CN115905869A - Ultrasonic water meter fault early warning method - Google Patents
Ultrasonic water meter fault early warning method Download PDFInfo
- Publication number
- CN115905869A CN115905869A CN202211503257.XA CN202211503257A CN115905869A CN 115905869 A CN115905869 A CN 115905869A CN 202211503257 A CN202211503257 A CN 202211503257A CN 115905869 A CN115905869 A CN 115905869A
- Authority
- CN
- China
- Prior art keywords
- data
- water meter
- ultrasonic water
- fault
- training set
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 70
- 238000000034 method Methods 0.000 title claims abstract description 23
- 238000012549 training Methods 0.000 claims abstract description 31
- 238000013145 classification model Methods 0.000 claims abstract description 20
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 238000011144 upstream manufacturing Methods 0.000 claims description 9
- 238000004140 cleaning Methods 0.000 claims description 7
- 238000010606 normalization Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 7
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 claims description 4
- 238000005457 optimization Methods 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 238000005406 washing Methods 0.000 claims description 2
- 238000003745 diagnosis Methods 0.000 description 3
- 101100409194 Rattus norvegicus Ppargc1b gene Proteins 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A20/00—Water conservation; Efficient water supply; Efficient water use
Landscapes
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention relates to the technical field of water meter fault early warning, and discloses an ultrasonic water meter fault early warning method, which comprises the following steps: acquiring normal operation data and fault data of the ultrasonic water meter to form a prediction training set of an LSTM prediction model, wherein the normal operation data is used for forming a classification training set of an OCSVM classification model; preprocessing and normalizing the ultrasonic water meter data, and then forming a training set by taking the data every 6 hours as a group; constructing a prediction model according to the prediction training set, and constructing a classification model according to the classification training set; and predicting the ultrasonic water meter data of the next 6 hours through the prediction model, sending the predicted data into the classification model for fault recognition, and reporting early warning information by the ultrasonic water meter if the fault is recognized. According to the method, after the data of the ultrasonic water meter within 6 hours is predicted through the LSTM model, the fault of the ultrasonic water meter is identified through the OCSVM model, so that the fault early warning of the ultrasonic water meter within 6 hours in advance is realized, and the economic loss is reduced.
Description
Technical Field
The invention relates to the technical field of water meter fault early warning, in particular to an ultrasonic water meter fault early warning method.
Background
The time of the internet of things comes, and the traditional mechanical water meter is gradually replaced by an intelligent water meter. The ultrasonic water meter is a product which is concerned by intelligent water meters, and the ultrasonic water meter is a novel water meter which analyzes and calculates the flow velocity of outlet water by detecting the time difference generated by the change of the velocity when ultrasonic sound beams are transmitted in downstream and upstream in water, so as to further calculate the flow of the outlet water. Because the working environment of the water meter is very harsh, in practical application, the measuring precision of the water meter is reduced due to the damage of electronic components, the aging of a transducer of the water meter, the damage of a flow field structure and other faults, and economic loss is brought to residents or water supply companies.
The existing diagnosis modes for the faults of the ultrasonic water meter are all real-time or lagged, when the faults are diagnosed, the faults destroy the safe operation of the water meter, and loss is caused to users or water supply companies. Meanwhile, the ultrasonic water meter has more fault types, such as abnormal work of a test circuit caused by under-voltage of a battery; the transducer is aged to cause the reduction of the metering performance of the water meter; or the flow field structure is damaged, so that the water meter is influenced by turbulent flow. For the faults, the conventional fault detection algorithm is very easy to have the phenomena of fault missing report or false report.
Disclosure of Invention
The invention provides an ultrasonic water meter fault early warning method aiming at the defects in the prior art, and the method is characterized in that after data of an ultrasonic water meter within 6 hours is predicted through an LSTM prediction model, faults of the ultrasonic water meter are identified through an OCSVM classification model, so that the fault early warning of the ultrasonic water meter within 6 hours in advance is realized, and the economic loss is reduced.
