CN113723210A - Method and system for detecting leakage edge equipment of water supply pipe in intelligent park - Google Patents
Method and system for detecting leakage edge equipment of water supply pipe in intelligent park Download PDFInfo
- Publication number
- CN113723210A CN113723210A CN202110898121.2A CN202110898121A CN113723210A CN 113723210 A CN113723210 A CN 113723210A CN 202110898121 A CN202110898121 A CN 202110898121A CN 113723210 A CN113723210 A CN 113723210A
- Authority
- CN
- China
- Prior art keywords
- water supply
- supply pipe
- neural network
- network model
- convolution neural
- 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 60
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000003062 neural network model Methods 0.000 claims abstract description 37
- 238000001514 detection method Methods 0.000 claims abstract description 35
- 238000013138 pruning Methods 0.000 claims abstract description 23
- 238000012549 training Methods 0.000 claims abstract description 21
- 238000012360 testing method Methods 0.000 claims abstract description 14
- 240000007651 Rubus glaucus Species 0.000 claims abstract description 8
- 235000011034 Rubus glaucus Nutrition 0.000 claims abstract description 8
- 235000009122 Rubus idaeus Nutrition 0.000 claims abstract description 8
- 238000002372 labelling Methods 0.000 claims abstract description 7
- 238000012545 processing Methods 0.000 claims description 20
- 239000011159 matrix material Substances 0.000 claims description 18
- 238000000354 decomposition reaction Methods 0.000 claims description 17
- 238000010606 normalization Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 4
- 238000005457 optimization Methods 0.000 claims description 4
- 230000009467 reduction Effects 0.000 claims description 4
- 230000009466 transformation Effects 0.000 claims description 4
- 230000001131 transforming effect Effects 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
- G06F2218/04—Denoising
- G06F2218/06—Denoising by applying a scale-space analysis, e.g. using wavelet analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Abstract
The invention provides a method and a system for detecting leakage edge equipment of a water supply pipe in an intelligent park, which are used for collecting the temperature and noise around the water supply pipe and the pressure and flow inside the water supply pipe to form a water supply pipe detection database; denoising; normalizing the denoised data, then manually labeling labels, and dividing the normalized data into a training set and a test set; training the time convolution neural network model by utilizing a training set and a test set; optimizing the time convolution neural network model based on a pruning algorithm; and deploying the optimized time convolution neural network model on a raspberry party to identify whether the water supply pipe leaks or not. The trained model is compressed and optimized through the pruning algorithm, so that the model is light, and can be deployed on edge equipment after being compressed, so that the leakage detection of the water pipe can be more timely.
Description
Technical Field
The invention belongs to the field of pipeline tightness detection, and particularly relates to a method and a system for detecting leakage edge equipment of a water supply pipe in an intelligent park.
Background
With the rapid development of the urbanization process, the aging of the water supply pipe and the increasing shortage of water resources, the timely detection and maintenance of the leakage of the water supply pipe are important measures for avoiding the waste of the water resources. The traditional water pipe leakage detection method utilizes single information, and is difficult to effectively detect the water pipe leakage in real time. At present, the deep learning method can effectively realize the comprehensive processing of multi-source information, thereby realizing the effective detection of the leakage condition. However, the deep learning model has higher requirements on the computing power of the deployed device due to the large parameter number. Although data processing can be implemented in a cloud-based manner, this may increase the construction cost.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the method and the system for detecting the leakage edge equipment of the water supply pipe in the intelligent park are applied to enable the model to be light.
The technical scheme adopted by the invention for solving the technical problems is as follows: a method for detecting equipment of leakage edge of a water supply pipe in an intelligent park comprises the following steps:
s1, constructing a water supply pipe detection database:
respectively detecting the temperature and noise around the water supply pipe and the pressure and flow inside the water supply pipe through a temperature sensor, a microphone array, a flow sensor and a pressure sensor, and acquiring data to form a water supply pipe detection database;
s2, carrying out denoising processing on the data in the water supply pipe detection database;
s3, carrying out normalization processing on the data after denoising processing, then carrying out manual labeling, and dividing the normalized data into a training set and a test set;
s4, constructing a time convolution neural network model, and training the time convolution neural network model by using the training set and the test set;
s5, optimizing the time convolution neural network model based on a pruning algorithm;
and S6, deploying the optimized time convolution neural network model on the controller to realize the identification of whether the water supply pipe leaks.
