CN111365624A - Intelligent terminal and method for detecting leakage of brine transportation pipeline - Google Patents
Intelligent terminal and method for detecting leakage of brine transportation pipeline Download PDFInfo
- Publication number
- CN111365624A CN111365624A CN202010202066.4A CN202010202066A CN111365624A CN 111365624 A CN111365624 A CN 111365624A CN 202010202066 A CN202010202066 A CN 202010202066A CN 111365624 A CN111365624 A CN 111365624A
- Authority
- CN
- China
- Prior art keywords
- transformation
- data
- conveying pipeline
- leakage
- signals
- 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
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17D—PIPE-LINE SYSTEMS; PIPE-LINES
- F17D5/00—Protection or supervision of installations
- F17D5/02—Preventing, monitoring, or locating loss
- F17D5/06—Preventing, monitoring, or locating loss using electric or acoustic means
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M3/00—Investigating fluid-tightness of structures
- G01M3/02—Investigating fluid-tightness of structures by using fluid or vacuum
- G01M3/04—Investigating fluid-tightness of structures by using fluid or vacuum by detecting the presence of fluid at the leakage point
- G01M3/24—Investigating fluid-tightness of structures by using fluid or vacuum by detecting the presence of fluid at the leakage point using infrasonic, sonic, or ultrasonic vibrations
- G01M3/243—Investigating fluid-tightness of structures by using fluid or vacuum by detecting the presence of fluid at the leakage point using infrasonic, sonic, or ultrasonic vibrations for pipes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M3/00—Investigating fluid-tightness of structures
- G01M3/02—Investigating fluid-tightness of structures by using fluid or vacuum
- G01M3/26—Investigating fluid-tightness of structures by using fluid or vacuum by measuring rate of loss or gain of fluid, e.g. by pressure-responsive devices, by flow detectors
- G01M3/28—Investigating fluid-tightness of structures by using fluid or vacuum by measuring rate of loss or gain of fluid, e.g. by pressure-responsive devices, by flow detectors for pipes, cables or tubes; for pipe joints or seals; for valves ; for welds
- G01M3/2807—Investigating fluid-tightness of structures by using fluid or vacuum by measuring rate of loss or gain of fluid, e.g. by pressure-responsive devices, by flow detectors for pipes, cables or tubes; for pipe joints or seals; for valves ; for welds for pipes
- G01M3/2815—Investigating fluid-tightness of structures by using fluid or vacuum by measuring rate of loss or gain of fluid, e.g. by pressure-responsive devices, by flow detectors for pipes, cables or tubes; for pipe joints or seals; for valves ; for welds for pipes using pressure measurements
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Pipeline Systems (AREA)
Abstract
The invention relates to the technical field of halogen conveying pipeline detection, and discloses an intelligent terminal and a method for detecting leakage of a halogen conveying pipeline. The detection method comprises the steps of obtaining a historical data set H; carrying out discrete S transformation on the test data, and dividing the test data into a training set Z and a test set T; training and determining an LSTM model; synchronously sampling the signals of the halogen conveying pipeline, and performing S discrete transformation on the signals; inputting the current data into the well-trained LSTM model to predict whether leakage occurs. Compared with the prior art, the method has the advantages that the data characteristics of the brine conveying pipeline at a certain time are fully known through S conversion, the time correlation among data is solved through LSTM modeling, manual threshold setting is avoided, and the accuracy of leakage judgment is improved.
Description
Technical Field
The invention relates to the technical field of halogen conveying pipeline detection, in particular to an intelligent terminal and method for detecting leakage of a halogen conveying pipeline.
Background
As the service life of the pipeline increases, accidents of pipeline leakage are increased continuously, the leakage of the pipeline not only causes serious pollution to the environment, but also brings huge economic loss to enterprises. Therefore, the method has important research significance for monitoring the pipeline in real time, determining the occurrence of faults in time and accurately positioning leakage points.