The purpose of the invention can be realized by the following technical scheme:
an ultrasonic water meter fault early warning method comprises the following steps:
s1, acquiring normal operation data and fault data of the ultrasonic water meter in a period of time T to form a prediction training set of an LSTM prediction model;
acquiring normal operation data of the ultrasonic water meter in a period of time T to form a classification training set of an OCSVM classification model;
the data comprises upstream and downstream signal propagation time difference, water temperature, upstream and downstream received signal peak-to-peak values, instantaneous flow and battery voltage;
s2, preprocessing the acquired data;
carrying out normalization processing on the preprocessed data;
taking the data after the normalization processing as a group to form a prediction training set and a classification training set every 6 hours;
s3, constructing an LSTM prediction model according to the prediction training set, and optimizing parameters of the model by using an Adam optimization algorithm;
s4, extracting the characteristics of the classification training set;
constructing an OCSVM classification model;
training and optimizing an OCSVM classification model by using the extracted characteristic values;
s5, predicting the ultrasonic water meter data of the next 6 hours through an LSTM prediction model;
and s6, sending the prediction data of the next 6 hours into an OCSVM classification model for fault recognition, and if the fault is recognized, reporting early warning information by the ultrasonic water meter.
Further, the data preprocessing procedure in step s2 is:
s21, screening the data by using a ratio threshold method, namely setting a threshold range of a ratio R of the propagation time difference of the upstream and downstream signals to the instantaneous flow, and discarding the data outside the threshold range of R;
s22, cleaning the data by the moving average method, the formula is as follows:
wherein x (n) is data before cleaning; y (m) is data after cleaning; and n is the ultrasonic water meter data index, and the step length is 5.
Further, in step s4, an OCSVM classification model is constructed by using a gaussian radial basis kernel function.
The invention has the beneficial technical effects that: and after the data of the ultrasonic water meter within 6 hours are predicted through the LSTM prediction model, the fault of the ultrasonic water meter is identified through an OCSVM classification model. Different from the real-time performance and the hysteresis performance of the conventional fault diagnosis, the fault diagnosis method can report the fault of the water meter in advance for 6 hours, and effectively avoids the loss and the damage caused by the fault of the water meter. Meanwhile, the ultrasonic water meter has many fault types, classification is impossible by extracting each fault feature, the classification is used as a single-classification support vector machine, an OCSVM classification model judges whether a data sample is normal data of the ultrasonic water meter, and then the data sample is reported, so that the fault recognition rate is high.
Drawings
FIG. 1 is a diagram of the method of the present invention.
Fig. 2 is a block diagram of an LSTM prediction model according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the invention.
As shown in 1~2, an ultrasonic water meter fault early warning method comprises the following steps:
s1: acquiring normal operation data and fault data of an ultrasonic water meter in a cell for three years to form a prediction training set of an LSTM prediction model, and acquiring data of the ultrasonic water meter in the cell for three years to form a classification training set of an OCSVM classification model, wherein the ultrasonic water meter data comprises upstream and downstream signal propagation time difference, water temperature, upstream and downstream received signal peak values, instantaneous flow and battery voltage;
s2: preprocessing the acquired data;
carrying out normalization processing on the preprocessed data;
taking the data after the normalization processing as a group to form a prediction training set and a classification training set every 6 hours; specifically, the method comprises the following steps:
s21, screening the data by using a ratio threshold method, wherein the calculation formula of the ratio R is as follows:
screening abnormal data by setting a threshold range Rmin to R, wherein Rmin is not more than R and not more than Rmax, rmin is the ratio when the flow is Q4, rmax is the ratio when the flow is Q1, and discarding data outside the threshold range of R;
and s22, cleaning the data of the ultrasonic water meter by a sliding average method, wherein the calculation formula is as follows:
wherein x (n) is data before cleaning; y (m) is data after washing; and n is the ultrasonic water meter data index, and the step length is 5.
s23, carrying out normalization processing on the preprocessed data, and carrying out linear transformation on the original data, wherein the formula is as follows:
wherein y is the preprocessed data,
is at a minimum value>
Is the maximum value.
s24: taking the ultrasonic water meter data as a group of data to form a training set every 6 hours; each set of data contained 4320 data points.