According to the method, the S2 adopts wavelet denoising method to perform denoising.
According to the above method, the S2 specifically includes:
transforming the acquired data, and setting the number of layers of wavelet decomposition to obtain a wavelet decomposition coefficient;
estimating the noise variance in each direction of each decomposition layer;
calculating each parameter, and obtaining a wavelet coefficient variance according to Gaussian distribution;
calculating a threshold coefficient according to the number of layers of wavelet decomposition and the length of a wavelet coefficient corresponding to each layer;
calculating a new threshold value by using the noise variance, the wavelet coefficient variance and the threshold value coefficient;
and carrying out wavelet soft threshold processing on the high-frequency coefficients of each layer to obtain a new wavelet coefficient, and carrying out wavelet inverse transformation on the processed wavelet coefficient to obtain de-noised data.
According to the above method, the S5 specifically includes:
(1) calculating the weight W of the ith layer aiming at the time convolution neural network model of S4, and solving a gradient matrix G of the weight W;
(2) finding the maximum of the absolute values of the gradients in the gradient matrix G is recorded as: gmax(ii) a Setting the total number n of thresholds, solving the step length and the candidate threshold Tm，TmRepresents the mth threshold;
step＝|g|max/n；
Tm＝step×m；m＝1,2,…,n；
(3) according to the candidate threshold value TmStatistical gradient values smaller than T in the gradient matrix GmIs recorded as Nm,m＝1,2,...,n；
(4) Calculating the residual parameter margin RN [ m ] of the time convolution neural network model,
RN[m]＝k×k×d×a-Nm；
wherein k, d and a are dimension parameters of the gradient matrix G;
(5) repeating (2) - (4);
(6) and (3) calculating: Δ RN [ m ] ═ RN [ m +1] -RN [ m ]
Wherein, RN [ m +1]]Indicating the use of a threshold value Tm+1The number of remaining parameters after pruning, Delta RN [ m ]]Representing the difference of the parameter residual quantity after adjacent pruning;
(7) judgement of Delta RN [ m ]]If the value is not greater than 0, the current m value is saved, and the final threshold value T is obtainedm(ii) a Otherwise, repeating (6) until:
ΔRN[m]＞Value
wherein Value is a self-defined parameter;
(8) and setting the weight matrix corresponding to the gradient matrix smaller than the final threshold value T as 0 to finish pruning.
According to the method, the total number n of the threshold values is 200.
According to the method, the controller is a raspberry pie.
The utility model provides a be applied to wisdom garden feed pipe and reveal marginal equipment detecting system, this system includes:
the water supply pipe detection database construction module is used for acquiring the temperature and noise around the water supply pipe and the pressure and flow inside the water supply pipe to form a water supply pipe detection database;
the de-noising module is used for de-noising the data in the water supply pipe detection database;
the data preprocessing module is used for carrying out normalization processing on the data subjected to noise reduction processing, then carrying out manual labeling, and dividing the normalized data into a training set and a test set;
the time convolution neural network model module is used for constructing a time convolution neural network model and training the time convolution neural network model by utilizing the training set and the test set;
the pruning optimization module is used for optimizing the time convolution neural network model based on a pruning algorithm;
and the leakage detection module is used for deploying the optimized time convolution neural network model on the controller to realize the identification of whether the water supply pipe leaks or not.
According to the system, the controller is a raspberry pie.
The invention has the beneficial effects that: detecting whether a water supply pipe leaks or not by utilizing a time convolution neural network model and fusing multi-sensor information, compressing and optimizing the trained model through a pruning algorithm, reducing the parameter quantity of the model, constructing a corresponding environment on a raspberry group system, and deploying a detection model after pruning optimization; the method can effectively avoid false detection and missed detection for whether the water pipe leaks according to the fused multi-sensor data and the historical data; meanwhile, the model can be deployed on the edge equipment after being compressed, so that the leakage detection of the water pipe can be more timely, and the cost for establishing a large-scale server is saved.