At present, the detection method of pipeline leakage mainly comprises the following steps: 1. negative pressure wave method; 2. infrasonic wave method; 3. distributed optical fiber pre-warning method and the like. When the pipeline has a tiny leakage, the signal change is not obvious. When detecting a minute leak by these methods, there is a general problem of low detection accuracy.
Disclosure of Invention
The purpose of the invention is as follows: aiming at the problems in the prior art, the invention provides an intelligent terminal and a method for detecting the leakage of a brine transportation pipeline, which can solve the problem that the existing pipeline leakage detection algorithm has low precision.
The technical scheme is as follows: the invention provides an intelligent terminal for detecting leakage of a brine conveying pipeline, which comprises an STM32F7 chip, a piezoelectric composite sensor, a filter circuit module, a high-precision A/D conversion circuit, a GPS module, an external SDRAM module, an SD card module and a 4G communication module;
the piezoelectric type composite sensor is used for detecting pressure signals and vibration signals inside a halogen conveying pipeline, analog signals collected by the piezoelectric type composite sensor are converted into digital signals through a filter circuit module and a high-precision A/D conversion circuit, the digital signals are transmitted to an STM32F7 chip in an SPI mode, collected data are written into an external SDRAM module, the STM32F7 chip analyzes the data, suspected leaked signals are stored in an SD card, and the signals are transmitted to an upper computer through a 4G module.
Furthermore, the intelligent terminal synchronously acquires vibration signals and pressure signals of the upper stream and the lower stream of the halogen conveying pipeline at a certain moment through pulse per second signals of the GPS module, and the GPS module is used for adding a time stamp to the acquired data.
Further, the high-precision a/D conversion circuit employs the ADS 1274.
The invention also discloses a method for detecting the leakage of the brine transportation pipeline, which comprises the following steps:
sept 1: acquiring a historical data set H of pressure and vibration signals of the inner wall of the brine conveying pipeline;
sept 2: performing discrete S transformation on the historical data set H, recording a data set D after the S transformation, and dividing the data set D after the S transformation into a training set Z and a test set T;
sept 3: building an LSTM model, selecting a training set Z in Sept2 to train the LSTM model, adjusting parameters until the network effect reaches the expected effect, and determining the LSTM model;
sept 4: taking a test set T in Sept2 as the input of an LSTM model, and verifying the accuracy of the model;
sept 5: synchronously sampling current vibration and pressure signals of the brine conveying pipeline, and performing S discrete transformation on current sampling data;
sept 6: and inputting the current data after S transformation into the well-trained LSTM model to predict whether leakage occurs.
Preferably, the discrete form of the S-transform is as follows:
where N is the total number of sampling points of the signal, T is the sampling period, X [ kT ] (k is 0,1,2 … N-1) is the sampled signal, N is the number of the nth point, m is the frequency point shifted to the left, and j is an imaginary unit.
Preferably, the specific steps of the S-transform are as follows:
step1.1: collecting pressure signal X [ kT ] of the inner wall of the halogen conveying pipeline;
Step1.3: when n is equal to 0, turning to step1.4, and executing step1.4 and step 1.5; when n is not 0, for a given frequency point n, the FFT of the gaussian window function is calculated:
step1.4: calculating S transform S [ kt,0] of a time series corresponding to a given time point k according to an equation of N ═ 0 (k ═ 0,1,2, …, N-1 denotes time sampling points);
step1.5: making k equal to k +1, repeating Step1.4 until S transformation of all the points is completed, and ending the S transformation;
step1.6: the product obtained in Step1.2The frequency spectrum function is obtained by translating m frequency points to the left
Step1.7: performing convolution on the Gaussian window function after Fourier transform and the spectrum function after translation to obtainThen, inverse Fourier transform is carried out to obtain an S transform spectrum corresponding to the frequency point n
Step 1.8: let n be n +1, repeat step1.6, step1.7 until S transform of all frequency points is calculated.
