Remote water meter reading method and system and electronic equipment

Abstract

The invention discloses a remote water meter reading method and system and electronic equipment, and particularly relates to intelligent water meter fault analysis, which comprises the following steps: acquiring water meter monitoring data of n intelligent water meters according to an electric signal, and generating a water meter monitoring coefficient based on the water meter monitoring data; the water meter monitoring data comprises actually measured fluctuation data and preset standard fluctuation data; extracting a water meter monitoring coefficient time sequence set of the nth intelligent water meter, inputting historical water meter monitoring coefficients in the water meter monitoring coefficient time sequence set into a pre-constructed first deep learning model, and predicting water meter monitoring coefficients at a future T moment; according to the invention, correct water meter monitoring data can be sent to the intelligent water meter, the abnormal intelligent water meter and the fault reason can be found quickly based on the water meter monitoring data, water management personnel can arrive at the corresponding position of the abnormal intelligent water meter in time, and the abnormal intelligent water meter can be repaired or replaced quickly according to the fault reason of the abnormal intelligent water meter. And the loss caused by the abnormal intelligent water meter is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent water meter fault analysis, and more specifically, to a water meter remote meter reading method, system and electronic equipment. Background Art

[0002] Smart water meters are water meters that integrate advanced technologies, and their purpose is to provide smarter, more efficient and more convenient water management. Smart water meters usually include flow sensors, temperature sensors, communication modules and data processors. During meter reading, the water flow conditions are obtained through the built-in sensors of the smart water meters and transmitted to the cloud platform through the communication module. The cloud platform analyzes the data and processes the data in real time, realizing the remote meter reading function, reducing the workload of manual meter reading and improving meter reading efficiency.

[0003] Water meter counting is related to the water fee collection of thousands of households, and there can be no mistakes. However, a qualified smart water meter may have hardware failure after running for a period of time, resulting in abnormal water fee measurement and a mismatch between actual water consumption and readings. Therefore, it is crucial to quickly and accurately detect defects in smart water meters.

[0004] At present, the existing remote meter reading methods for water meters mainly judge whether an error exceeding the standard occurs through simple data comparison. For example, the application document with application publication number CN1 12325968A discloses a smart water meter based on the Internet of Things and its fault diagnosis system. Another example is the application document with application publication number CN109697842A, which discloses a remote processing method for abnormal data without continuous data for many days based on a smart water meter. Although such inventions compare and analyze historical data, the analysis process is too simple and easily leads to data judgment errors, thereby reducing the accuracy of the data.

[0005] Therefore, the present invention provides a water meter remote reading method, system and electronic equipment. Summary of the invention

[0006] In order to overcome the above defects of the prior art, the present invention provides a water meter remote reading method, system and electronic equipment to solve the problems raised in the above background technology.

[0007] To achieve the above object, the present invention provides the following technical solution: a water meter remote reading method, comprising:

[0008] Step 1: acquiring water meter monitoring data of n smart water meters according to the electrical signal, and generating a water meter monitoring coefficient based on the water meter monitoring data; n is an integer greater than zero; the water meter monitoring data includes measured fluctuation data and preset standard fluctuation data;

[0009] Step 2: extract the water meter monitoring coefficient time series set of the nth smart water meter, input the historical water meter monitoring coefficient in the water meter monitoring coefficient time series set into the pre-built first deep learning model, and predict the water meter monitoring coefficient at the future time T;

[0010] Step 3: preset a gradient threshold, compare the water meter monitoring coefficients corresponding to the n smart water meters at the future time T with the preset gradient threshold, so as to obtain L abnormal smart water meters, L∈n;

[0011] Step 4, obtaining the abnormal characteristic data of the Lth abnormal smart water meter, determining the fault type data of the abnormal smart water meter according to the abnormal characteristic data, and determining the fault analysis data corresponding to the fault type data based on the preset relationship between the fault type data and the fault analysis data, wherein the fault analysis data includes E abnormal causes and standard abnormal vibration FFT diagrams associated with the E abnormal causes; the fault type data includes the fault type and the position of the fault component; E is an integer greater than zero; the abnormal characteristic data includes an abnormal water pressure spectrum diagram and an abnormal current spectrum diagram;

[0012] Step 5: Obtain the measured abnormal vibration FFT graph of the Lth abnormal smart water meter within a preset time interval according to the location of the faulty component, compare the measured abnormal vibration FFT graph with the standard abnormal vibration FFT graph, and determine the abnormal cause of the abnormal smart water meter based on the comparison result.

[0013] Furthermore, a water meter monitoring coefficient is generated based on the water meter monitoring data, including:

[0014] Based on the water meter monitoring data, the measured fluctuation data of the nth smart water meter within a preset time interval is obtained; the measured fluctuation data includes a fluctuating water volume value, a fluctuating temperature value and a fluctuating pressure value,

[0015] Extracting preset standard fluctuation data from a system database, wherein the preset standard fluctuation data includes a preset standard water volume value, a preset standard temperature value, and a preset standard pressure value;

[0016] It should be noted that the preset standard fluctuation data is the average value calculated from the historical measured fluctuation data in the system database;

[0017] The fluctuating water volume value and the preset standard water volume value are calculated by formulating a water volume assessment coefficient, and the calculation formula of the water volume assessment coefficient is: Where Lpn represents the water volume evaluation coefficient of the nth smart water meter, Lyn represents the fluctuating water volume value of the nth smart water meter, and Ly′ n represents the preset standard water volume value of the nth smart water meter, α n represents the correction constant of the water volume assessment coefficient of the nth smart water meter;

[0018] The fluctuating temperature value and the preset standard temperature value are calculated by formulating a water temperature evaluation coefficient, and the calculation formula of the water temperature evaluation coefficient is: Where Wp n Represents the water temperature evaluation coefficient of the nth smart water meter, Wd n Represents the fluctuating temperature value of the nth smart water meter, Wd′ n Represents the preset standard temperature value of the nth smart water meter, α n represents the correction constant of the water temperature evaluation coefficient of the nth smart water meter;

[0019] The fluctuating pressure value and the preset standard pressure value are calculated by formulating a water pressure assessment coefficient, and the calculation formula of the water pressure assessment coefficient is: In the formula, Yp n represents the water pressure assessment coefficient of the nth smart water meter, Ys n Represents the fluctuating pressure value of the nth smart water meter, Ys′ n represents the preset standard pressure value of the nth smart water meter, γ n represents the correction constant of the water pressure assessment coefficient of the nth smart water meter;

[0020] The water volume assessment coefficient, water temperature assessment coefficient and water pressure assessment coefficient are dimensionlessly processed and correlated to obtain the water meter monitoring coefficient. The calculation formula of the water meter monitoring coefficient is:

[0021] Where SJn represents the water meter monitoring coefficient of the nth smart water meter, μ1 represents the weight factor of the water volume assessment coefficient, μ2 represents the weight factor of the water temperature assessment coefficient, and μ3 represents the weight factor of the water pressure assessment coefficient.