Drawings
FIG. 1 is a flowchart of a method according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of a sensor arrangement.
Fig. 3 is a flow chart of signal wavelet denoising.
FIG. 4 is a diagram of a water supply pipe leakage detection model based on a time convolution network model.
FIG. 5 is a flow chart of a compression model based on a pruning algorithm.
Detailed Description
The invention is further illustrated by the following specific examples and figures.
The invention provides a method for detecting leakage edge equipment of a water supply pipe in an intelligent park, which comprises the following steps of:
s1, constructing a water supply pipe detection database: as shown in fig. 2, a temperature sensor, a microphone array, a flow sensor and a pressure sensor are used to detect the temperature and noise around the water supply pipe and the pressure and flow inside the water supply pipe, and data are collected to form a water supply pipe detection database.
And S2, carrying out denoising treatment on the data in the water supply pipe detection database.
In this embodiment, denoising is performed by using a wavelet denoising method, as shown in fig. 3, which specifically includes:
transforming the acquired data, and setting the number of layers of wavelet decomposition to obtain a wavelet decomposition coefficient;
estimating the noise variance in each direction of each decomposition layer;
calculating each parameter, and obtaining a wavelet coefficient variance according to Gaussian distribution;
calculating a threshold coefficient according to the number of layers of wavelet decomposition and the length of a wavelet coefficient corresponding to each layer;
calculating a new threshold value by using the noise variance, the wavelet coefficient variance and the threshold value coefficient;
and carrying out wavelet soft threshold processing on the high-frequency coefficients of each layer to obtain a new wavelet coefficient, and carrying out wavelet inverse transformation on the processed wavelet coefficient to obtain de-noised data.
In this embodiment, the specific process of signal noise reduction is as follows:
(1) transforming the acquired signal f (i, j) to obtain a wavelet decomposition coefficient Wg (i, j) (s, j), wherein i is a serial number, j is 1,2,3, … s, and s represents the total layer number of wavelet decomposition;
(2) and estimating the noise variance in each direction of each decomposition layer:
wherein the content of the first and second substances,
is the variance of the noise;
(3) calculating parameters to obtain a noise threshold according to a Gaussian distribution:
by
Obtaining:
wherein the content of the first and second substances,
is the wavelet coefficient variance;
(4) calculating a threshold coefficient:
wherein beta is a threshold coefficient, LkIs the length of the wavelet coefficient of the kth layer of wavelet decomposition coefficients, j is the total number of layers of wavelet decomposition;
(5) and (4) solving a new threshold value:
wherein, T(s,j)Is a new threshold;
(6) carrying out wavelet soft threshold processing on the high-frequency coefficients of each layer to obtain new wavelet coefficients:
where WST (-) represents a soft thresholding function. For the processed wavelet coefficient
And performing wavelet inverse transformation to obtain a denoised signal.
S3, carrying out normalization processing on the data after denoising processing, then carrying out manual labeling, and dividing the normalized data into a training set and a test set.
S4, constructing a time convolution neural network model, as shown in fig. 4, and training the time convolution neural network model by using the training set and the test set.
And S5, optimizing the time convolution neural network model based on the pruning algorithm.
As shown in fig. 5, S5 specifically includes:
(1) calculating the weight W of the ith layer aiming at the time convolution neural network model of S4, and solving a gradient matrix G of the weight W;
(2) finding the maximum of the absolute values of the gradients in the gradient matrix G is recorded as: gmax(ii) a Setting the total number n of thresholds, taking 200 for this embodiment, and finding step and candidate threshold Tm，TmRepresents the mth threshold;
step＝|g|max/n；
Tm＝step×m；m＝1,2,…,n；
(3) according to the candidate threshold value TmStatistical gradient values smaller than T in the gradient matrix GmIs recorded as Nm,m＝1,2,...,n；
(4) Calculating the residual parameter margin RN [ m ] of the time convolution neural network model,
RN[m]＝k×k×d×a-Nm；
wherein k, d and a are dimension parameters of the gradient matrix G;
(5) repeating (2) - (4);
(6) and (3) calculating: Δ RN [ m ] ═ RN [ m +1] -RN [ m ]
Wherein, RN [ m +1]]Indicating the use of a threshold value Tm+1The number of remaining parameters after pruning, Delta RN [ m ]]Representing the difference of the parameter residual quantity after adjacent pruning;
(7) judgement of Delta RN [ m ]]If the value is not greater than 0, the current m value is saved, and the final threshold value T is obtainedm(ii) a Otherwise, repeating (6) until:
ΔRN[m]＞Value
wherein Value is a self-defined parameter;
(8) and setting the weight matrix corresponding to the gradient matrix smaller than the final threshold value T as 0 to finish pruning.
And S6, deploying the optimized time convolution neural network model on the controller to realize the identification of whether the water supply pipe leaks. The controller of the embodiment adopts a raspberry pi.
The invention also provides a detection system for the leakage edge equipment of the water supply pipe in the intelligent park, which comprises the following components:
the water supply pipe detection database construction module is used for acquiring the temperature and noise around the water supply pipe and the pressure and flow inside the water supply pipe to form a water supply pipe detection database;
the de-noising module is used for de-noising the data in the water supply pipe detection database;
the data preprocessing module is used for carrying out normalization processing on the data subjected to noise reduction processing, then carrying out manual labeling, and dividing the normalized data into a training set and a test set;
the time convolution neural network model module is used for constructing a time convolution neural network model and training the time convolution neural network model by utilizing the training set and the test set;
the pruning optimization module is used for optimizing the time convolution neural network model based on a pruning algorithm;
and the leakage detection module is used for deploying the optimized time convolution neural network model on the raspberry derivative to realize the identification of whether the water supply pipe leaks or not.
The invention also provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the steps of the method being implemented when the processor executes the program.
The invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method.
The above embodiments are only used for illustrating the design idea and features of the present invention, and the purpose of the present invention is to enable those skilled in the art to understand the content of the present invention and implement the present invention accordingly, and the protection scope of the present invention is not limited to the above embodiments. Therefore, all equivalent changes and modifications made in accordance with the principles and concepts disclosed herein are intended to be included within the scope of the present invention.
Claims (10)
1. The utility model provides a be applied to wisdom garden feed pipe and reveal marginal equipment detection method which characterized in that: the method comprises the following steps:
s1, constructing a water supply pipe detection database:
respectively detecting the temperature and noise around the water supply pipe and the pressure and flow inside the water supply pipe through a temperature sensor, a microphone array, a flow sensor and a pressure sensor, and acquiring data to form a water supply pipe detection database;
s2, carrying out denoising processing on the data in the water supply pipe detection database;
s3, carrying out normalization processing on the data after denoising processing, then carrying out manual labeling, and dividing the normalized data into a training set and a test set;
s4, constructing a time convolution neural network model, and training the time convolution neural network model by using the training set and the test set;
s5, optimizing the time convolution neural network model based on a pruning algorithm;
and S6, deploying the optimized time convolution neural network model on the controller to realize the identification of whether the water supply pipe leaks.
2. The method as claimed in claim 1, wherein the method comprises the steps of: and S2, denoising by adopting a wavelet denoising method.
3. The method as claimed in claim 2, wherein the method comprises the steps of: the S2 specifically includes:
transforming the acquired data, and setting the number of layers of wavelet decomposition to obtain a wavelet decomposition coefficient;
estimating the noise variance in each direction of each decomposition layer;
calculating each parameter, and obtaining a wavelet coefficient variance according to Gaussian distribution;
calculating a threshold coefficient according to the number of layers of wavelet decomposition and the length of a wavelet coefficient corresponding to each layer;
calculating a new threshold value by using the noise variance, the wavelet coefficient variance and the threshold value coefficient;
and carrying out wavelet soft threshold processing on the high-frequency coefficients of each layer to obtain a new wavelet coefficient, and carrying out wavelet inverse transformation on the processed wavelet coefficient to obtain de-noised data.