Preferably, the LSTM model formula includes:
1) forget the door: conditionally choose which information to discard from the current cell, the formula is as follows:
ft=σ(Wf.[ht-1,Xt]+bf)
wherein f ist∈[0,1]1 means "complete retention", 0 means "complete discard", wherein ht-1Representing the output, X, of the last instant LSTMtIndicating the current input of the cell, WfWeight matrix for forgetting gate, bfFor biasing, σ is an activation function, usually a Sigmoid function is chosen, i.e.
2) An input gate: conditionally deciding which information to store in the cell, the formula is as follows:
it=σ(Wi.[ht-1,Xt]+bi)
wherein, the input gate itIs composed of XtAnd ht-1Generated by calculation of Sigmoid function, itSame as ftLikewise is one between [0,1 ]]The vector of (a); the other is formed by XtAnd ht-1A vector generated by the tanh activation functionRepresents the cell state update value, itControl ofIs used to update the current state, thereby generating a new state
3) An output gate: conditionally deciding which information needs to be output, and outputting the information; the formula is as follows:
Ot=σ(Wo.[ht-1,Xt]+bo)
ht=Ot*tanh(Ct)
wherein a Sigmoid layer is run to determine which part of the cell state will be output, then the cell state is processed through tanh to get a value between-1 and 1, and it is multiplied by the output of the Sigmoid gate, and finally only the part that we determine the output will be output.
Preferably, in the Sept3, the difference between the actual output and the expected output is described through a cross entropy loss function, the cross entropy loss function is minimized by using a random gradient descent method, and the LSTM model is subjected to parameter adjustment until the model meets the requirements, wherein the cross entropy loss function formula is as follows:
wherein the content of the first and second substances,the actual probability of leakage of the brine conveying pipeline at the time t is shown, Z is a training set, Z is data in the training set, and p (y)t|ht) The probability of model prediction is represented, namely the probability when the halogen conveying pipeline leaks is as follows: p (y)t|ht)=softmax(θht+ b) ofθ=(θ1,θ2...θZ) For the weight matrix, b is the offset, and a "1" is marked as leaking, and a "0" indicates that the pipe is not leaking.
Has the advantages that:
1. the invention can fully know the time-frequency-mode three-dimensional characteristics of data at a certain moment of the halogen conveying pipeline through S conversion, and the characteristics of the data can be better learned by the model as the input of the LSTM model, thereby increasing the accuracy of model judgment.
2. According to the method, the pressure signal and the vibration signal in the halogen conveying pipeline are modeled through the LSTM, and the time correlation among data is solved.
3. In the prior art, the leakage judgment of the brine conveying pipeline needs to set a threshold, but the detection method provided by the invention can avoid manual setting of the threshold and increase the accuracy of the leakage judgment.
Drawings
FIG. 1 is a block diagram of a leak detection apparatus according to the present invention;
FIG. 2 is a circuit diagram of the smart terminal of the present invention;
FIG. 3 is an overall block diagram of the present invention;
FIG. 4 is a flow chart of the S transformation of the present invention;
FIG. 5 is a flow chart of the LSTM model of the present invention;
FIG. 6 is a graph of simulation data for the present invention;
FIG. 7 is a graph of the data after S-transform in accordance with the present invention.
Detailed Description
The present invention will be described in detail with reference to the accompanying drawings.
Fig. 1 shows an intelligent terminal for detecting leakage of a brine conveying pipeline, which comprises an STM32F7 chip, a piezoelectric composite sensor, a filter circuit module, a high-precision a/D conversion circuit, a GPS module, an external SDRAM module, an SD card module, and a 4G communication module. The intelligent terminal synchronously acquires vibration signals and pressure signals of the brine conveying pipeline at upstream and downstream certain moments through pulse per second signals of the GPS module, and the GPS module is utilized to add a timestamp to acquired data, so that the data processing after the data processing is facilitated. And the acquired analog data is subjected to clutter interference removal through a filter circuit module, and analog-to-digital conversion is carried out on the filtered analog signal through an A/D (analog/digital) conversion circuit.