[0022] Furthermore, the method for obtaining a time series set of water meter monitoring coefficients includes:

[0023] The water meter monitoring coefficient of the nth smart water meter in the historical monitoring process is extracted from the system database and marked as the historical water meter monitoring coefficient. The extracted historical water meter monitoring coefficient is used to construct a water meter monitoring coefficient time series set. The water meter monitoring coefficient time series set includes i historical water meter monitoring coefficients. The time intervals for obtaining the i historical water meter monitoring coefficients are equal. The i historical water meter monitoring coefficients correspond to a smart water meter reading cycle. The smart water meter reading cycle is day, month or year.

[0024] Further, the pre-construction logic of the first deep learning model is as follows: preset the time step S, the sliding step B, and the sliding window length H according to the actual experience of water management personnel; use the sliding window method to convert the historical water meter monitoring coefficients in the time series set of water meter monitoring coefficients into multiple training samples, take the training samples as the input of the first deep learning model, predict the water meter monitoring coefficients after the time step S as the output, take the subsequent water meter monitoring coefficients of each training sample as the prediction target, and use the prediction accuracy as the training target to train the first deep learning model; generate the first deep learning model for predicting the water meter monitoring coefficients at the future T moment based on the historical water meter monitoring coefficients in the time series set of water meter monitoring coefficients; wherein, the first deep learning model is an RNN neural network model.

[0025] Further, the logic for obtaining L abnormal intelligent water meters includes:

[0026] Preset gradient thresholds Yz1 and Yz2, where Yz1 > Yz2, and compare the water meter monitoring coefficients SJn at the future T moment with the preset gradient thresholds;

[0027] If SJ n > Yz1, it indicates that the corresponding intelligent water meter is an abnormal intelligent water meter;

[0028] If Yz1 ≥ SJ n ≥ Yz2, it is determined that the corresponding intelligent water meter is a normal intelligent water meter;

[0029] If SJ n < Yz2, it indicates that the corresponding intelligent water meter is an abnormal intelligent water meter;

[0030] Statistically count all the abnormal intelligent water meters to obtain L abnormal intelligent water meters.

[0031] Further, obtaining the abnormal feature data of the Lth abnormal intelligent water meter includes:

[0032] Step 301. Obtain the water pressure data set of the abnormal intelligent water meter; use the time in the water pressure data set as the horizontal axis and the water pressure data in the water pressure data set as the vertical axis to construct the measured water pressure trend chart;

[0033] Step 302. Divide the water pressure trend chart equally according to the preset time interval to obtain a set of measured water pressure broken line charts, and the set of measured water pressure broken line charts includes G measured water pressure broken line charts, where G is an integer greater than zero;

[0034] Step 303. Extract the gth measured water pressure broken line chart in the set of measured water pressure broken line charts, where g ∈ G and the initial value of g is 1;

[0035] Step 304. Obtain the corresponding standard water pressure interval of the smart water meter, extract the standard water pressure line graph associated with the corresponding standard water pressure interval, calculate the similarity between the measured water pressure line graph and the standard water pressure line graph, if the similarity between the measured water pressure line graph and the standard water pressure line graph is greater than or equal to the preset water pressure similarity threshold, jump to step 305; if the similarity between the measured water pressure line graph and the standard water pressure line graph is less than the preset vibration similarity threshold, mark the measured water pressure line graph as an abnormal water pressure line graph, and jump to step 305;

[0036] Step 305. Set g=g+1 and jump back to step 303;

[0037] Step 306. Repeat the above steps 303 to 305 until g=G, then end the cycle and obtain multiple abnormal water pressure line graphs;

[0038] Step 307. Extract the similarity corresponding to each abnormal water pressure line graph, and perform Fourier transform on the abnormal water pressure line graph with the greatest similarity to obtain an abnormal water pressure spectrum graph; the Fourier transform is specifically one of a fast Fourier transform and a short-time Fourier transform;

[0039] Obtain the abnormal characteristic data of the Lth abnormal smart water meter, including:

[0040] Step 401. Obtain a current data set of an abnormal smart water meter; construct a current trend graph with the time in the current data set as the horizontal axis and the current data in the current data set as the vertical axis;

[0041] Step 402: Divide the current trend graph into equal parts according to a preset time interval to obtain a set of measured current line graphs, wherein the set of measured current line graphs includes D measured current line graphs, where D is an integer greater than zero;

[0042] Step 403: extract the dth measured current line graph in the measured current line graph set, where d is a positive integer greater than zero, and the initial value of d is 1;

[0043] Step 404. Obtain the corresponding standard current interval of the smart water meter, extract the standard current line graph associated with the corresponding standard current interval, calculate the similarity between the measured current line graph and the standard current line graph, if the similarity between the measured current line graph and the standard current line graph is greater than or equal to the preset current similarity threshold, jump to step 405; if the similarity between the measured current line graph and the standard current line graph is less than the preset vibration similarity threshold, mark the measured current line graph as an abnormal current line graph, and jump to step 405;

[0044] Step 405. Set h=h+1 and jump back to step 403;

[0045] Step 406. Repeat the above steps 403 to 405 until d=D, then end the loop and obtain multiple abnormal current line graphs;

[0046] Step 407: extract the similarity corresponding to each abnormal current line graph, and perform Fourier transform on the abnormal current line graph with the greatest similarity to obtain an abnormal current spectrum graph; the Fourier transform is specifically one of a fast Fourier transform and a short-time Fourier transform.

[0047] Furthermore, the fault type data of the abnormal smart water meter is determined, including:

[0048] Obtain abnormal water pressure spectrum and abnormal current spectrum of abnormal smart water meters;

[0049] Inputting the abnormal water pressure spectrum diagram and the abnormal current spectrum diagram into the fault identification model to determine the fault type data of the abnormal smart water meter;

[0050] The generation logic of the fault identification model is as follows: obtaining historical fault data pre-stored in the system database for training the fault identification model, wherein the historical fault data includes abnormal water pressure spectrum diagram, abnormal current spectrum diagram and fault type; dividing the historical fault data for training the fault identification model into a type training set and a type test set, constructing a regression network model, using the abnormal water pressure spectrum diagram and abnormal current spectrum diagram in the type training set as the input of the regression network model, using the fault type in the type training set as the output of the regression network model, training the regression network model to obtain an initial regression network model; using the type test set to perform model testing on the initial regression network model, and screening the corresponding initial regression network model with a preset test accuracy as the fault identification model, wherein the regression network model includes a random forest regression algorithm model, a support vector machine regression algorithm model and a neural network algorithm model.