And s3, constructing an LSTM prediction model according to the prediction training set, and performing parameter optimization on the model by using an Adam optimization algorithm:
and s31, selecting the initialization network parameters to build an LSTM prediction model, and after determining the nodes of an input layer, a hidden layer and an output layer of the model, sending the normalized data into the model for training. The LSTM prediction model controls the transmission state through a sigmoid activation function, and the network model can be selectively forgotten about data with extremely low water consumption. This greatly compresses the network training time.
And s32, optimizing the network parameters by adopting an Adam algorithm in combination with the prediction training set.
And s33, in order to more intuitively measure the error between the predicted result and the actual result of the model, the commonly used average absolute error (mae) is used as a measurement standard. The average absolute value error formula is shown below and is used to represent the average of the absolute errors between the predicted value and the actual value:
wherein y is actual ultrasonic water meter data;
outputting a predicted value for the model; and m is the number of samples.
s4: performing feature extraction on the classified training set, building an OCSVM classification model, and performing fault classification and identification on the training set;
s41, assuming that the ultrasonic water meter data in a certain normal state is
In the example, t is 500. Preprocessing the normal data, and extracting the following 3 characteristic values S, perc and K to construct a characteristic set:
1) Standard deviation S:
wherein,
is data averagingThe value is obtained.
2) Percent Perc of the mean fluctuation amplitude:
wherein max (L) is a maximum value; min (L) is the minimum.
3) Data change slope K of t sets of data:
s42, selecting a Gaussian radial basis kernel function to establish an OCSVM classification model, wherein the error penalty coefficient is set to be 0.1; and training and optimizing the model by using the extracted characteristic values, and storing the optimal model.
s43, in order to better evaluate the classification effect of the model, the embodiment adopts two classification indexes of the precision rate P and the recall rate R. It is defined as:
where TP represents the number of samples for which positive class data is identified as positive class, FP represents the number of samples for which positive class data is identified as negative class, and FN represents the number of samples for which negative class data is identified as positive class.
And s5, sending the data in the previous six hours of the current time into an LSTM prediction model to predict the data of the ultrasonic water meter in the next six hours, and then carrying out reverse normalization processing.
And s6, performing feature extraction on the predicted data, sending the data into an OCSVM classification model for fault identification, and reporting the data if the data is identified as a fault.
The above-mentioned embodiments are illustrative of the specific embodiments of the present invention, and are not restrictive, and those skilled in the relevant art can make various changes and modifications to obtain corresponding equivalent technical solutions without departing from the spirit and scope of the present invention, so that all equivalent technical solutions should be included in the scope of the present invention.
Claims (3)
1. An ultrasonic water meter fault early warning method is characterized by comprising the following steps:
s1, acquiring normal operation data and fault data of the ultrasonic water meter in a period of time T to form a prediction training set of an LSTM prediction model;
acquiring normal operation data of the ultrasonic water meter in a period of time T to form a classification training set of an OCSVM classification model;
the data comprises upstream and downstream signal propagation time difference, water temperature, upstream and downstream received signal peak-to-peak values, instantaneous flow and battery voltage;
s2, preprocessing the acquired data;
normalizing the preprocessed data;
taking the data after the normalization processing as a group to form a prediction training set and a classification training set every 6 hours;
s3, constructing an LSTM prediction model according to the prediction training set, and optimizing parameters of the model by using an Adam optimization algorithm;
s4, extracting the characteristics of the classification training set;
constructing an OCSVM classification model;
training and optimizing an OCSVM classification model by using the extracted characteristic values;
s5, predicting the ultrasonic water meter data of the next 6 hours through an LSTM prediction model;
and s6, sending the prediction data of the next 6 hours into an OCSVM classification model for fault recognition, and if the fault is recognized, reporting early warning information by the ultrasonic water meter.