The high-precision A/D conversion circuit adopts ADS 1274. The ADS1274 is a 24-bit successive approximation type analog-digital converter including four-way AD conversion circuits. The ADS1274 and the STM32F7 perform data transmission through the SPI. The STM32F7 chip receives the PPS interrupt signal of GPS through the capture function of the timer, when the timer captures the rising edge, the data ready signal of ADS1274 is detected in the PPS interrupt processing functionWhether a falling edge is generated. If a falling edge occurs, it indicates that the data is ready, at which point the data transmission begins. The intelligent terminal temporarily stores these time-stamped unanalyzed digital signals in an external SDRAM to relieve the computational pressure of STM32F7, so that simple data analysis can be performed in STM32F7 of the intelligent terminal. And storing the suspected leakage signal analyzed by the intelligent terminal into the SD card. Simultaneously, this intelligent terminal utilizes the 4G module to upload the defeated steamed pipeline upstream and downstream data of gathering to the high in the clouds, gathers a large amount of data and analyzes. The circuit connection diagram of the intelligent terminal is shown in fig. 1 and 2.
Fig. 2 is a filter circuit diagram of the circuit. The invention needs to analyze the alternating current signal generated by the internal vibration of the halogen conveying pipeline, so that the alternating current signal is amplified by the first part of the filtering and amplifying circuit, and the direct current signal is used as a carrier signal and is kept unchanged. The second part is a differential amplifying circuit. For a direct current signal, the differential amplification circuit is a common-mode input, the voltage of the output end is 0, the interference of the direct current voltage is avoided, and meanwhile, the required alternating current signal is amplified.
The invention also discloses a method for detecting the leakage of the brine conveying pipeline, the whole flow chart is shown in figure 3, the total sampling point number of the signal is set to be N, and the adopted period is T. The detection method mainly comprises the following steps:
sept 1: and acquiring a historical data set H of the pressure and vibration signals of the inner wall of the halogen conveying pipeline.
Pressure signals of the inner wall of the pipeline are obtained through the piezoelectric composite sensor (vibration signals are analyzed in the same way), and the sampled signals are X [ kT ] (k is 0,1,2 … N-1).
Sept 2: performing discrete S transformation on a historical data set H, recording a data set D after S transformation, and dividing the data set D after S transformation into a training set Z (70% of total data) and a testing set T (30% of total data)
The discrete form of the S transform is as follows:
where N is the total number of sampling points of the signal, T is the sampling period, X [ kT ] (k is 0,1,2 … N-1) is the sampled signal, N is the number of the nth point, m is the frequency point shifted to the left, and j is an imaginary unit.
And (4) performing discrete S transformation on all acquired signals (historical data set H), and recording the data set after S transformation.
The specific steps of S transformation are shown in fig. 4:
step2.1: and collecting a pressure signal X [ kT ] of the inner wall of the data pipeline.
Step2.3: when n is equal to 0, the operation goes to step2.4, and step2.4 and step2.5 are executed; when n is not 0, for a given frequency point n, the FFT of the gaussian window function is calculated:
Step2.4: the S transform S [ Kt,0] of the time series corresponding to a given time point k is calculated according to the formula where N is 0 (k is 0,1,2, …, N-1 denotes a time sampling point).
Step2.5: let k be k +1 and repeat step2.4 until the S transform is completed for all points.
Step2.7: performing convolution on the Gaussian window function after Fourier transform and the spectrum function after translation to obtainThen, inverse Fourier transform is carried out to obtain an S transform spectrum corresponding to the frequency point n
Step2.8: let n be n +1, repeat step2.6, step2.7 until S-transform of all frequency points is calculated.
Sept 3: and (3) obtaining a plurality of matrixes after S conversion of the N signal points, building an LSTM model by using the matrixes, selecting a training set Z in Sept2 to train the LSTM model, adjusting parameters until the network effect reaches the expected effect, and determining the LSTM model.