[0051] Furthermore, the measured abnormal vibration FFT graph is compared with the standard abnormal vibration FFT graph, and the abnormal cause of the abnormal smart water meter is determined according to the comparison result, including:

[0052] A vibration frequency fluctuation diagram of the smart water meter is obtained within a preset time interval, and the vibration frequency fluctuation diagram is Fourier transformed into an FFT diagram of the measured abnormal vibration; the vibration frequency fluctuation diagram is generated by r vibration frequencies obtained by real-time acquisition by the vibration sensor within the preset time interval, where r is an integer greater than 1;

[0053] Vectorize the measured abnormal vibration FFT image and the standard abnormal vibration FFT image, and calculate the image similarity between the vectorized measured abnormal vibration FFT image and the standard abnormal vibration FFT image according to the cosine similarity model;

[0054] It is determined whether the image similarity is greater than a preset image similarity threshold. If so, a comparison result is generated, and the abnormal cause corresponding to the standard abnormal vibration FFT image is extracted according to the comparison result as the abnormal cause of the abnormal smart water meter.

[0055] In a second aspect, the present invention provides a water meter remote reading system, which is used to implement the above-mentioned water meter remote reading method, comprising:

[0056] A data generation module, used to obtain water meter monitoring data of n smart water meters according to the electrical signal, and generate a water meter monitoring coefficient based on the water meter monitoring data; n is an integer greater than zero; the water meter monitoring data includes measured fluctuation data and preset standard fluctuation data;

[0057] A data prediction module is used to extract a time series set of water meter monitoring coefficients of the nth smart water meter, input the historical water meter monitoring coefficients in the time series set of water meter monitoring coefficients into a pre-built first deep learning model, and predict the water meter monitoring coefficients at the future time T;

[0058] The data comparison module presets a gradient threshold, compares the water meter monitoring coefficients corresponding to the n smart water meters at the future time T with the preset gradient threshold, so as to obtain L abnormal smart water meters, L∈n;

[0059] A data analysis module is used to obtain abnormal characteristic data of the Lth abnormal smart water meter, determine the fault type data of the abnormal smart water meter according to the abnormal characteristic data, and determine the fault analysis data corresponding to the fault type data based on a preset relationship between the fault type data and the fault analysis data, wherein the fault analysis data includes E abnormal causes and a standard abnormal vibration FFT diagram associated with the E abnormal causes; the fault type data includes a fault type and a fault component position; E is an integer greater than zero; the abnormal characteristic data includes an abnormal water pressure spectrum diagram and an abnormal current spectrum diagram;

[0060] The data judgment module is used to obtain the measured abnormal vibration FFT diagram of the Lth abnormal smart water meter within a preset time interval according to the position of the faulty component, compare the measured abnormal vibration FFT diagram with the standard abnormal vibration FFT diagram, and determine the abnormal cause of the abnormal smart water meter based on the comparison result.

[0061] In a third aspect, the present invention provides an electronic device, comprising: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0062] The processor executes the above-mentioned water meter remote reading method by calling the computer program stored in the memory.

[0063] Technical effects and advantages of the present invention:

[0064] The present invention obtains water meter monitoring data of n smart water meters according to electrical signals, and generates water meter monitoring coefficients based on the water meter monitoring data; extracts a water meter monitoring coefficient time series set of the nth smart water meter, inputs the historical water meter monitoring coefficients in the water meter monitoring coefficient time series set into a pre-constructed first deep learning model, and predicts the water meter monitoring coefficients at a future time T; presets a gradient threshold, and compares the water meter monitoring coefficients at a future time T corresponding to the n smart water meters with the preset gradient threshold to obtain L abnormal smart water meters; obtains abnormal feature data of the Lth abnormal smart water meter, determines fault type data of the abnormal smart water meter according to the abnormal feature data, and determines the fault type based on a preset relationship between the fault type data and the fault analysis data. Fault analysis data corresponding to the fault type data, the fault type data including the fault type and the fault component position; obtaining the measured abnormal vibration FFT graph of the Lth abnormal smart water meter within a preset time interval according to the fault component position, comparing the measured abnormal vibration FFT graph with the standard abnormal vibration FFT graph, and determining the abnormal cause of the abnormal smart water meter according to the comparison result; the present invention is conducive to sending correct water meter monitoring data to the smart water meter, and quickly discovering the abnormal smart water meter and the cause of the failure based on the water meter monitoring data, so as to facilitate water management personnel to reach the corresponding position of the abnormal smart water meter in time, and quickly repair or replace the abnormal smart water meter according to the fault cause of the abnormal smart water meter, thereby reducing the loss caused by the abnormal smart water meter. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 This is a flow chart of the water meter remote meter reading method of Example 1;

[0066] Figure 2 This is a schematic diagram of a water meter remote meter reading system in Example 2;

[0067] Figure 3 This is a schematic diagram of an electronic device according to Embodiment 3;

[0068] Figure 4 A schematic diagram of a computer-readable storage medium of Example 4. DETAILED DESCRIPTION

[0069] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0070] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0071] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, a first unit may be referred to as a second unit, and a similar second unit may be referred to as a first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0072] Example 1

[0073] See also Figure 1 As shown, this embodiment discloses a water meter remote meter reading method, including:

[0074] Step 1: acquiring water meter monitoring data of n smart water meters according to the electrical signal, and generating a water meter monitoring coefficient based on the water meter monitoring data; n is an integer greater than zero; the water meter monitoring data includes measured fluctuation data and preset standard fluctuation data;

[0075] It should be noted that the N smart water meters are pre-set in the target city according to the urban water pipe topology network, and each of the n smart water meters is provided with a remote meter reading device, which receives the electrical signal from the remote server and collects the water meter monitoring data. The water meter monitoring data is stored in the system database. A plurality of sensors are installed on the remote meter reading device, and the sensors include but are not limited to flow sensors, temperature sensors, vibration sensors or pressure sensors, etc. The type of the remote meter reading device is determined by the water management personnel according to the situation and is not excessively limited here.

