronic device 500 may include a bus 501, one or more CPUs 502, a read-only memory (ROM) 503, a random access memory (RAM) 504, a communication port 505 connected to a network, an input / output component 506, a hard disk 507, and the like.

[0136] The storage device in the electronic device 500, such as the ROM 503 or the hard disk 507, can store the artificial intelligence-based secondary pressurized domestic water supply remote early warning method provided by the present invention.

[0137] A remote early warning method for secondary pressurized domestic water supply based on artificial intelligence includes: setting up multi-point sensors in a secondary pressurized water supply network, and collecting the operation data of the water supply network in real time, wherein the operation data includes the number and working frequency of variable frequency water pumps, and pre-processing the collected data; establishing a secondary pressurized water supply operation database based on the pre-processed data, and establishing a water supply pressure prediction model by using a support vector machine (SVM) model; using the water supply pressure prediction model to predict the water supply pressure and flow in the future time period; and constructing an early warning mechanism, when the predicted value deviates from the actual value, sending an early warning message to the management personnel, and performing water supply fault detection; constructing a water supply fault detection mechanism to apply pressure disturbance to the secondary pressurized water supply network, detecting the pressure response data of each measuring point of the network, and using a decision tree model to detect whether the secondary pressurized water supply network has a fault; when the water supply fault detection mechanism detects a fault in the secondary pressurized water supply network, the fault is processed; when the water supply fault detection mechanism does not detect a fault in the secondary pressurized water supply network, the current secondary pressurized water supply pressure is adjusted to adjust the water supply pressure value to a normal range.

[0138] Furthermore, the electronic device 500 may also include a user interface 508. Figure 3 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Figure 3 One or more components of an electronic device are shown.

[0139] Example 4

[0140] Figure 4 It is a schematic diagram of the structure of a computer-readable storage medium provided by an embodiment of the present invention.

[0141] like Figure 4 As shown, a computer readable storage medium 600 according to one embodiment of the present invention.

[0142] Computer readable storage medium 600 has computer readable instructions stored thereon.

[0143] When the computer-readable instructions are executed by the processor, the artificial intelligence-based secondary pressurized domestic water supply remote early warning method according to the embodiment of the present invention described with reference to the above drawings can be executed.

[0144] The storage medium 600 includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. In addition, according to an embodiment of the present invention, the process described above with reference to the flowchart may be implemented as a computer software program.

[0145] For example, the present invention provides a non-transitory machine-readable storage medium, which stores machine-readable instructions, and the machine-readable instructions can be executed by a processor to execute instructions corresponding to the method steps provided by the present invention, for example: setting up multi-point sensors in a secondary pressurized water supply network, and collecting operating data of the water supply network in real time, wherein the operating data includes the number and operating frequency of variable frequency water pumps, and pre-processing the collected data; based on the pre-processed data, establishing a secondary pressurized water supply operation database, and using a support vector machine SVM model to establish a water supply pressure prediction model; using the water supply pressure prediction model to predict the future The water supply pressure and flow rate in the coming time period are predicted; and an early warning mechanism is established. When the predicted value deviates from the actual value, an early warning message is issued to the management personnel, and water supply fault detection is performed; a water supply fault detection mechanism is established to apply pressure disturbance to the secondary pressurized water supply network, detect the pressure response data of each measuring point of the network, and use a decision tree model to detect whether the secondary pressurized water supply network has a fault; when the water supply fault detection mechanism detects a secondary pressurized water supply network fault, the fault is handled; when the water supply fault detection mechanism does not detect a secondary pressurized water supply network fault, the current secondary pressurized water supply pressure is adjusted to adjust the water supply pressure value to a normal range.

[0146] When the computer program is executed by the central processing unit (CPU), the above functions defined in the method of the present invention are performed. The method, apparatus, and device of the present invention may be implemented in many ways. For example, the method, apparatus, and device of the present invention may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware.

[0147] The above sequence for the steps of the method is for illustration only, and the steps of the method of the present invention are not limited to the sequence specifically described above unless otherwise specifically stated.

[0148] In addition, in some embodiments, the present invention can also be implemented as a program recorded in a recording medium, which includes machine-readable instructions for implementing the method according to the present invention. Therefore, the present invention also covers a recording medium storing a program for executing the method according to the present invention.

[0149] In addition, the parts of the above technical solutions provided in the embodiments of the present invention that are consistent with the implementation principles of the corresponding technical solutions in the prior art are not described in detail to avoid excessive redundancy.

[0150] The specific implementation modes as described above further describe the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation mode of the present invention and is not intended to limit the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A remote early warning method for secondary pressurized domestic water supply based on artificial intelligence, characterized in that: include: Setting up multi-point sensors in the secondary pressurized water supply network and collecting the operation data of the water supply network in real time, the operation data including the number and working frequency of the variable frequency water pumps, and pre-processing the collected data; Based on the preprocessed data, a secondary pressurized water supply operation database is established, and a water supply pressure prediction model is established using the support vector machine (SVM) model. Use the water supply pressure prediction model to predict the water supply pressure and flow in the future time period; And build an early warning mechanism to send early warning information to managers and conduct water supply fault detection when there is a deviation between the predicted value and the actual value; A water supply fault detection mechanism is constructed to apply pressure disturbance to the secondary pressurized water supply network, detect the pressure response data of each measuring point in the network, and use a decision tree model to detect whether the secondary pressurized water supply network has a fault; When the water supply fault detection mechanism detects a fault in the secondary pressurized water supply network, the fault is handled; When the water supply fault detection mechanism does not detect a secondary pressurized water supply network fault, the current secondary pressurized water supply pressure is adjusted to adjust the water supply pressure value to a normal range.

2. The artificial intelligence-based secondary pressurized domestic water supply remote early warning method according to claim 1 is characterized in that: The sensor includes a pressure sensor and a flow sensor, which are used to collect the pressure P and instantaneous flow Q of the secondary water supply pressure pipe network respectively; The collected data are preprocessed to remove outliers and noise, time synchronize and normalize.

3. The artificial intelligence-based secondary pressurized domestic water supply remote early warning method according to claim 2 is characterized in that: The secondary pressurized water supply operation database includes a real-time data table, a historical data table, an equipment ledger table and an operation log table; The support vector machine (SVM) model is used to construct a water supply pressure prediction model. The input data set is set to x = {P, Q, S, F}, and the constructed water supply pressure prediction model is: in, represents the predicted pressure value, N represents the number of data sets, S is the number of variable frequency water pumps, and F is the average operating frequency of the variable frequency water pumps; α i and is the Lagrange multiplier, K(·) is the kernel function, is the support vector, x i represents the input feature vector, and b is the bias term; Solve for the model parameters by minimizing the objective function: Among them, w is the weight vector, w T represents the transpose of the weight vector, φ(·) is the feature mapping function, C is the penalty factor, ε is the error tolerance, ξ i and is the slack variable, y i is the output value of the i-th data sample.

4. The artificial intelligence-based secondary pressurized domestic water supply remote early warning method according to claim 3 is characterized in that: Based on the established water supply pressure prediction model, the parameters of water supply pressure and flow in the future time period are predicted; Set the warning threshold θ w and the severity threshold θ s , where θ w <θ s ; When the predicted pressure value The actual pressure value P t The deviation is greater than or equal to the warning threshold θ w and is less than the severe threshold θ s When Send warning information about changes in secondary pressurized water supply pressure to management personnel; When the predicted pressure value The actual pressure value P t The deviation is greater than or equal to the severe threshold θ s When Send warning information about changes in secondary pressurized water supply pressure to management personnel and activate the water supply fault detection mechanism.

5. The artificial intelligence-based secondary pressurized domestic water supply remote early warning method according to claim 4 is characterized in that: When the water supply fault detection mechanism is triggered, the response characteristics of the water supply network are tested by actively applying disturbance pressure, and the response data of the water supply network is collected and calculated to detect whether the water supply network has a fault; The disturbance pressure ΔP is applied by adjusting the working frequency f of the variable frequency water pump: f=f0±Δf,ΔP=kΔf Among them, f0 is the initial operating frequency of the variable frequency water pump, Δf is the frequency adjustment step, and k is the pressure-frequency coefficient of the variable frequency water pump; In the process of applying disturbed water supply, the response data of each measuring point in the pipe network is collected in real time through the pressure sensor, a response curve is constructed based on the response data, and the characteristic parameters of the response curve are extracted. The characteristic parameters include response time Δt, peak value Steady-state value and the decay rate λ i , the decay rate λ i The calculation formula is as follows: Among them, P i (t) is the pressure value measured by the i-th pressure sensor at time t, the steady-state value Represents the steady-state value of the pressure of the i-th pressure sensor, the peak value Represents the peak pressure value of the i-th pressure sensor.

6. The artificial intelligence-based secondary pressurized domestic water supply remote early warning method according to claim 5 is characterized in that: The extracted characteristic parameters are input into the decision tree model, and the fault type of the water supply network is determined through the recognition and classification algorithms in the model; The decision tree model is used to perform multi-classification of secondary pressurized water supply network faults. For each fault sample j, Its eigenvector is The corresponding label is y j ∈0,1,2,...,M, where M is the number of fault types and 0 means no fault; The training process of the decision tree model is as follows: Step a: Collect historical fault data, extract features and label each fault sample; divide the feature data and corresponding labels into a data set, and randomly divide the data set into a training set and a test set; Step b: For each feature data, calculate the information gain and Gini index between the feature data and the label, and use the feature with the largest index value as the split feature; select the feature with the largest index value as the split feature of the current node, and for continuous features, find the optimal split threshold through enumeration or optimization algorithm; Step c: Divide the training set samples into left and right child nodes according to the selected split features and optimal split threshold; Recursively repeat steps b and c for the left and right child nodes until the stopping condition is met; Step d: Mark the nodes that meet the stopping condition as leaf nodes, and set the leaf node category label to the majority category of the samples in the node.

7. The artificial intelligence-based secondary pressurized domestic water supply remote early warning method according to claim 6 is characterized in that: Use the trained decision tree model for new fault diagnosis; For a new input feature vector, starting from the root node of the decision tree model, the tree is recursively traversed according to the split features and the optimal split threshold until a leaf node is reached, and the corresponding fault type is output; When the decision tree model detects a fault in the secondary pressurized water supply network, the fault in the secondary pressurized water supply network is processed; When the decision tree model does not detect a secondary pressurized water supply network fault, the current secondary pressurized water supply pressure is adjusted to a normal range by adjusting the number and operating frequency of the variable frequency water pumps. t Adjust to range, η is the error parameter.

8. A remote early warning system for secondary pressurized domestic water supply based on artificial intelligence, which is used to implement the remote early warning method for secondary pressurized domestic water supply based on artificial intelligence as claimed in any one of claims 1 to 7, characterized in that: include: Data acquisition and processing module, secondary water supply pressure prediction module, secondary water supply pressure warning module, water supply fault detection module, and fault handling and pressure adjustment module; The data acquisition and processing module sets up multi-point sensors in the secondary pressurized water supply network, collects the operation data of the water supply network in real time, the operation data includes the number and working frequency of the variable frequency water pumps, and pre-processes the collected data; The secondary water supply pressure prediction module establishes a secondary pressurized water supply operation database based on the preprocessed data, and establishes a water supply pressure prediction model using a support vector machine (SVM) model; The secondary water supply pressure warning module uses a water supply pressure prediction model to predict the water supply pressure and flow rate in the future time period; And build an early warning mechanism to send early warning information to managers and conduct water supply fault detection when there is a deviation between the predicted value and the actual value; The water supply fault detection module constructs a water supply fault detection mechanism to apply pressure disturbance to the secondary pressurized water supply network, detect the pressure response data of each measuring point in the network, and use a decision tree model to detect whether the secondary pressurized water supply network has a fault; The fault handling and pressure adjustment module handles the fault when the water supply fault detection mechanism detects a fault in the secondary pressurized water supply network; When the water supply fault detection mechanism does not detect a secondary pressurized water supply network fault, the current secondary pressurized water supply pressure is adjusted to adjust the water supply pressure value to a normal range.

9. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; The processor executes the artificial intelligence-based secondary pressurized domestic water supply remote early warning method described in any one of claims 1 to 7 by calling the computer program stored in the memory.

10. A computer-readable storage medium, characterized in that: It includes storing instructions, which, when executed on a computer, enable the computer to execute the artificial intelligence-based secondary pressurized domestic water supply remote early warning method as described in any one of claims 1 to 7.

Citation Information

Patent Citations

  • Hot water supply network intelligent management method based on cloud computing technology

    CN116777077A

  • Intelligent leakage monitoring method based on edge learning

    CN117113241A

  • Intelligent water affair comprehensive management system and method based on big data

    CN117892921A

  • Remote monitoring and fault prediction system for water chiller

    CN118194150A

Cited By

  • Constant-pressure water supply control method and system for secondary-supply standardized pump house and medium

    CN119294689A

  • Secondary water supply water quality collaborative management platform system

    CN119379489A

  • Repair processing method and system based on intelligent customer service, medium and program product

    CN120198104A

  • Repair processing method, system, medium and program product based on intelligent customer service

    CN120198104B

  • Secondary water supply operation data processing method and system based on multi-dimensional analysis

    CN120995314A