Sept 4: and (5) taking the test set T in the Sept2 as the input of the LSTM model, and verifying the accuracy of the model.
Sept 5: synchronously sampling the current vibration and pressure signals of the halogen conveying pipeline, and performing S discrete transformation on the current sampling data.
Sept 6: and inputting the current data after S transformation into the well-trained LSTM model to predict whether leakage occurs.
The formula of the LSTM model comprises:
1) forget the door: conditionally choose which information to discard from the current cell, the formula is as follows:
ft=σ(Wf.[ht-1,Xt]+bf)
wherein f ist∈[0,1]1 means "complete retention", 0 means "complete discard", wherein ht-1Representing the output, X, of the last instant LSTMtIndicating the current input of the cell, WfWeight matrix for forgetting gate, bfFor biasing, σ is an activation function, usually a Sigmoid function is chosen, i.e.
2) An input gate: conditionally deciding which information to store in the cell, the formula is as follows:
it=σ(Wi.[ht-1,Xt]+bi)
wherein, the input gate itIs composed of XtAnd ht-1Generated by calculation of Sigmoid function, itSame as ftLikewise is one between [0,1 ]]The vector of (a); the other is formed by XtAnd ht-1A vector generated by the tanh activation functionRepresents the cell state update value, itControl ofIs used to update the current state, thereby generating a new state
3) An output gate: conditionally deciding which information needs to be output, and outputting the information; the formula is as follows:
Ot=σ(Wo.[ht-1,Xt]+bo)
ht=Ot*tanh(Ct)
wherein a Sigmoid layer is run to determine which part of the cell state will be output, then the cell state is processed through tanh to get a value between-1 and 1, and it is multiplied by the output of the Sigmoid gate, and finally only the part that we determine the output will be output.
Let "1" mark leakage and "0" indicate that no leakage has occurred in the pipe. And (4) carrying out model parameter adjustment by minimizing cross entropy loss through a random gradient descent method until the accuracy of the model meets the requirement. The formula of the loss function is as follows:
wherein the content of the first and second substances,the actual probability of leakage of the brine conveying pipeline at the time t is shown, Z is a training set, Z is data in the training set, and p (y)t|ht) The probability of model prediction is represented, namely the probability when the halogen conveying pipeline leaks is as follows: p (y)t|ht)=soft max(θht+ b) ofθ=(θ1,θ2...θZ) B is the bias.
Fig. 6 is a simulation diagram of a halogen pipeline, in which a white noise signal is added to a collected signal to simulate noise of the halogen pipeline. Fig. 7 is a two-dimensional contour diagram after S-transformation of the simulation data, i.e., a time-frequency-mode graph of the halogen transporting pipeline. Finally, the matrix after S transformation is used as the input of the LSTM model, when the output is 1, the table leaks, and when the output is 0, the table does not leak.
The above embodiments are merely illustrative of the technical concepts and features of the present invention, and the purpose of the embodiments is to enable those skilled in the art to understand the contents of the present invention and implement the present invention, and not to limit the protection scope of the present invention. All equivalent changes and modifications made according to the spirit of the present invention should be covered within the protection scope of the present invention.
Claims (8)
1. An intelligent terminal for detecting leakage of a brine conveying pipeline is characterized by comprising an STM32F7 chip, a piezoelectric composite sensor, a filter circuit module, a high-precision A/D conversion circuit, a GPS module, an external SDRAM module, an SD card module and a 4G communication module;
the piezoelectric type composite sensor is used for detecting pressure signals and vibration signals inside a halogen conveying pipeline, analog signals collected by the piezoelectric type composite sensor are converted into digital signals through a filter circuit module and a high-precision A/D conversion circuit, the digital signals are transmitted to an STM32F7 chip in an SPI mode, collected data are written into an external SDRAM module, the STM32F7 chip analyzes the data, suspected leaked signals are stored in an SD card, and the signals are transmitted to an upper computer through a 4G module.