[0076] In a preferred embodiment, generating a water meter monitoring coefficient based on water meter monitoring data includes:

[0077] 101. Based on the water meter monitoring data, the measured fluctuation data of the nth smart water meter within a preset time interval is obtained; the measured fluctuation data includes a fluctuation water volume value, a fluctuation temperature value and a fluctuation pressure value,

[0078] 102. Extracting preset standard fluctuation data from the system database, wherein the preset standard fluctuation data includes a preset standard water volume value, a preset standard temperature value, and a preset standard pressure value;

[0079] It should be noted that the preset standard fluctuation data is the average value calculated from the historical measured fluctuation data in the system database;

[0080] 103. The fluctuating water volume value and the preset standard water volume value are calculated by formulating a water volume assessment coefficient, and the calculation formula of the water volume assessment coefficient is: In the formula, Lp n represents the water volume assessment coefficient of the nth smart water meter, Ly n Represents the fluctuating water volume value of the nth smart water meter, Ly′ n represents the preset standard water volume value of the nth smart water meter, α n represents the correction constant of the water volume assessment coefficient of the nth smart water meter;

[0081] 104. The fluctuating temperature value and the preset standard temperature value are calculated by formulating a water temperature evaluation coefficient, and the calculation formula of the water temperature evaluation coefficient is: Where Wp n Represents the water temperature evaluation coefficient of the nth smart water meter, Wd n Represents the fluctuating temperature value of the nth smart water meter, Wd′ n Represents the preset standard temperature value of the nth smart water meter, α n represents the correction constant of the water temperature evaluation coefficient of the nth smart water meter;

[0082] 105. The fluctuating pressure value and the preset standard pressure value are calculated by formulating a water pressure assessment coefficient, and the calculation formula of the water pressure assessment coefficient is: Where Wp n represents the water pressure assessment coefficient of the nth smart water meter, Ys n Represents the fluctuating pressure value of the nth smart water meter, Wd′ n represents the preset standard pressure value of the nth smart water meter, γ n represents the correction constant of the water pressure assessment coefficient of the nth smart water meter;

[0083] 106. The water volume assessment coefficient, water temperature assessment coefficient and water pressure assessment coefficient are dimensionless and correlated to obtain the water meter monitoring coefficient. The calculation formula of the water meter monitoring coefficient is:

[0084] In the formula, SJ nrepresents the water meter monitoring coefficient of the nth smart water meter, μ1 represents the weight factor of the water volume assessment coefficient, μ2 represents the weight factor of the water temperature assessment coefficient, and μ3 represents the weight factor of the water pressure assessment coefficient;

[0085] Step 2: extract the water meter monitoring coefficient time series set of the nth smart water meter, input the historical water meter monitoring coefficient in the water meter monitoring coefficient time series set into the pre-built first deep learning model, and predict the water meter monitoring coefficient at the future time T;

[0086] It should be noted that the method for obtaining the time series set of water meter monitoring coefficients includes:

[0087] Extract the water meter monitoring coefficient of the nth smart water meter in the historical monitoring process from the system database and mark it as the historical water meter monitoring coefficient. Use the extracted historical water meter monitoring coefficient to construct a water meter monitoring coefficient time series set. The water meter monitoring coefficient time series set includes i historical water meter monitoring coefficients. The time intervals of obtaining the i historical water meter monitoring coefficients are equal. The i historical water meter monitoring coefficients correspond to one smart water meter reading cycle.

[0088] The meter reading cycle of the smart water meter can be daily, monthly or annual, and can also be set by water management personnel based on actual experience, and is not specifically limited here.

[0089] Specifically, the pre-construction logic of the first deep learning model is: preset the time step S, sliding step B and sliding window length H according to the actual experience of water management personnel; convert the historical water meter monitoring coefficients in the water meter monitoring coefficient time series set into multiple training samples using the sliding window method, use the training samples as the input of the first deep learning model, predict the water meter monitoring coefficient after the time step S as the output, and use the subsequent water meter monitoring coefficient of each training sample as the prediction target. The first deep learning model is trained with the prediction accuracy as the training target; generate a first deep learning model that predicts the water meter monitoring coefficient at the future time T based on the historical water meter monitoring coefficients in the water meter monitoring coefficient time series set; wherein, the first deep learning model can be an RNN neural network model; by using the water meter monitoring coefficient time series set, the future water meter monitoring coefficients of n smart water meters are predicted, thereby realizing the prediction of the smart water meter reading situation to be predicted based on the future water meter monitoring coefficient, and predicting the water meter monitoring coefficient from a macro level;

[0090] It should be noted that the water meter monitoring coefficient time series set is divided into A sliding windows of equal size, the water meter monitoring coefficient in each window is taken as a sample, and the water meter monitoring coefficient of the window at the future T time is taken as a digital label. It should be noted that one sample corresponds to one digital label, and one sample and the corresponding digital label constitute one training data, and multiple groups of training data constitute a training set;

[0091] Further by way of example, it is assumed that the set A of water meter monitoring coefficient time series contains 10 sets of historical water meter monitoring coefficients, A = {A1, A2, A3, A4, A5,..., A 10}, A a is the a-th set of historical water meter monitoring coefficients. Multiple training samples are constructed using a sliding window. The prediction time step is set to 1, the length H of the sliding window is 5, and the sliding step B is 1. Then each training sample generated contains 5 consecutive historical water meter monitoring coefficients, and the next water meter monitoring coefficient of the 5 consecutive historical water meter monitoring coefficients is used as the prediction target; for example:

[0092] {A1, A2, A3, A4, A5} is used as training data, and the corresponding prediction target is A6;

[0093] {A2, A3, A4, A5, A6} is used as training data, and the corresponding prediction target is A7;

[0094] And so on, for training the first deep learning model for predicting the water meter monitoring coefficients at future moments.

[0095] Step 3: Preset a gradient threshold, and compare the water meter monitoring coefficients at the future T moment corresponding to n intelligent water meters with the preset gradient threshold to obtain L abnormal intelligent water meters, where L ∈ n;

[0096] The logic for obtaining L abnormal intelligent water meters includes:

[0097] 201. Preset gradient thresholds Yz1 and Yz2, where Yz1 > Yz2, and compare the water meter monitoring coefficient SJ at the future T moment n with the preset gradient threshold;

[0098] 202. If SJ n > Yz1, it indicates that the corresponding intelligent water meter is an abnormal intelligent water meter;

[0099] If Yz1 ≥ SJ n ≥ Yz2, it is determined that the corresponding intelligent water meter is a normal intelligent water meter;

[0100] If SJ n < Yz2, it indicates that the corresponding intelligent water meter is an abnormal intelligent water meter;

[0101] 203. Statistically count all the abnormal intelligent water meters to obtain L abnormal intelligent water meters;

[0102] Step 4, obtaining abnormal characteristic data of the Lth abnormal smart water meter, determining the fault type data of the abnormal smart water meter according to the abnormal characteristic data, and determining the fault analysis data corresponding to the fault type data based on a preset relationship between the fault type data and the fault analysis data, wherein the fault analysis data includes E abnormal causes and a standard abnormal vibration FFT graph associated with the E abnormal causes; the fault type data includes a fault type and a fault component position; and E is an integer greater than zero;

[0103] Specifically, the abnormal characteristic data shown include an abnormal water pressure spectrum diagram and an abnormal current spectrum diagram;

[0104] In a specific implementation, obtaining abnormal characteristic data of the Lth abnormal smart water meter includes:

[0105] 301. Obtain a water pressure data set of an abnormal smart water meter; construct a measured water pressure trend graph with the time in the water pressure data set as the horizontal axis and the water pressure data in the water pressure data set as the vertical axis;

[0106] 302. Divide the water pressure trend graph into equal parts according to a preset time interval to obtain a set of measured water pressure line graphs, wherein the set of measured water pressure line graphs includes G measured water pressure line graphs, where G is an integer greater than zero;

[0107] 303. Extract the gth measured water pressure line graph from the measured water pressure line graph set, g∈G, and the initial value of g is 1;

[0108] 304. Obtain the corresponding standard water pressure interval of the smart water meter, extract the standard water pressure line graph associated with the corresponding standard water pressure interval, calculate the similarity between the measured water pressure line graph and the standard water pressure line graph, if the similarity between the measured water pressure line graph and the standard water pressure line graph is greater than or equal to the preset water pressure similarity threshold, jump to step 305; if the similarity between the measured water pressure line graph and the standard water pressure line graph is less than the preset vibration similarity threshold, mark the measured water pressure line graph as an abnormal water pressure line graph, and jump to step 305;

[0109] 305. Set g=g+1, and jump back to step 303;

[0110] 306. Repeat the above steps 303 to 305 until g=G, then end the cycle and obtain multiple abnormal water pressure line graphs;

[0111] 307. Extract the similarity corresponding to each abnormal water pressure line graph, and perform Fourier transform on the abnormal water pressure line graph with the greatest similarity to obtain an abnormal water pressure spectrum graph;

[0112] In a specific implementation, obtaining abnormal characteristic data of the Lth abnormal smart water meter further includes:

[0113] 401. Obtain a current data set of an abnormal smart water meter; construct a current trend graph with the time in the current data set as the horizontal axis and the current data in the current data set as the vertical axis;

[0114] 402. Divide the current trend graph into equal parts according to a preset time interval to obtain a set of measured current line graphs, wherein the set of measured current line graphs includes D measured current line graphs, where D is an integer greater than zero;

[0115] 403. Extract the dth measured current line graph in the measured current line graph set, where d is a positive integer greater than zero, and the initial value of d is 1;

[0116] 404. Obtain the corresponding standard current interval of the smart water meter, extract the standard current line graph associated with the corresponding standard current interval, calculate the similarity between the measured current line graph and the standard current line graph, if the similarity between the measured current line graph and the standard current line graph is greater than or equal to the preset current similarity threshold, jump to step 405; if the similarity between the measured current line graph and the standard current line graph is less than the preset vibration similarity threshold, mark the measured current line graph as an abnormal current line graph, and jump to step 405;

[0117] It should be noted that: a plurality of current intervals are pre-stored in the system database, and each current interval is associated with a standard current line graph, which reflects the normal current representation of the smart water meter under normal circumstances;

[0118] 405. Let h=h+1, and jump back to step 403;

[0119] 406. Repeat the above steps 403 to 405 until d=D, then end the loop and obtain multiple abnormal current line graphs;

[0120] 407. Extract the similarity corresponding to each abnormal current line graph, and perform Fourier transform on the abnormal current line graph with the largest similarity to obtain an abnormal current spectrum graph;

[0121] It should be noted that the Fourier transform is specifically one of a fast Fourier transform or a short-time Fourier transform;

[0122] In implementation, the fault type data of abnormal smart water meters are determined, including:

[0123] Obtain abnormal water pressure spectrum and abnormal current spectrum of abnormal smart water meters;

[0124] Inputting the abnormal water pressure spectrum diagram and the abnormal current spectrum diagram into the fault identification model to determine the fault type data of the abnormal smart water meter;

[0125] Specifically, the generation logic of the fault identification model is as follows: obtaining historical fault data pre-stored in the system database for training the fault identification model, wherein the historical fault data includes an abnormal water pressure spectrum diagram, an abnormal current spectrum diagram, and a fault type; dividing the historical fault data for training the fault identification model into a type training set and a type test set, constructing a regression network model, using the abnormal water pressure spectrum diagram and the abnormal current spectrum diagram in the type training set as inputs of the regression network model, using the fault type in the type training set as outputs of the regression network model, training the regression network model to obtain an initial regression network model; using the type test set to perform a model test on the initial regression network model, and screening the corresponding initial regression network model with a test accuracy greater than or equal to a preset value as the fault identification model;

[0126] Wherein, the regression network model includes but is not limited to a random forest regression algorithm model, a support vector machine regression algorithm model, a neural network algorithm model, etc.;

[0127] It should be noted that the fault type includes u kinds of fault component names, such as: mechanical components (gears, mechanical transmission devices or metering pointers), battery components (batteries or external power supplies) and sensors (flow sensors, temperature sensors or water pressure sensors), etc. The location of the fault component is determined according to the name of the fault component. Specifically, the installation position of the corresponding fault component can be obtained according to the smart water meter design drawings.