4. The method as claimed in claim 1, wherein the method comprises the steps of: the S5 specifically includes:
(1) calculating the weight W of the ith layer aiming at the time convolution neural network model of S4, and solving a gradient matrix G of the weight W;
(2) finding the maximum of the absolute values of the gradients in the gradient matrix G is recorded as: gmax(ii) a Setting the total number n of thresholds, solving the step length and the candidate threshold Tm，TmRepresents the mth threshold;
step＝|g|max/n；
Tm＝step×m；m＝1,2,…,n；
(3) according to the candidate threshold value TmStatistical gradient values smaller than T in the gradient matrix GmIs recorded as Nm,m＝1,2,...,n；
(4) Calculating the residual parameter margin RN [ m ] of the time convolution neural network model,
RN[m]＝k×k×d×a-Nm；
wherein k, d and a are dimension parameters of the gradient matrix G;
(5) repeating (2) - (4);
(6) and (3) calculating: Δ RN [ m ] ═ RN [ m +1] -RN [ m ]
Wherein, RN [ m +1]]Indicating the use of a threshold value Tm+1The number of remaining parameters after pruning, Delta RN [ m ]]Representing the difference of the parameter residual quantity after adjacent pruning;
(7) judgement of Delta RN [ m ]]If it is greater than 0, if it is not greater than 0, then it is guaranteedStoring the current m value and obtaining the final threshold value T ═ Tm(ii) a Otherwise, repeating (6) until:
ΔRN[m]＞Value
wherein Value is a self-defined parameter;
(8) and setting the weight matrix corresponding to the gradient matrix smaller than the final threshold value T as 0 to finish pruning.
5. The method as claimed in claim 4, wherein the method comprises the steps of: the total number n of the thresholds is 200.
6. The method as claimed in claim 1, wherein the method comprises the steps of: the controller is a raspberry pie.
7. The utility model provides a be applied to wisdom garden feed pipe and reveal marginal equipment detecting system which characterized in that: the system comprises:
the water supply pipe detection database construction module is used for acquiring the temperature and noise around the water supply pipe and the pressure and flow inside the water supply pipe to form a water supply pipe detection database;
the de-noising module is used for de-noising the data in the water supply pipe detection database;
the data preprocessing module is used for carrying out normalization processing on the data subjected to noise reduction processing, then carrying out manual labeling, and dividing the normalized data into a training set and a test set;
the time convolution neural network model module is used for constructing a time convolution neural network model and training the time convolution neural network model by utilizing the training set and the test set;
the pruning optimization module is used for optimizing the time convolution neural network model based on a pruning algorithm;
and the leakage detection module is used for deploying the optimized time convolution neural network model on the controller to realize the identification of whether the water supply pipe leaks or not.
8. The system of claim 7, wherein the system is applied to the detection of the leakage edge of the intelligent park water supply pipe: the controller is a raspberry pie.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method according to any of claims 1 to 5 are implemented when the processor executes the program.
10. A non-transitory computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110898121.2A CN113723210A (en) | 2021-08-05 | 2021-08-05 | Method and system for detecting leakage edge equipment of water supply pipe in intelligent park |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110898121.2A CN113723210A (en) | 2021-08-05 | 2021-08-05 | Method and system for detecting leakage edge equipment of water supply pipe in intelligent park |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113723210A true CN113723210A (en) | 2021-11-30 |
Family
ID=78674977
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110898121.2A Pending CN113723210A (en) | 2021-08-05 | 2021-08-05 | Method and system for detecting leakage edge equipment of water supply pipe in intelligent park |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113723210A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115993268A (en) * | 2023-03-22 | 2023-04-21 | 福建天甫电子材料有限公司 | Sampling system and method for anhydrous hydrogen fluoride |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200143519A1 (en) * | 2018-11-07 | 2020-05-07 | Spectrum Optix Inc. | Bright Spot Removal Using A Neural Network |
| CN111291806A (en) * | 2020-02-02 | 2020-06-16 | 西南交通大学 | Identification method of label number of industrial product based on convolutional neural network |
| WO2020133639A1 (en) * | 2018-12-29 | 2020-07-02 | 东北大学 | Intelligent analysis system for magnetic flux leakage detection data in pipeline |
| KR102226871B1 (en) * | 2020-10-26 | 2021-03-10 | 인천대학교 산학협력단 | Artificial intelligence-based leak monitoring apparatus that monitors the severity of leaks in the water pipe network and the operating method thereof |
| US20210110532A1 (en) * | 2019-10-11 | 2021-04-15 | International Business Machines Corporation | Disease detection from weakly annotated volumetric medical images using convolutional long short-term memory |
| CN112949817A (en) * | 2020-12-24 | 2021-06-11 | 长江勘测规划设计研究有限责任公司 | Water supply pipe leakage edge equipment detection method based on time convolution neural network |
-
2021
- 2021-08-05 CN CN202110898121.2A patent/CN113723210A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200143519A1 (en) * | 2018-11-07 | 2020-05-07 | Spectrum Optix Inc. | Bright Spot Removal Using A Neural Network |
| WO2020133639A1 (en) * | 2018-12-29 | 2020-07-02 | 东北大学 | Intelligent analysis system for magnetic flux leakage detection data in pipeline |
| US20210110532A1 (en) * | 2019-10-11 | 2021-04-15 | International Business Machines Corporation | Disease detection from weakly annotated volumetric medical images using convolutional long short-term memory |
| CN111291806A (en) * | 2020-02-02 | 2020-06-16 | 西南交通大学 | Identification method of label number of industrial product based on convolutional neural network |
| KR102226871B1 (en) * | 2020-10-26 | 2021-03-10 | 인천대학교 산학협력단 | Artificial intelligence-based leak monitoring apparatus that monitors the severity of leaks in the water pipe network and the operating method thereof |
| CN112949817A (en) * | 2020-12-24 | 2021-06-11 | 长江勘测规划设计研究有限责任公司 | Water supply pipe leakage edge equipment detection method based on time convolution neural network |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115993268A (en) * | 2023-03-22 | 2023-04-21 | 福建天甫电子材料有限公司 | Sampling system and method for anhydrous hydrogen fluoride |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106971152B (en) | Method for detecting bird nest in power transmission line based on aerial images | |
| CN112949817A (en) | Water supply pipe leakage edge equipment detection method based on time convolution neural network | |
| CN110533086B (en) | Semi-automatic image data labeling method | |
| CN113158364B (en) | Method and system for detecting bearing faults of circulating pump | |
| CN109359697A (en) | Graph image recognition methods and inspection system used in a kind of power equipment inspection | |
| CN110675421B (en) | Depth image collaborative segmentation method based on few labeling frames | |
| WO2023082418A1 (en) | Power utility tunnel settlement crack identification method based on artificial intelligence technology | |
| CN114241364A (en) | Method for quickly calibrating foreign object target of overhead transmission line | |
| CN113205039A (en) | Power equipment fault image identification and disaster investigation system and method based on multiple DCNNs | |
| CN112184661A (en) | Power equipment defect identification method based on image fusion deep learning model | |
| CN113723210A (en) | Method and system for detecting leakage edge equipment of water supply pipe in intelligent park | |
| CN113506239A (en) | Strip steel surface defect detection method based on cross-stage local network | |
| Altabey et al. | Research in image processing for pipeline crack detection applications | |
| CN114359702A (en) | Method and system for identifying building violation of remote sensing image of homestead based on Transformer | |
| CN116310358B (en) | Method, storage medium and equipment for detecting bolt loss of railway wagon | |
| CN111275025A (en) | Parking space detection method based on deep learning | |
| CN117079005A (en) | Optical cable fault monitoring method, system, device and readable storage medium | |
| CN114140731B (en) | Traction substation abnormality detection method | |
| CN115908843A (en) | Superheat degree recognition model training method, recognition method, equipment and storage medium | |
| CN113496159B (en) | Multi-scale convolution and dynamic weight cost function smoke target segmentation method | |
| Wang et al. | Rust defect detection and segmentation method for tower crane | |
| CN114519293A (en) | Cable body fault identification method based on hand sample machine learning model | |
| CN117292266B (en) | Method and device for detecting concrete cracks of main canal of irrigation area and storage medium | |
| CN116912637B (en) | Method, device, computer equipment and storage medium for identifying power transmission and transformation defects | |
| CN113627553B (en) | Image recognition method and system for recognizing abnormal label of electric energy meter |
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 |