2. The intelligent terminal for detecting the leakage of the brine transportation pipeline as claimed in claim 1, wherein the intelligent terminal synchronously acquires the vibration signal and the pressure signal at a certain time upstream and downstream of the brine transportation pipeline through a pulse per second signal of the GPS module, and the GPS module is used for adding a time stamp to the acquired data.
3. The intelligent terminal for detecting the leakage of the halogen transmission pipeline according to claim 1, wherein the high-precision A/D conversion circuit adopts ADS 1274.
4. A method for detecting leakage of a halogen conveying pipeline is characterized by comprising the following steps:
sept 1: acquiring a historical data set H of pressure and vibration signals of the inner wall of the brine conveying pipeline;
sept 2: performing discrete S transformation on the historical data set H, recording a data set D after the S transformation, and dividing the data set D after the S transformation into a training set Z and a test set T;
sept 3: building an LSTM model, selecting a training set Z in Sept2 to train the LSTM model, adjusting parameters until the network effect reaches the expected effect, and determining the LSTM model;
sept 4: taking a test set T in Sept2 as the input of an LSTM model, and verifying the accuracy of the model;
sept 5: synchronously sampling current vibration and pressure signals of the brine conveying pipeline, and performing S discrete transformation on current sampling data;
sept 6: and inputting the current data after S transformation into the well-trained LSTM model to predict whether leakage occurs.
5. The method of claim 4, wherein the discrete form of the S transformation is as follows:
where N is the total number of sampling points of the signal, T is the sampling period, X [ kT ] (k is 0,1,2 … N-1) is the sampled signal, N is the number of the nth point, m is the frequency point shifted to the left, and j is an imaginary unit.
6. The method for detecting the leakage of the brine transportation pipeline according to claim 5, wherein the specific steps of S transformation are as follows:
step1.1: collecting pressure signal X [ kT ] of the inner wall of the halogen conveying pipeline;
Step1.3: when n is equal to 0, turning to step1.4, and executing step1.4 and step 1.5; when n is not 0, for a given frequency point n, the FFT of the gaussian window function is calculated:
step1.4: calculating S transform S [ kt,0] of a time series corresponding to a given time point k according to an equation of N ═ 0 (k ═ 0,1,2, …, N-1 denotes time sampling points);
step1.5: making k equal to k +1, repeating Step1.4 until S transformation of all the points is completed, and ending the S transformation;
step1.6: the product obtained in Step1.2The frequency spectrum function is obtained by translating m frequency points to the left
Step1.7: performing convolution on the Gaussian window function after Fourier transform and the spectrum function after translation to obtainThen, inverse Fourier transform is carried out to obtain an S transform spectrum corresponding to the frequency point n
Step 1.8: let n be n +1, repeat step1.6, step1.7 until S transform of all frequency points is calculated.
7. The method of claim 4, wherein the LSTM model formula comprises:
1) forget the door: conditionally choose which information to discard from the current cell, the formula is as follows:
ft=σ(Wf.[ht-1,Xt]+bf)
wherein f ist∈[0,1]1 means "complete retention", 0 means "complete discard", wherein ht-1Representing the output, X, of the last instant LSTMtIndicating the current input of the cell, WfWeight matrix for forgetting gate, bfFor biasing, σ is an activation function, usually a Sigmoid function is chosen, i.e.
2) An input gate: conditionally deciding which information to store in the cell, the formula is as follows:
it=σ(Wi.[ht-1,Xt]+bi)
wherein, the input gate itIs composed of XtAnd ht-1Generated by calculation of Sigmoid function, itSame as ftLikewise is one between [0,1 ]]The vector of (a); the other is formed by XtAnd ht-1A vector generated by the tanh activation functionRepresents the cell state update value, itControl ofIs used to update the current state, thereby generating a new state
3) An output gate: conditionally deciding which information needs to be output, and outputting the information; the formula is as follows:
Ot=σ(Wo.[ht-1,Xt]+bo)
ht=Ot*tanh(Ct)
wherein a Sigmoid layer is run to determine which part of the cell state will be output, then the cell state is processed through tanh to get a value between-1 and 1, and it is multiplied by the output of the Sigmoid gate, and finally only the part that we determine the output will be output.