[0128] Step 5: Obtain the measured abnormal vibration FFT graph of the Lth abnormal smart water meter within a preset time interval according to the position of the faulty component, compare the measured abnormal vibration FFT graph with the standard abnormal vibration FFT graph, and determine the abnormal cause of the abnormal smart water meter according to the comparison result;

[0129] Specifically, the measured abnormal vibration FFT graph is compared with the standard abnormal vibration FFT graph, and the abnormal cause of the abnormal smart water meter is determined according to the comparison result, including:

[0130] A vibration frequency fluctuation diagram of the smart water meter is obtained within a preset time interval, and the vibration frequency fluctuation diagram is Fourier transformed into an FFT diagram of the measured abnormal vibration; the vibration frequency fluctuation diagram is generated by r vibration frequencies obtained by real-time acquisition by the vibration sensor within the preset time interval, where r is an integer greater than 1;

[0131] Vectorize the measured abnormal vibration FFT image and the standard abnormal vibration FFT image, and calculate the image similarity between the vectorized measured abnormal vibration FFT image and the standard abnormal vibration FFT image according to the cosine similarity model;

[0132] It should be noted that the purpose of vectorizing the measured abnormal vibration FFT graph and the standard abnormal vibration FFT graph is to convert the complex vibration spectrum data into a form that is easier to process and analyze, so as to better identify and understand the patterns and features in the vibration data.

[0133] Determine whether the image similarity is greater than a preset image similarity threshold, and if so, generate a comparison result, and extract the abnormal cause corresponding to the standard abnormal vibration FFT graph as the abnormal cause of the abnormal smart water meter according to the comparison result;

[0134] It should be noted that: if there is no comparison result greater than the preset image similarity threshold, a null value is displayed;

[0135] Optionally, the method further includes:

[0136] Determine whether there is a null value in the comparison result, and if so, record the corresponding measured abnormal vibration FFT image as a non-pre-stored image;

[0137] updating the correspondence between the second standard abnormal vibration FFT graph and the fault analysis data according to the non-prestored image;

[0138] The corresponding position data of the abnormal smart water meter in the urban water pipe topology network is obtained according to the comparison results or non-pre-stored images, and a fault warning is sent to the system server; it is convenient for water management personnel to reach the corresponding position of the abnormal smart water meter in time, and quickly repair or replace the abnormal smart water meter according to the cause of the fault of the abnormal smart water meter, thereby reducing the loss caused by the abnormal smart water meter.

[0139] It should be noted that: the remote meter reading device is connected to the smart water meter through remote communication.

[0140] This embodiment obtains water meter monitoring data of n smart water meters according to electrical signals, and generates water meter monitoring coefficients based on the water meter monitoring data; extracts a time series set of water meter monitoring coefficients of the nth smart water meter, inputs the historical water meter monitoring coefficients in the time series set of water meter monitoring coefficients into a pre-constructed first deep learning model, and predicts the water meter monitoring coefficients at a future time T; presets a gradient threshold, and compares the water meter monitoring coefficients at a future time T corresponding to the n smart water meters with the preset gradient threshold to obtain L abnormal smart water meters; obtains abnormal feature data of the Lth abnormal smart water meter, determines fault type data of the abnormal smart water meter according to the abnormal feature data, and determines fault analysis data corresponding to the fault type data based on a preset relationship between the fault type data and the fault analysis data, wherein the fault The analysis data includes E abnormal causes and standard abnormal vibration FFT graphs associated with the E abnormal causes; the fault type data includes the fault type and the fault component location; the measured abnormal vibration FFT graph of the Lth abnormal smart water meter within a preset time interval is obtained according to the fault component location, and the measured abnormal vibration FFT graph is compared with the standard abnormal vibration FFT graph, and the abnormal cause of the abnormal smart water meter is determined according to the comparison result, which is conducive to sending correct water meter monitoring data to the smart water meter, and quickly discovering the abnormal smart water meter and the cause of the fault based on the water meter monitoring data, so as to facilitate water management personnel to reach the corresponding position of the abnormal smart water meter in time, and quickly repair or replace the abnormal smart water meter according to the fault cause of the abnormal smart water meter, thereby reducing the loss caused by the abnormal smart water meter.

[0141] The formulas involved in the above are all calculated by removing dimensions and taking their numerical values. They are a formula that is closest to the actual situation obtained by collecting a large amount of data and performing software simulation. The weight factors in the formula and the preset thresholds in the analysis process are set by technicians in this field according to actual conditions or obtained by simulating a large amount of data; the size of the weight factor is to quantify each parameter to obtain a specific value for subsequent comparison. The size of the weight factor depends on the amount of sample data and the corresponding processing coefficient initially set by technicians in this field for each group of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0142] Example 2

[0143] See also Figure 2 As shown, this embodiment provides a water meter remote meter reading system, including:

[0144] A data generation module, used to obtain water meter monitoring data of n smart water meters according to the electrical signal, and generate a water meter monitoring coefficient based on the water meter monitoring data; n is an integer greater than zero; the water meter monitoring data includes measured fluctuation data and preset standard fluctuation data;

[0145] A data prediction module is used to extract a time series set of water meter monitoring coefficients of the nth smart water meter, input the historical water meter monitoring coefficients in the time series set of water meter monitoring coefficients into a pre-built first deep learning model, and predict the water meter monitoring coefficients at the future time T;

[0146] The data comparison module presets a gradient threshold, compares the water meter monitoring coefficients corresponding to the n smart water meters at the future time T with the preset gradient threshold, so as to obtain L abnormal smart water meters, L∈n;

[0147] A data analysis module is used to obtain abnormal characteristic data of the Lth abnormal smart water meter, determine the fault type data of the abnormal smart water meter according to the abnormal characteristic data, and determine the fault analysis data corresponding to the fault type data based on a preset relationship between the fault type data and the fault analysis data, wherein the fault analysis data includes E abnormal causes and a standard abnormal vibration FFT diagram associated with the E abnormal causes; the fault type data includes a fault type and a fault component position; E is an integer greater than zero; the abnormal characteristic data includes an abnormal water pressure spectrum diagram and an abnormal current spectrum diagram;

[0148] The data judgment module is used to obtain the measured abnormal vibration FFT diagram of the Lth abnormal smart water meter within a preset time interval according to the position of the faulty component, compare the measured abnormal vibration FFT diagram with the standard abnormal vibration FFT diagram, and determine the abnormal cause of the abnormal smart water meter based on the comparison result.

[0149] Example 3

[0150] See also Figure 3 As shown, this embodiment provides an electronic device, including: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0151] The processor executes a water meter remote reading method of embodiment 1 by calling the computer program stored in the memory.

[0152] Example 4

[0153] See also Figure 4 As shown, this embodiment provides a computer-readable storage medium storing instructions. When the instructions are executed on a computer, the computer executes a water meter remote reading method according to Embodiment 1.