2. The ultrasonic water meter fault early warning method according to claim 1, wherein the data preprocessing procedure in the step s2 is as follows:
s21, screening the data by using a ratio threshold method, namely setting a threshold range of a ratio R of the propagation time difference of the upstream and downstream signals to the instantaneous flow, and discarding the data outside the threshold range of R;
s22, cleaning the data by the moving average method, the formula is as follows:
wherein x (n) is data before cleaning; y (m) is data after washing; and n is the ultrasonic water meter data index, and the step length is 5.
3. The method for warning the fault on the ultrasonic water meter according to claim 1, wherein an OCSVM classification model is constructed by using a gaussian radial basis kernel function in the step s 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211503257.XA CN115905869A (en) | 2022-11-29 | 2022-11-29 | Ultrasonic water meter fault early warning method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211503257.XA CN115905869A (en) | 2022-11-29 | 2022-11-29 | Ultrasonic water meter fault early warning method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115905869A true CN115905869A (en) | 2023-04-04 |
Family
ID=86477623
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211503257.XA Pending CN115905869A (en) | 2022-11-29 | 2022-11-29 | Ultrasonic water meter fault early warning method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115905869A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117574244A (en) * | 2024-01-15 | 2024-02-20 | 成都秦川物联网科技股份有限公司 | Ultrasonic water meter fault prediction method, device and equipment based on Internet of things |
-
2022
- 2022-11-29 CN CN202211503257.XA patent/CN115905869A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117574244A (en) * | 2024-01-15 | 2024-02-20 | 成都秦川物联网科技股份有限公司 | Ultrasonic water meter fault prediction method, device and equipment based on Internet of things |
| CN117574244B (en) * | 2024-01-15 | 2024-04-02 | 成都秦川物联网科技股份有限公司 | Ultrasonic water meter fault prediction method, device and equipment based on Internet of things |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113518011B (en) | Abnormality detection method and apparatus, electronic device, and computer-readable storage medium | |
| US20210364481A1 (en) | Method for evaluating mechanical state of high-voltage shunt reactor based on vibration characteristics | |
| CN117406026A (en) | Power distribution network fault detection method suitable for distributed power supply | |
| CN118100446B (en) | Intelligent detection method for node running state of power system | |
| CN115905869A (en) | Ultrasonic water meter fault early warning method | |
| CN117560300B (en) | Intelligent internet of things flow prediction and optimization system | |
| CN118300273B (en) | Cable room fault early warning system based on multi-field coupling | |
| CN118503636A (en) | Power distribution equipment health state assessment method and system | |
| CN115222141A (en) | Multivariable time sequence abnormity detection method, system, medium, equipment and terminal | |
| CN115839763A (en) | Transformer vibration noise monitoring system | |
| Fang et al. | An event detection approach based on improved CUSUM algorithm and kalman filter | |
| CN114997313A (en) | Anomaly detection method for ocean online monitoring data | |
| CN117978628B (en) | Communication control method and system based on intelligent park | |
| CN116910677A (en) | Industrial instrument fault diagnosis method and system | |
| CN117553840A (en) | Instrument based on intelligent management and system thereof | |
| CN110852906A (en) | Method and system for identifying electricity stealing suspicion based on high-dimensional random matrix | |
| CN116384843B (en) | Energy efficiency evaluation model training method and monitoring method for digital energy nitrogen station | |
| CN116128690B (en) | Carbon emission cost value calculation method, device, equipment and medium | |
| CN109872511B (en) | Self-adaptive two-stage alarm method for monitoring axial displacement sudden change | |
| CN114996815A (en) | Decision tree algorithm-based metal roof state judgment method and system | |
| CN118295881B (en) | Packaged data supervision system and method for chip grid array | |
| CN116342110B (en) | Intelligent fault diagnosis and fault tolerance measurement method for multiple temperature measurement loops of train | |
| CN118245917B (en) | Fault detection method and system for servo inverter | |
| CN118501720B (en) | Lithium battery abnormality detection system based on big data analysis | |
| CN116010807A (en) | Multi-variable fusion diagnosis method for differential pressure type flowmeter |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |