A method for detecting water seepage in water meter

Abstract

This invention discloses a water meter seepage detection method. By combining humidity, temperature, and ultrasonic sensor data, and utilizing a machine learning model and triangulation algorithms, it achieves efficient detection and precise location of water meter seepage. This method boasts high detection efficiency, high accuracy, and a high degree of intelligence. It is suitable for real-time monitoring and maintenance of water supply systems, addressing the low efficiency, insufficient accuracy, and inability to accurately locate water meter seepage in existing water meter seepage detection methods.

Description

Technical Field

[0001] The present invention relates to the technical field of water meter detection, and in particular to a water meter water seepage detection method. Background Art

[0002] Water meters are essential devices used to measure water consumption in water supply systems. Their proper operation is crucial to the management and maintenance of water supply systems. However, over time, water meters may leak due to aging, corrosion, or external impact. Existing methods for detecting water meter leakage primarily rely on manual inspections or single sensor detection, which presents the following issues:

[0003] Low detection efficiency: Manual inspections consume a lot of time and manpower and cannot achieve real-time monitoring.

[0004] Insufficient detection accuracy: Single sensors (such as humidity sensors) are easily affected by environmental interference and have a high false alarm rate.

[0005] Unable to accurately locate: Existing technologies make it difficult to accurately determine the location of water seepage, resulting in low maintenance efficiency.

[0006] Therefore, there is an urgent need for a water meter seepage detection method that is efficient, accurate and capable of real-time monitoring. Summary of the Invention

[0007] The purpose of this section is to summarize some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the abstract and title of this application to avoid obscuring the purpose of this section, the abstract and the title of the invention, and such simplifications or omissions should not be used to limit the scope of the present invention.

[0008] In view of the problems existing in the above-mentioned existing water meter seepage detection method, the present invention is proposed.

[0009] Therefore, the technical problem solved by the present invention is to solve the problems of low detection efficiency, insufficient detection accuracy and inability to accurately locate water meter seepage detection methods in the prior art.

[0010] In order to solve the above technical problems, the present invention provides the following technical solutions: a water meter water seepage detection method, comprising the following steps: S1: sensor data acquisition, which collects corresponding sensor data in real time through multiple sensors installed at the water meter interface or inside the meter case; S2: preprocessing and feature extraction of the data; S3: building a water seepage detection model and calculating the water seepage probability; S4: using a triangulation positioning algorithm to determine the water seepage location; S5: triggering an alarm and sending the detection results to a management platform; wherein the multiple sensors include: humidity sensor: used to detect humidity changes in the environment around the water meter; temperature sensor: used to monitor the humidity of the water meter; Measure the water meter temperature to eliminate humidity false alarms caused by temperature changes; vibration sensor: used to detect whether the water meter has abnormal vibrations caused by water seepage; ultrasonic sensor: used to detect whether there is liquid leakage inside the water meter; Among them, data preprocessing specifically includes the following steps: Q1: filter and denoise the collected sensor data to eliminate environmental interference; Q2: use the Kalman filter algorithm to fuse multi-sensor data to improve data accuracy and reliability; Among them, data feature extraction specifically includes: extracting the following features from the preprocessed data: humidity change rate: ΔH= (H t −H t−1 ) / Δt, where H t is the current humidity value, H t−1 is the humidity value at the last moment, Δt is the time interval; temperature change rate: ΔT= (T t −T t−1 ) / Δt, where T t is the current temperature value, T t−1 is the temperature value at the previous moment; vibration frequency: the spectrum characteristics of the vibration signal are extracted through Fourier transform; ultrasonic signal strength: the signal strength of the liquid leakage detected by the ultrasonic sensor; wherein, the constructed water seepage detection model is specifically:

[0011] ;

[0012] Among them, P is the probability of water seepage, F v is the vibration frequency, S u is the ultrasonic signal intensity, f is the machine learning model;

[0013] in,

[0014] ;

[0015] Among them, 1.13, 1.132, 1.26, 0.8 and -1 / 2 are adjustment constants, and dz is the integral operation.

[0016] As a preferred solution of the water meter seepage detection method described in the present invention, when the water seepage probability P is higher than a certain threshold, it is defined as a water seepage abnormality, an alarm is issued, and the detection results and positioning information are sent to the management platform through the wireless communication module.

[0017] As a preferred solution of the water meter seepage detection method described in the present invention, the threshold value is defined as 6.77 or 6.774.

[0018] As a preferred embodiment of the water meter seepage detection method of the present invention, a triangulation positioning algorithm is used to determine the seepage location, specifically according to the following formula:

[0019] ;

[0020] Among them, (x, y) is the coordinate of the seepage location, (x i ,y i ) is the position of the i-th sensor, d i is the water seepage distance detected by the sensor, σ i is the sensor measurement error.

[0021] The present invention provides a water meter seepage detection method that combines humidity, temperature, and ultrasonic sensor data with a machine learning model and triangulation algorithms to efficiently detect and accurately locate water meter seepage. This method boasts high detection efficiency, high accuracy, and a high degree of intelligence, making it suitable for real-time monitoring and maintenance of water supply systems. It addresses the low efficiency, insufficient accuracy, and inability to accurately locate water meter seepage in existing water meter seepage detection methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort. Among them:

[0023] Figure 1 This is a flow chart of the overall method of the water meter seepage detection method provided by the present invention.

[0024] Figure 2 Flowchart of the method for preprocessing data. DETAILED DESCRIPTION

[0025] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0026] Existing water meter seepage detection methods mainly rely on manual inspections or single sensor detection, which has the following problems:

[0027] Low detection efficiency: Manual inspections consume a lot of time and manpower and cannot achieve real-time monitoring.

[0028] Insufficient detection accuracy: Single sensors (such as humidity sensors) are easily affected by environmental interference and have a high false alarm rate.

[0029] Unable to accurately locate: Existing technologies make it difficult to accurately determine the location of water seepage, resulting in low maintenance efficiency.

[0030] Therefore, please refer to Figure 1 The present invention provides a water meter seepage detection method, comprising the following steps:

[0031] S1: Sensor data acquisition, which collects corresponding sensor data in real time through various sensors installed at the water meter interface or inside the meter case;

[0032] S2: preprocessing and feature extraction of data;

[0033] S3: Build a water seepage detection model and calculate the water seepage probability;

[0034] S4: Use triangulation algorithm to determine the location of water seepage;

[0035] S5: Trigger an alarm and send the detection results to the management platform.

[0036] Specifically, the various sensors include:

[0037] Humidity sensor: used to detect humidity changes in the environment around the water meter;

[0038] Temperature sensor: used to monitor water meter temperature and eliminate false humidity alarms caused by temperature changes;

[0039] Vibration sensor: used to detect whether the water meter has abnormal vibration caused by water seepage;

[0040] Ultrasonic sensor: used to detect whether there is liquid leakage inside the water meter.

[0041] It should be noted that the above sensors are direct applications of existing conventional sensors and will not be described in detail here.

[0042] See Figure 2 , the data preprocessing specifically includes the following steps:

[0043] Q1: Filter and denoise the collected sensor data to eliminate environmental interference;

[0044] Q2: Use the Kalman filter algorithm to fuse multi-sensor data to improve data accuracy and reliability.

[0045] It should be noted that the above pretreatment steps are all existing conventional pretreatment steps.

[0046] Furthermore, feature extraction of data specifically includes:

[0047] The following features are extracted from the preprocessed data:

[0048] Humidity change rate: ΔH=(H t −H t−1 ) / Δt, where H t is the current humidity value, H t−1 is the humidity value at the previous moment, Δt is the time interval;

[0049] Temperature change rate: ΔT=(T t −T t−1 ) / Δt, where T t is the current temperature value, T t−1 is the temperature value at the previous moment;

[0050] Vibration frequency: Extract the spectral characteristics of the vibration signal through Fourier transform;

[0051] Ultrasonic signal strength: The signal strength of the ultrasonic sensor used to detect liquid leakage.

[0052] Furthermore, the constructed water seepage detection model is as follows:

[0053] ;

[0054] Among them, P is the probability of water seepage, F v is the vibration frequency, S u is the ultrasonic signal intensity, f is the machine learning model;

[0055] in,

[0056] ;

[0057] Among them, 1.13, 1.132, 1.26, 0.8 and -1 / 2 are adjustment constants, and dz is the integral operation.

[0058] Specifically, when the water seepage probability P is higher than a certain threshold, it is defined as a water seepage anomaly, an alarm is issued, and the detection results and positioning information are sent to the management platform through the wireless communication module.

[0059] Specifically, the threshold is defined as 6.77 or 6.774.

[0060] Additionally, a triangulation algorithm is used to determine the location of the water seepage, according to the following formula:

[0061] ;

[0062] Among them, (x, y) is the coordinate of the seepage location, (x i ,y i ) is the position of the i-th sensor, d i is the water seepage distance detected by the sensor, σ i is the sensor measurement error.

[0063] In order to verify the technical effect of the present invention, the following simulation experiment is carried out:

[0064] Purpose of the experiment

[0065] Verify the advantages of the water meter seepage detection method proposed in the present invention in terms of detection efficiency, detection accuracy and positioning accuracy.

[0066] Experimental design

[0067] Prepare the experimental environment, install the water meter and connect various sensors (humidity, temperature, vibration, and ultrasonic).

[0068] Set water seepage points to simulate water seepage events under different circumstances.

[0069] Water seepage detection is performed simultaneously by the method of the present invention and the existing method.

[0070] Record the detection results, including water seepage detection time, water seepage probability, water seepage location coordinates, etc.

[0071] Compare and analyze the test results.

[0072] Experimental procedures

[0073] Step 1: Sensor Data Collection

[0074] Install the sensor and calibrate it.

[0075] Start collecting data and record the start time.

[0076] Step 2: Data Preprocessing

[0077] Apply filtering and denoising.

[0078] The Kalman filter algorithm is used for data fusion.

[0079] Step 3: Feature Extraction

[0080] Calculate the humidity change rate ΔH and temperature change rate ΔT.

[0081] Extract the vibration frequency Fv and ultrasonic signal intensity Su.

[0082] Step 4: Water seepage detection model construction

[0083] Use a machine learning model and input feature data.

[0084] Output the water seepage probability P and the water seepage location coordinates.

[0085] Step 5: Record and analyze results

[0086] Record various parameters of water seepage detection.

[0087] The detection efficiency, precision and positioning accuracy of the method of the present invention are compared with those of existing methods.

[0088] Experimental data table

[0089] Seepage point number Start time End Time Water seepage probability P Actual position (X, Y) Detection position (X', Y') Detection error method 1 10:00 10:05 0.92 (5, 10) (5.1, 10.2) 0.1 The present invention 2 10:10 10:15 0.85 (6, 12) (5.9, 11.8) 0.2 The present invention 3 10:20 10:25 0.78 (7, 14) (6.8, 14.2) 0.4 Existing methods 4 10:30 10:35 0.90 (8, 16) (7.5, 15.8) 0.5 Existing methods ... ... ... ... ... ... ... ...

[0090] The data in the table allows for a visual comparison of the differences between the present invention and existing methods in terms of water seepage detection time, detection probability, and positioning accuracy. For example, the present invention method can provide a higher water seepage probability in a shorter time, and the detected location is closer to the actual location, indicating higher detection accuracy and positioning accuracy.

[0091] This invention provides a water meter seepage detection method that combines humidity, temperature, and ultrasonic sensor data with a machine learning model and triangulation algorithms to achieve efficient detection and precise location of water meter seepage. This method boasts high detection efficiency, high accuracy, and a high level of intelligence. It is suitable for real-time monitoring and maintenance of water supply systems, addressing the low efficiency, insufficient accuracy, and inability to accurately locate water meter seepage in existing water meter seepage detection methods.

[0092] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A water meter seepage detection method, characterized in that: The steps include: S1: Sensor data acquisition, which collects corresponding sensor data in real time through various sensors installed at the water meter interface or inside the meter case; S2: preprocessing and feature extraction of data; S3: Build a water seepage detection model and calculate the water seepage probability; S4: Use triangulation algorithm to determine the location of water seepage; S5: trigger an alarm and send the detection results to the management platform; Among them, various sensors include: Humidity sensor: used to detect humidity changes in the environment around the water meter; Temperature sensor: used to monitor water meter temperature and eliminate false humidity alarms caused by temperature changes; Vibration sensor: used to detect whether the water meter has abnormal vibration caused by water seepage; Ultrasonic sensor: used to detect whether there is liquid leakage inside the water meter; The data preprocessing specifically includes the following steps: Q1: Filter and denoise the collected sensor data to eliminate environmental interference; Q2: Use the Kalman filter algorithm to fuse multi-sensor data to improve data accuracy and reliability; The feature extraction of data specifically includes: The following features are extracted from the preprocessed data: Humidity change rate: ΔH=(H t −H t−1 ) / Δt, where H t is the current humidity value, H t−1 is the humidity value at the previous moment, Δt is the time interval; Temperature change rate: ΔT=(T t −T t−1 ) / Δt, where T t is the current temperature value, T t−1 is the temperature value at the previous moment; Vibration frequency: Extract the spectral characteristics of the vibration signal through Fourier transform; Ultrasonic signal strength: The signal strength of the ultrasonic sensor to detect liquid leakage; The water seepage detection model constructed is specifically as follows: ； Among them, P is the probability of water seepage, F v is the vibration frequency, S u is the ultrasonic signal intensity, f is the machine learning model; in, ； Among them, 1.13, 1.132, 1.26, 0.8 and -1 / 2 are adjustment constants, and dz is the integral operation.

2. The water meter seepage detection method according to claim 1, characterized in that: When the water seepage probability P is higher than a certain threshold, it is defined as a water seepage anomaly and an alarm is issued. The detection results and positioning information are sent to the management platform through the wireless communication module.

3. The water meter seepage detection method according to claim 2, characterized in that: The threshold is defined as 6.77 or 6.

774.

4. The water meter seepage detection method according to claim 3, characterized in that: The water seepage location is determined using a triangulation algorithm, based on the following formula: ； Among them, (x, y) is the coordinate of the seepage location, (x i ,y i ) is the position of the i-th sensor, d i is the water seepage distance detected by the sensor, σ i is the sensor measurement error.

Images