[0154] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center via a wired network. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0155] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0156] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0157] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only one. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0158] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0159] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0160] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0161] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0162] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A water meter remote reading method, characterized in that: include: Step 1: Acquire water meter monitoring data of n smart water meters according to the electrical signal, and generate a water meter monitoring coefficient based on the water meter monitoring data; n is an integer greater than zero; the water meter monitoring data includes measured fluctuation data and preset standard fluctuation data; Step 2: extract the water meter monitoring coefficient time series set of the nth smart water meter, input the historical water meter monitoring coefficient in the water meter monitoring coefficient time series set into the pre-built first deep learning model, and predict the water meter monitoring coefficient at the future time T; Step 3: preset a gradient threshold, compare the water meter monitoring coefficients corresponding to the n smart water meters at the future time T with the preset gradient threshold, so as to obtain L abnormal smart water meters, L∈n; Step 4, obtaining the abnormal characteristic data of the Lth abnormal smart water meter, determining the fault type data of the abnormal smart water meter according to the abnormal characteristic data, and determining the fault analysis data corresponding to the fault type data based on the preset relationship between the fault type data and the fault analysis data, wherein the fault analysis data includes E abnormal causes and standard abnormal vibration FFT diagrams associated with the E abnormal causes; the fault type data includes the fault type and the position of the fault component; E is an integer greater than zero; the abnormal characteristic data includes an abnormal water pressure spectrum diagram and an abnormal current spectrum diagram; Step 5: Obtain the measured abnormal vibration FFT graph of the Lth abnormal smart water meter within a preset time interval according to the location of the faulty component, compare the measured abnormal vibration FFT graph with the standard abnormal vibration FFT graph, and determine the abnormal cause of the abnormal smart water meter based on the comparison result.

2. A water meter remote reading method according to claim 1, characterized in that: The methods for generating water meter monitoring coefficients based on water meter monitoring data include: Based on the water meter monitoring data, the measured fluctuation data of the nth smart water meter within a preset time interval is obtained; the measured fluctuation data includes a fluctuation water volume value, a fluctuation temperature value and a fluctuation pressure value; Extracting preset standard fluctuation data from the system database, wherein the preset standard fluctuation data includes a preset standard water volume value, a preset standard temperature value, and a preset standard pressure value; the preset standard fluctuation data is an average value calculated from the historical measured fluctuation data in the system database; The fluctuating water volume value and the preset standard water volume value are calculated by formulating a water volume assessment coefficient, and the calculation formula of the water volume assessment coefficient is: , where represents the water volume assessment coefficient of the nth smart water meter, Represents the fluctuating water volume value of the nth smart water meter, Indicates the preset standard water volume value of the nth smart water meter, represents the correction constant of the water volume assessment coefficient of the nth smart water meter; The fluctuating temperature value and the preset standard temperature value are calculated by formulating a water temperature evaluation coefficient, and the calculation formula of the water temperature evaluation coefficient is: , where represents the water temperature evaluation coefficient of the nth smart water meter, represents the fluctuating temperature value of the nth smart water meter, Indicates the preset standard temperature value of the nth smart water meter, represents the correction constant of the water temperature evaluation coefficient of the nth smart water meter; The fluctuating pressure value and the preset standard pressure value are calculated by formulating a water pressure assessment coefficient, and the calculation formula of the water pressure assessment coefficient is: , where represents the water pressure assessment coefficient of the nth smart water meter, Indicates the fluctuating pressure value of the nth smart water meter, Indicates the preset standard pressure value of the nth smart water meter, represents the correction constant of the water pressure assessment coefficient of the nth smart water meter; The water volume assessment coefficient, water temperature assessment coefficient and water pressure assessment coefficient are dimensionlessly processed and correlated to obtain the water meter monitoring coefficient. The calculation formula of the water meter monitoring coefficient is: ; In the formula, represents the water meter monitoring coefficient of the nth smart water meter, represents the weight factor of the water quantity assessment coefficient, represents the weight factor of the water temperature assessment coefficient, Represents the weighting factor of the water pressure assessment coefficient.

3. A water meter remote reading method according to claim 2, characterized in that: The method for obtaining a time series set of water meter monitoring coefficients includes: The water meter monitoring coefficient of the nth smart water meter in the historical monitoring process is extracted from the system database and marked as the historical water meter monitoring coefficient. The extracted historical water meter monitoring coefficient is used to construct a water meter monitoring coefficient time series set. The water meter monitoring coefficient time series set includes i historical water meter monitoring coefficients. The time intervals for obtaining the i historical water meter monitoring coefficients are equal. The i historical water meter monitoring coefficients correspond to a smart water meter reading cycle. The smart water meter reading cycle is day, month or year.

4. A water meter remote reading method according to claim 3, characterized in that: The pre-construction logic of the first deep learning model is: preset time step S, sliding step B and sliding window length H; convert the historical water meter monitoring coefficients in the water meter monitoring coefficient time series set into multiple training samples using the sliding window method, use the training samples as the input of the first deep learning model, predict the water meter monitoring coefficient after the time step S as the output, and use the subsequent water meter monitoring coefficient of each training sample as the prediction target. The first deep learning model is trained with the prediction accuracy as the training target; generate a first deep learning model that predicts the water meter monitoring coefficient at the future time T based on the historical water meter monitoring coefficients in the water meter monitoring coefficient time series set; wherein the first deep learning model is an RNN neural network model.

5. A water meter remote reading method according to claim 4, characterized in that: The logic for obtaining L abnormal smart water meters includes: Preset gradient threshold and ,in > , the water meter monitoring coefficient at time T in the future Compare with the preset gradient threshold; like > , it means that the corresponding smart water meter is an abnormal smart water meter; like , then the corresponding smart water meter is determined to be a normal smart water meter; like , it means that the corresponding smart water meter is an abnormal smart water meter; All abnormal smart water meters are counted to obtain L abnormal smart water meters.