8. The method of claim 7, wherein the Sept3 is characterized by that the difference between the actual output and the expected output is characterized by a cross entropy loss function, and the cross entropy loss function is minimized by using a stochastic gradient descent method, and the LSTM model is parametrically adjusted until the model meets the requirement, and when "1" is marked as leakage, and "0" indicates that no leakage occurs in the pipeline, the cross entropy loss function is formulated as:
wherein the content of the first and second substances,the actual probability of leakage of the brine conveying pipeline at the time t is shown, Z is a training set, Z is data in the training set, and p (y)t|ht) The probability of model prediction is represented, namely the probability when the halogen conveying pipeline leaks is as follows: p (y)t|ht)=softmax(θht+ b) ofθ=(θ1,θ2...θZ) B is the bias.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010202066.4A CN111365624A (en) | 2020-03-20 | 2020-03-20 | Intelligent terminal and method for detecting leakage of brine transportation pipeline |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010202066.4A CN111365624A (en) | 2020-03-20 | 2020-03-20 | Intelligent terminal and method for detecting leakage of brine transportation pipeline |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111365624A true CN111365624A (en) | 2020-07-03 |
Family
ID=71207656
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010202066.4A Pending CN111365624A (en) | 2020-03-20 | 2020-03-20 | Intelligent terminal and method for detecting leakage of brine transportation pipeline |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111365624A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111693264A (en) * | 2020-06-16 | 2020-09-22 | 清华大学 | Fluid machinery diagnosis system and method based on artificial intelligence and big data |
CN113446593A (en) * | 2021-06-25 | 2021-09-28 | 吉林化工学院 | Boiler pressure-bearing pipeline leakage detection system |
CN116306377A (en) * | 2023-04-04 | 2023-06-23 | 中国石油大学(华东) | Method and system for rapidly predicting consequences of leakage accident of hydrogen station |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20060059977A1 (en) * | 2004-09-23 | 2006-03-23 | Lawrence Kates | System and method for utility metering and leak detection |
CN101546906A (en) * | 2009-05-05 | 2009-09-30 | 昆明理工大学 | Method for fault line selection of electric distribution network by using S transformation energy relative entropy |
CN102563362A (en) * | 2011-12-31 | 2012-07-11 | 杭州哲达科技股份有限公司 | Compressed air system and intelligent pipe network leakage detecting method for same |
CN104075122A (en) * | 2014-06-12 | 2014-10-01 | 东北大学 | Portable integrated pipe leakage detection device and method |
CN106287240A (en) * | 2016-09-05 | 2017-01-04 | 中国石油大学(华东) | A kind of pipeline leakage testing device based on acoustic emission and single-sensor localization method |
CN110222953A (en) * | 2018-12-29 | 2019-09-10 | 北京理工大学 | A kind of power quality hybrid perturbation analysis method based on deep learning |
-
2020
- 2020-03-20 CN CN202010202066.4A patent/CN111365624A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20060059977A1 (en) * | 2004-09-23 | 2006-03-23 | Lawrence Kates | System and method for utility metering and leak detection |
CN101546906A (en) * | 2009-05-05 | 2009-09-30 | 昆明理工大学 | Method for fault line selection of electric distribution network by using S transformation energy relative entropy |
CN102563362A (en) * | 2011-12-31 | 2012-07-11 | 杭州哲达科技股份有限公司 | Compressed air system and intelligent pipe network leakage detecting method for same |
CN104075122A (en) * | 2014-06-12 | 2014-10-01 | 东北大学 | Portable integrated pipe leakage detection device and method |
CN106287240A (en) * | 2016-09-05 | 2017-01-04 | 中国石油大学(华东) | A kind of pipeline leakage testing device based on acoustic emission and single-sensor localization method |
CN110222953A (en) * | 2018-12-29 | 2019-09-10 | 北京理工大学 | A kind of power quality hybrid perturbation analysis method based on deep learning |
Non-Patent Citations (3)
Title |
---|
范乐: "热网关键节点泄漏监测系统的设计与研发", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
邵萌等: "《微位移平台数据采集与处理技术》", 30 September 2018, 东北大学出版社 * |
雷振山等: "《LabVIEW高级编程与虚拟仪器工程应用》", 31 August 2013, 中国铁道出版社 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111693264A (en) * | 2020-06-16 | 2020-09-22 | 清华大学 | Fluid machinery diagnosis system and method based on artificial intelligence and big data |
CN111693264B (en) * | 2020-06-16 | 2021-03-16 | 清华大学 | Fluid machinery diagnosis system and method based on artificial intelligence and big data |
CN113446593A (en) * | 2021-06-25 | 2021-09-28 | 吉林化工学院 | Boiler pressure-bearing pipeline leakage detection system |
CN116306377A (en) * | 2023-04-04 | 2023-06-23 | 中国石油大学(华东) | Method and system for rapidly predicting consequences of leakage accident of hydrogen station |
CN116306377B (en) * | 2023-04-04 | 2024-04-05 | 中国石油大学(华东) | Method and system for rapidly predicting consequences of leakage accident of hydrogen station |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111365624A (en) | Intelligent terminal and method for detecting leakage of brine transportation pipeline | |
CN108805269B (en) | Method for picking seismic facies arrival time based on LSTM recurrent neural network | |
KR102181966B1 (en) | Soft survey method and system for hydraulic cylinder comprehensive test station | |
CN105546352A (en) | Natural gas pipeline tiny leakage detection method based on sound signals | |
CN109492708A (en) | Missing data interpolating method is detected in a kind of pipe leakage based on LS-KNN | |
CN111853555A (en) | Water supply pipe network blind leakage identification method based on dynamic process | |
CN113687433B (en) | Bi-LSTM-based magnetotelluric signal denoising method and system | |
CN112884213B (en) | Coal-fired boiler NOx prediction method based on wavelet decomposition and dynamic mixed deep learning | |
CN115951014A (en) | CNN-LSTM-BP multi-mode air pollutant prediction method combining meteorological features | |
CN111695413A (en) | Signal first arrival pickup method and device combining U-Net and Temporal encoding | |
CN110514366B (en) | Method for detecting weak leakage of pipeline under small sample condition | |
CN114330120B (en) | 24-Hour PM prediction based on deep neural network2.5Concentration method | |
CN113920255B (en) | High-efficient mapping system based on point cloud data | |
CN113361782B (en) | Photovoltaic power generation power short-term rolling prediction method based on improved MKPLS | |
CN114676779A (en) | Atmospheric quality monitoring data calibration method and system based on robust width network | |
CN114462717A (en) | Small sample gas concentration prediction method based on improved GAN and LSTM | |
CN113988210A (en) | Method and device for restoring distorted data of structure monitoring sensor network and storage medium | |
CN117113854A (en) | Salt tide forecasting method based on ConvLSTM and three-dimensional numerical simulation | |
CN117332324A (en) | Pipeline leakage detection method and device, electronic equipment and storage medium | |
CN114943189B (en) | XGboost-based acoustic velocity profile inversion method and system | |
CN116772122A (en) | Natural gas pipeline leakage fault diagnosis method, system, equipment and medium | |
CN116244596A (en) | Industrial time sequence data anomaly detection method based on TCN and attention mechanism | |
CN115081741A (en) | Natural gas metrological verification intelligent prediction method based on neural network | |
CN109945075B (en) | Method and device for detecting leakage degree of water supply pipeline | |
CN113065498A (en) | Abnormal data detection method based on improved EMD and neural network model |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200703 |
|
RJ01 | Rejection of invention patent application after publication |