6. A water meter remote reading method according to claim 5, characterized in that: Obtain the abnormal feature data of the Lth abnormal smart water meter, including: Step 301. Obtain a water pressure data set of an abnormal smart water meter; construct a measured water pressure trend graph with the time in the water pressure data set as the horizontal axis and the water pressure data in the water pressure data set as the vertical axis; Step 302: Divide the water pressure trend graph into equal parts according to a preset time interval to obtain a set of measured water pressure line graphs, wherein the set of measured water pressure line graphs includes G measured water pressure line graphs, where G is an integer greater than zero; Step 303: extract the gth measured water pressure line graph in the measured water pressure line graph set, g∈G, and the initial value of g is 1; Step 304. Obtain the corresponding standard water pressure interval of the smart water meter, extract the standard water pressure line graph associated with the corresponding standard water pressure interval, calculate the similarity between the measured water pressure line graph and the standard water pressure line graph, if the similarity between the measured water pressure line graph and the standard water pressure line graph is greater than or equal to the preset water pressure similarity threshold, jump to step 305; if the similarity between the measured water pressure line graph and the standard water pressure line graph is less than the preset vibration similarity threshold, mark the measured water pressure line graph as an abnormal water pressure line graph, and jump to step 305; Step 305. Set g=g+1 and jump back to step 303; Step 306. Repeat the above steps 303 to 305 until g=G, then end the cycle and obtain multiple abnormal water pressure line graphs; Step 307. extract the similarity corresponding to each abnormal water pressure line graph, and perform Fourier transform on the abnormal water pressure line graph with the smallest similarity to obtain an abnormal water pressure spectrum graph; the Fourier transform is specifically one of a fast Fourier transform and a short-time Fourier transform; Obtain the abnormal characteristic data of the Lth abnormal smart water meter, including: Step 401. Obtain a current data set of an abnormal smart water meter; construct a current trend graph with the time in the current data set as the horizontal axis and the current data in the current data set as the vertical axis; Step 402: Divide the current trend graph into equal parts according to a preset time interval to obtain a set of measured current line graphs, wherein the set of measured current line graphs includes D measured current line graphs, where D is an integer greater than zero; Step 403: extract the dth measured current line graph in the measured current line graph set, where d is a positive integer greater than zero, and the initial value of d is 1; Step 404. Obtain the corresponding standard current interval of the smart water meter, extract the standard current line graph associated with the corresponding standard current interval, calculate the similarity between the measured current line graph and the standard current line graph, if the similarity between the measured current line graph and the standard current line graph is greater than or equal to the preset current similarity threshold, jump to step 405; if the similarity between the measured current line graph and the standard current line graph is less than the preset vibration similarity threshold, mark the measured current line graph as an abnormal current line graph, and jump to step 405; Step 405. Set h=h+1 and jump back to step 403; Step 406. Repeat the above steps 403 to 405 until d=D, then end the loop and obtain multiple abnormal current line graphs; Step 407: extract the similarity corresponding to each abnormal current line graph, and perform Fourier transform on the abnormal current line graph with the smallest similarity to obtain an abnormal current spectrum graph; the Fourier transform is specifically one of a fast Fourier transform and a short-time Fourier transform.

7. A water meter remote reading method according to claim 6, characterized in that: Determine the fault type data of abnormal smart water meters, including: Obtain abnormal water pressure spectrum and abnormal current spectrum of abnormal smart water meters; Inputting the abnormal water pressure spectrum diagram and the abnormal current spectrum diagram into the fault identification model to determine the fault type data of the abnormal smart water meter; The generation logic of the fault identification model is as follows: obtaining historical fault data pre-stored in the system database for training the fault identification model, wherein the historical fault data includes an abnormal water pressure spectrum diagram, an abnormal current spectrum diagram and a fault type; dividing the historical fault data for training the fault identification model into a type training set and a type test set, constructing a regression network model, using the abnormal water pressure spectrum diagram and the abnormal current spectrum diagram in the type training set as inputs of the regression network model, using the fault type in the type training set as outputs of the regression network model, training the regression network model to obtain an initial regression network model; using the type test set to perform a model test on the initial regression network model, and screening the corresponding initial regression network model with a test accuracy greater than or equal to a preset accuracy as the fault identification model, wherein the regression network model includes a random forest regression algorithm model, a support vector machine regression algorithm model or a neural network algorithm model; The fault type includes u kinds of fault component names, and the fault component location is determined according to the fault component name.

8. A water meter remote reading method according to claim 7, characterized in that: The measured abnormal vibration FFT graph is compared with the standard abnormal vibration FFT graph, and the abnormal cause of the abnormal smart water meter is determined according to the comparison result, including: A vibration frequency fluctuation diagram of the smart water meter is obtained within a preset time interval, and the vibration frequency fluctuation diagram is Fourier transformed into an FFT diagram of the measured abnormal vibration; the vibration frequency fluctuation diagram is generated by r vibration frequencies obtained by real-time acquisition by the vibration sensor within the preset time interval, where r is an integer greater than 1; Vectorize the measured abnormal vibration FFT image and the standard abnormal vibration FFT image, and calculate the image similarity between the vectorized measured abnormal vibration FFT image and the standard abnormal vibration FFT image according to the cosine similarity model; It is determined whether the image similarity is greater than a preset image similarity threshold. If so, a comparison result is generated, and the abnormal cause corresponding to the standard abnormal vibration FFT image is extracted according to the comparison result as the abnormal cause of the abnormal smart water meter.

9. A water meter remote reading system, used for implementing a water meter remote reading method according to any one of claims 1 to 8, characterized in that: include: A data generation module, used for acquiring water meter monitoring data of n smart water meters according to the electrical signals, and generating water meter monitoring coefficients based on the water meter monitoring data; n is an integer greater than zero; the water meter monitoring data includes measured fluctuation data and preset standard fluctuation data; A data prediction module is used to extract a time series set of water meter monitoring coefficients of the nth smart water meter, input the historical water meter monitoring coefficients in the time series set of water meter monitoring coefficients into a pre-built first deep learning model, and predict the water meter monitoring coefficients at the future time T; The data comparison module presets a gradient threshold, compares the water meter monitoring coefficients corresponding to the n smart water meters at the future time T with the preset gradient threshold, so as to obtain L abnormal smart water meters, L∈n; A data analysis module is used to obtain abnormal characteristic data of the Lth abnormal smart water meter, determine the fault type data of the abnormal smart water meter according to the abnormal characteristic data, and determine the fault analysis data corresponding to the fault type data based on a preset relationship between the fault type data and the fault analysis data, wherein the fault analysis data includes E abnormal causes and a standard abnormal vibration FFT diagram associated with the E abnormal causes; the fault type data includes a fault type and a fault component position; E is an integer greater than zero; the abnormal characteristic data includes an abnormal water pressure spectrum diagram and an abnormal current spectrum diagram; The data judgment module is used to obtain the measured abnormal vibration FFT diagram of the Lth abnormal smart water meter within a preset time interval according to the position of the faulty component, compare the measured abnormal vibration FFT diagram with the standard abnormal vibration FFT diagram, and determine the abnormal cause of the abnormal smart water meter based on the comparison result.

10. 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 a water meter remote reading method according to any one of claims 1 to 8 by calling a computer program stored in the memory.

Images