CN118091331B - Cable fault sensing method and system - Google Patents
Cable fault sensing method and system Download PDFInfo
- Publication number
- CN118091331B CN118091331B CN202410510585.5A CN202410510585A CN118091331B CN 118091331 B CN118091331 B CN 118091331B CN 202410510585 A CN202410510585 A CN 202410510585A CN 118091331 B CN118091331 B CN 118091331B
- Authority
- CN
- China
- Prior art keywords
- cable line
- data
- deep learning
- iot
- cable
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000012544 monitoring process Methods 0.000 claims abstract description 99
- 238000013136 deep learning model Methods 0.000 claims abstract description 97
- 238000001514 detection method Methods 0.000 claims abstract description 55
- 238000013135 deep learning Methods 0.000 claims abstract description 31
- 238000005516 engineering process Methods 0.000 claims abstract description 21
- 230000008447 perception Effects 0.000 claims abstract 2
- 230000005540 biological transmission Effects 0.000 claims description 58
- 230000005684 electric field Effects 0.000 claims description 56
- 230000006870 function Effects 0.000 claims description 25
- 238000012549 training Methods 0.000 claims description 24
- 210000002569 neuron Anatomy 0.000 claims description 20
- 230000008569 process Effects 0.000 claims description 18
- 230000014509 gene expression Effects 0.000 claims description 17
- 230000004913 activation Effects 0.000 claims description 10
- 238000010276 construction Methods 0.000 claims description 10
- 238000001914 filtration Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 9
- ODKSFYDXXFIFQN-UHFFFAOYSA-M argininate Chemical group [O-]C(=O)C(N)CCCNC(N)=N ODKSFYDXXFIFQN-UHFFFAOYSA-M 0.000 claims description 5
- 238000013528 artificial neural network Methods 0.000 claims description 5
- 238000012360 testing method Methods 0.000 claims description 5
- 238000004891 communication Methods 0.000 abstract description 3
- 238000005265 energy consumption Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 7
- 238000012423 maintenance Methods 0.000 description 6
- 238000004590 computer program Methods 0.000 description 5
- 230000002159 abnormal effect Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 241000764238 Isis Species 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000000969 carrier Substances 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005672 electromagnetic field Effects 0.000 description 1
- 101150012763 endA gene Proteins 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000010363 phase shift Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Landscapes
- Testing Of Short-Circuits, Discontinuities, Leakage, Or Incorrect Line Connections (AREA)
- Monitoring And Testing Of Transmission In General (AREA)
Abstract
The invention discloses a cable fault sensing method and a system, wherein the method comprises the following steps: collecting fault monitoring data information of a cable circuit; transmitting the cable line fault monitoring data information by utilizing an NB-IoT technology, including modulating and demodulating the cable line fault monitoring data information by utilizing a QPSK technology; constructing a cable line fault detection model based on deep learning; extracting a connection weight and a threshold value from a cable line fault detection model based on deep learning, constructing a cable line fault detection deep learning model library, updating the cable line fault detection deep learning model library into a cable line fault monitoring system, and transmitting collected field data into the cable line fault monitoring system based on NB-IoT for online monitoring of cable line faults. The invention has the characteristics of wide monitoring range, low communication energy consumption, strong perceptibility and the like, and can comprehensively improve the perception level of cable line faults.
Description
Technical Field
The invention relates to the technical field of electrical equipment, in particular to a cable fault sensing method and system.
Background
Cable line fault monitoring is of great significance to the operation of the power system. Firstly, for safety, potential cable line problems can be found in time through monitoring, potential safety hazards such as fire and electric shock are avoided, and therefore overall safety of a power system is improved. Secondly, fault monitoring helps to improve reliability of the power system, and reduces power failure time of the cable line by timely finding and repairing faults. In addition, monitoring can also improve maintenance efficiency, reduce associated costs, and reduce emergency maintenance requirements by predictively maintaining problems that are discovered and repaired before the failure is exacerbated. The service lives of the cable lines and related equipment can be prolonged by timely processing faults, and the equipment aging process is slowed down. Finally, the fault monitoring can prevent the problems of voltage fluctuation, harmonic waves and the like caused by cable line faults, and ensure the stable operation of the power system.
At present, many researches on a cable fault monitoring method are carried out, but the following disadvantages still exist: first, the limited real-time performance and sensitivity, the conventional cable fault monitoring system has a certain limitation in terms of real-time performance and fault sensitivity, and may not be capable of detecting a weak fault signal immediately. The complexity of the sensor data, the environment of the cabling, is then complex, and the sensor data may be affected by a variety of factors, including temperature, humidity, electromagnetic interference, etc., thereby affecting the accuracy of the monitoring. Second, the high cost and complex maintenance, which is typically required for large scale equipment deployment, brings about high equipment costs and complex maintenance requirements, especially in large power systems, where the costs and complexity are more pronounced. Finally, it is difficult to distinguish between normal operation and potential faults, some changes in the normal operation may be misinterpreted as faults, resulting in false alarms, or the actual potential fault signals may be masked.
Disclosure of Invention
In order to solve the above problems, the present invention provides a cable fault sensing method and system capable of improving the capability of monitoring cable faults.
In order to achieve the above object, the present invention is realized by the following technical scheme:
the invention relates to a cable fault sensing method, which comprises the following operations:
Collecting fault monitoring data information of a cable line, wherein the fault monitoring data information comprises current data, voltage data, temperature data, humidity data, resistance data, vibration data, electric field data and magnetic field data of the cable;
Transmitting the cable line fault monitoring data information by utilizing an NB-IoT technology, including modulating and demodulating the cable line fault monitoring data information by utilizing a QPSK technology;
constructing a cable line fault detection model based on deep learning;
Extracting a connection weight and a threshold value from a cable line fault detection model based on deep learning, constructing a cable line fault detection deep learning model library, updating the cable line fault detection deep learning model library into a cable line fault monitoring system, and transmitting collected field data into the cable line fault monitoring system based on NB-IoT for online monitoring of cable line faults.
The invention further improves that: the collected cable line fault monitoring data information expression is as follows:
（1）；
In the method, in the process of the invention, For the cable line fault monitoring data at time t,For the cabling current data at time t,For the cable line voltage data at time t,Is the temperature data of the cable line at the time t,The humidity data of the cable circuit at the moment t,The data of the resistance of the cable line at the time t,The vibration data of the cable line at the moment t,For the cable line electric field data at time t,And the magnetic field data of the cable line at the time t.
The invention further improves that: the transmission of the cable line fault monitoring data information by using the NB-IoT technology comprises the modulation and demodulation of the cable line fault monitoring data information by using the QPSK technology, and specifically comprises the following operations: modulating the collected cable line fault monitoring data information, wherein the NB-IoT transmits the modulated cable line fault monitoring data information, a receiving end of the NB-IoT demodulates the received cable line fault monitoring data information, the following formulas (2) - (6) are cable line electric field data NB-IoT transmission processing procedures, and the formula (7) is an expression of the cable line fault monitoring data information obtained through NB-IoT transmission:
（2）；
（3）；
（4）；
（5）；
（6）；
（7）；
Wherein: For the modulated cable line electric field data at time t, For the cable line electric field data at time t,The electric field signal frequency of the cable line at the time t,For the electric field phase angle of the cable line at the time t,For the receiving end to receive the electric field data of the cable line at the time t,For the noise experienced in NB-IoT transmission signals,、The sine component and the cosine component after the low-pass filtering process respectively, the lowpass { } function represents low-pass filtering for extracting the baseband signal component in the function, the arg () function represents finding the largest sine and cosine component,For the cable line fault monitoring data after transmission over NB-IoT,For the cable line current data transmitted over NB-IoT,For the cable line voltage data transmitted over NB-IoT,For the cabling temperature data after transmission over NB-IoT,For the cabling wetness data after transmission over NB-IoT,For the cabling resistance data after transmission over NB-IoT,For the cabling vibration data after transmission over NB-IoT,For the cable line electric field data after transmission over NB-IoT,Is the cabling magnetic field data after being transmitted through the NB-IoT.
The invention further improves that: the construction of the cable line fault detection model based on deep learning specifically comprises the following operations:
Marking the received cable line fault monitoring data to form a training sample of the deep learning model; training a sample by using a deep learning model, wherein the training comprises forward propagation and reverse propagation training processes, the prediction error of the deep learning model is minimized by adjusting the weight and the bias of a neural network, the performance of the deep learning model is estimated by using an independent test data set, and the final training forms a cable line fault detection model based on deep learning;
The cable line fault detection model based on deep learning comprises 8 inputs and 2 outputs, wherein the 8 inputs are respectively: cable line current data transmitted over NB-IoT Is a sample of the cable line voltage dataIs a sample of the cabling temperature dataIs a sample of the cable run humidity dataIs a sample of the cable run resistance dataIs a sample of the cable run vibration dataIs a sample of the cable run electric field dataIs a sample of the cabling magnetic field dataThe 2 outputs are respectively: in order for a fault to be present, To be fault-free;
The hidden layer of the deep learning model has n neurons, and each neuron in the hidden layer The outputs of (2) are calculated by weighting and through an activation function, and the expressions are shown in (8) - (9):
（8）；
（9）；
Wherein: Is a neuron of an hidden layer of the deep learning model, j is a neuron serial number, the range of values is 1-n, As an activation function of the deep learning model,Is a connection inputAnd neuronsIs used for the weight of the (c),Is a neuronH is the hidden layer output vector of the deep learning model,The input of the deep learning model is that i is the layer number of the deep learning model;
the output of the deep learning model is:
（10）；
Wherein: for the output of the deep learning model, To connect neuronsAnd output ofIs used for the weight of the (c),For outputtingIs included.
The invention further improves that: the expression of the cable line fault detection deep learning model library is as follows:
（11）；
Wherein: a deep learning model for the kth cabling fault detection, In order to train the deep learning model well,And connecting weights from the input layer to the output layer of the trained deep learning model.
The invention discloses a cable fault sensing system, which comprises an acquisition module, an NB-IoT transmission module, a model construction module, a model library construction and update module and an alarm module, wherein the acquisition module is used for acquiring a cable of a cable;
The acquisition module is used for acquiring fault monitoring data information of the cable line, including current data, voltage data, temperature data, humidity data, resistance data, vibration data, electric field data and magnetic field data of the cable;
The NB-IoT transmission module is configured to transmit cable line fault monitoring data information, and includes performing modulation and demodulation of the cable line fault monitoring data information by using a QPSK technology;
the model construction module is used for constructing a cable line fault detection model based on deep learning;
The model library constructing and updating module is used for extracting a connection weight and a threshold value from a cable line fault detection model based on deep learning, constructing a cable line fault detection deep learning model library, and updating the cable line fault detection deep learning model library into a cable line fault monitoring system;
and the alarm module is used for giving an alarm when the cable line fault monitoring system detects a fault.
The invention further improves that: the collected cable line fault monitoring data information expression is as follows:
（12）；
In the method, in the process of the invention, For the cable line fault monitoring data at time t,For the cabling current data at time t,For the cable line voltage data at time t,Is the temperature data of the cable line at the time t,The humidity data of the cable circuit at the moment t,The data of the resistance of the cable line at the time t,The vibration data of the cable line at the moment t,For the cable line electric field data at time t,And the magnetic field data of the cable line at the time t.
The invention further improves that: the NB-IoT transmission module includes: modulating the collected cable line fault monitoring data information, wherein the NB-IoT transmits the modulated cable line fault monitoring data information, a receiving end of the NB-IoT demodulates the received cable line fault monitoring data information, the following formulas (13) - (17) are cable line electric field data NB-IoT transmission processing processes, and the formula (18) is an expression of the cable line fault monitoring data information obtained through NB-IoT transmission;
（13）；
（14）；
（15）；
（16）；
（17）；
（18）；
Wherein: For the modulated cable line electric field data at time t, For the cable line electric field data at time t,The electric field signal frequency of the cable line at the time t,For the electric field phase angle of the cable line at the time t,For the receiving end to receive the electric field data of the cable line at the time t,For the noise experienced in NB-IoT transmission signals,、The sine component and the cosine component after the low-pass filtering process respectively, the lowpass { } function represents low-pass filtering for extracting the baseband signal component in the function, the arg () function represents finding the largest sine and cosine component,For the cable line fault monitoring data after transmission over NB-IoT,For the cable line current data transmitted over NB-IoT,For the cable line voltage data transmitted over NB-IoT,For the cabling temperature data after transmission over NB-IoT,For the cabling wetness data after transmission over NB-IoT,For the cabling resistance data after transmission over NB-IoT,For the cabling vibration data after transmission over NB-IoT,For the cable line electric field data after transmission over NB-IoT,Is the cabling magnetic field data after being transmitted through the NB-IoT.
The invention further improves that: the construction of the cable line fault detection model based on deep learning specifically comprises the following operations:
Marking the received cable line fault monitoring data to form a training sample of the deep learning model; training a sample by using a deep learning model, wherein the training comprises forward propagation and reverse propagation training processes, the prediction error of the deep learning model is minimized by adjusting the weight and the bias of a neural network, the performance of the deep learning model is estimated by using an independent test data set, and the final training forms a cable line fault detection model based on deep learning;
The cable line fault detection model based on deep learning comprises 8 inputs and 2 outputs, wherein the 8 inputs are respectively: cable line current data transmitted over NB-IoT Is a sample of the cable line voltage dataIs a sample of the cabling temperature dataIs a sample of the cable run humidity dataIs a sample of the cable run resistance dataIs a sample of the cable run vibration dataIs a sample of the cable run electric field dataIs a sample of the cabling magnetic field dataThe 2 outputs are respectively: in order for a fault to be present, To be fault-free;
The hidden layer of the deep learning model has n neurons, and each neuron in the hidden layer The outputs of (2) are weighted and calculated by an activation function, and the expressions are shown in (8) - (9):
（19）；
（20）；
Wherein: Is a neuron of an hidden layer of the deep learning model, j is a neuron serial number, the range of values is 1-n, As an activation function of the deep learning model,Is a connection inputAnd neuronsIs used for the weight of the (c),Is a neuronH is the hidden layer output vector of the deep learning model,The input of the deep learning model is that i is the layer number of the deep learning model;
the output of the deep learning model is:
（21）；
Wherein: for the output of the deep learning model, To connect neuronsAnd output ofIs used for the weight of the (c),For outputtingIs included.
The invention further improves that: the expression of the cable line fault detection deep learning model library is as follows:
（22）；
Wherein: a deep learning model for the kth cabling fault detection, In order to train the deep learning model well,And connecting weights from the input layer to the output layer of the trained deep learning model.
The beneficial effects of the invention are as follows: 1) With NB-IoT technology, wider coverage connectivity can be provided while reducing the power consumption of the device, enabling the monitoring system to be deployed over a larger range and run for a longer period of time.
2) The invention supports remote monitoring and management, so that a user can monitor the state of the cable line at any time and any place and timely acquire fault information.
3) Real-time decision making and predictive maintenance are combined with NB-IoT and deep learning, the system can achieve real-time decision making and predictive maintenance, discover and respond to potential problems in time, reduce outage time, and improve reliability of the power system.
Drawings
FIG. 1 is a flow chart of a method in an embodiment of the invention;
fig. 2 is a schematic diagram of a cable line fault detection model based on deep learning in an embodiment of the invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention. In addition, the technical features of the embodiments of the present invention described below may be combined with each other as long as they do not collide with each other.
As shown in fig. 1, a cable fault sensing method of the present embodiment includes the following operations:
And step 1, providing a cable line fault monitoring data acquisition technology. The collected cable line fault monitoring number information comprises current data, voltage data, temperature data, humidity data, resistance data, vibration data, electric field data and magnetic field data of the cable. Current data, abnormal current waveforms in the cable lines, may suggest potential faults, such as short circuits or overloads. Voltage data, which may evaluate the electrical performance of the cabling, may indicate that the cable is problematic due to unstable voltages or voltage fluctuations. Temperature data, abnormal temperature rise may indicate cable overload or other problems. Humidity data, in a humid environment, humidity monitoring is important to prevent insulation problems and corrosion. Resistance data, resistance changes in the cable, including potential short circuits or ground problems, can be detected. Vibration data, mainly detecting abnormal vibrations on the cable lines, may be caused by mechanical problems or external disturbances. Electric and magnetic field data, electric and magnetic field sensors can be used to monitor electric and magnetic field changes in the vicinity of the cable to help identify cable faults.
Step 2, propose the cable line information transmission technology based on NB-IoT. The cable distribution range is wide due to the low probability of cable lines failing. Therefore, the present embodiment adopts NB-IoT wide area low power technology to transmit the cable line fault monitoring data information, and uses QPSK (Quadrature PHASE SHIFT KEYING) technology to modulate and demodulate the cable line fault monitoring data information: QPSK modulation modulates signals mainly on two orthogonal carriers, converts digital data into analog signals, and in modulation, each symbol represents two bits, and has higher data transmission rate; demodulation of QPSK involves a phase demodulator that compares the received signal with a known phase to recover the original binary data. The embodiment utilizes the NB-IoT technology to periodically send the cable line fault monitoring data, reduces the communication energy consumption and the cost, and realizes the effective transmission of the data of the cable line in a large range.
And step 3, providing a cable line fault detection model based on deep learning. Marking the received cable line fault monitoring data according to the presence or absence of faults to form a training sample of a deep learning model; training samples by using a deep learning model, including forward propagation and reverse propagation training processes, minimizing prediction errors of the deep learning model by adjusting weights and biases of a neural network, evaluating performance of the deep learning model by using an independent test data set, ensuring that the deep learning model can accurately classify normal conditions and various fault conditions, and finally training to form a cable line fault detection model based on deep learning. The data under the environments such as temperature and humidity, electromagnetic fields and the like are not used, a cable line fault detection deep learning model library under different environments can be obtained, and effective detection of cable line faults under different environments is realized.
And 4, providing a cable line fault monitoring model. And in the online monitoring stage of the cable line fault, updating the cable line fault detection deep learning model library into a cable line fault monitoring system. And the collected field data is transmitted to a monitoring system based on NB-IoT, the monitoring system inputs the data into a fault detection deep learning model library for analysis, and once a fault is found, an alarm is sent out to realize the online monitoring of the fault of each cable line.
In step 1, the information expression of the collected cable line fault monitoring data is as follows:
（1）；
In the method, in the process of the invention, For the cable line fault monitoring data at time t,For the cabling current data at time t,For the cable line voltage data at time t,Is the temperature data of the cable line at the time t,The humidity data of the cable circuit at the moment t,The data of the resistance of the cable line at the time t,The vibration data of the cable line at the moment t,For the cable line electric field data at time t,And the magnetic field data of the cable line at the time t.
In step 2, the proposed NB-IoT-based cable line information transmission technology is shown in formulas (2) - (6), and mainly includes the processes of QPSK modulation and demodulation of cable line data. Taking cable line electric field data as an example, taking (2) as a modulation process function of the cable line electric field data, and collecting the cable line electric field dataModulating, wherein the modulated electric field data is that. NB-IoT transmission of modulated electric field dataThe noise received in the transmission process isIs the effect of the received cable line electric field data at the receiving endAs shown in formula (3). The NB-IoT receiver demodulates the received electric field information as shown in equations (4) - (6). First, the received signal is processedThe method comprises the steps of dividing the filter into a sine component and a cosine component, and carrying out low-pass filtering treatment, wherein the sine component and the cosine component after the treatment are respectively、. Finally, the demodulated signal is mapped back to the original binary data according to equation (6). According to the principle, other information in the formula (1) is processed, and finally information transmitted through NB-IoT is shown in the formula (7).
（2）；
（3）；
（4）；
（5）；
（6）；
（7）；
Wherein: For the modulated cable line electric field data at time t, For the cable line electric field data at time t,The electric field signal frequency of the cable line at the time t,For the electric field phase angle of the cable line at the time t,For the receiving end to receive the electric field data of the cable line at the time t,For the noise experienced in NB-IoT transmission signals,、The lowpass { } function represents low-pass filtering for extracting baseband signal components in the function, the arg () function represents finding the largest sine and cosine components,For the cable line fault monitoring data after transmission over NB-IoT,For the cable line current data transmitted over NB-IoT,For the cable line voltage data transmitted over NB-IoT,For the cabling temperature data after transmission over NB-IoT,For the cabling wetness data after transmission over NB-IoT,For the cabling resistance data after transmission over NB-IoT,For the cabling vibration data after transmission over NB-IoT,For the cable line electric field data after transmission over NB-IoT,Is the cabling magnetic field data after being transmitted through the NB-IoT.
In step 3, a cable line fault detection model based on deep learning is shown in fig. 2, and cable line fault characteristics under different environments are extracted through deep learning of fault samples of the cable line, so that accurate identification of cable faults under different environments is realized.
The cable line fault detection model based on deep learning comprises 8 inputs and 2 outputs, wherein the 8 inputs are respectively: cable line current data transmitted over NB-IoTIs a sample of the cable line voltage dataIs a sample of the cabling temperature dataIs a sample of the cable run humidity dataIs a sample of the cable run resistance dataIs a sample of the cable run vibration dataIs a sample of the cable run electric field dataIs a sample of the cabling magnetic field dataThe 2 outputs are respectively: in order for a fault to be present, To be fault-free;
The hidden layer of the deep learning model has n neurons, and each neuron in the hidden layer The outputs of (2) are calculated by weighting and through an activation function, and the expressions are shown in (8) - (9):
（8）；
（9）；
Wherein: Is a neuron of an hidden layer of the deep learning model, j is a neuron serial number, the range of values is 1-n, As an activation function of the deep learning model,Is a connection inputAnd neuronsIs used for the weight of the (c),Is a neuronH is the hidden layer output vector of the deep learning model,The input of the deep learning model is that i is the layer number of the deep learning model;
the output of the deep learning model is:
（10）；
Wherein: for the output of the deep learning model, To connect neuronsAnd output ofIs used for the weight of the (c),For outputtingIs included.
In step 4, extracting a connection weight and a threshold value from a cable line fault detection model based on deep learning, and constructing a cable line fault detection deep learning model library, wherein the expression of the cable line fault detection deep learning model library is as follows:
（11）；
Wherein: a deep learning model for the kth cabling fault detection, In order to train the deep learning model well,And connecting weights from the input layer to the output layer of the trained deep learning model.
And updating the cable line fault detection deep learning model library to periodically update the cable line fault detection deep learning model library to a cable line fault monitoring system, analyzing cable line data based on NB-IoT online transmission, and realizing effective monitoring of cable line faults in different environments.
The cable line fault monitoring model based on NB-IoT and deep learning constructed by the invention has low communication power consumption and wide monitoring range, and can be suitable for effectively monitoring cable line faults in an unused environment.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus, systems, computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
While the foregoing is directed to embodiments of the present invention, other and further details of the invention may be had by the present invention, it should be understood that the foregoing description is merely illustrative of the present invention and that no limitations are intended to the scope of the invention, except insofar as modifications, equivalents, improvements or modifications are within the spirit and principles of the invention.
Claims (6)
1. A cable fault sensing method is characterized in that: comprising the following operations:
Collecting fault monitoring data information of a cable line, wherein the fault monitoring data information comprises current data, voltage data, temperature data, humidity data, resistance data, vibration data, electric field data and magnetic field data of the cable;
Transmitting the cable line fault monitoring data information by utilizing an NB-IoT technology, including modulating and demodulating the cable line fault monitoring data information by utilizing a QPSK technology;
constructing a cable line fault detection model based on deep learning;
Extracting a connection weight and a threshold value from a cable line fault detection model based on deep learning, constructing a cable line fault detection deep learning model library, updating the cable line fault detection deep learning model library into a cable line fault monitoring system, and transmitting collected field data into the cable line fault monitoring system based on NB-IoT for online monitoring of cable line faults;
The transmission of the cable line fault monitoring data information by using the NB-IoT technology comprises the modulation and demodulation of the cable line fault monitoring data information by using the QPSK technology, and specifically comprises the following operations: modulating the collected cable line fault monitoring data information, wherein the NB-IoT transmits the modulated cable line fault monitoring data information, a receiving end of the NB-IoT demodulates the received cable line fault monitoring data information, the following formulas (2) - (6) are cable line electric field data NB-IoT transmission processing procedures, and the formula (7) is cable line fault monitoring data information obtained through NB-IoT transmission:
（2）；
（3）；
（4）；
（5）；
（6）；
（7）；
Wherein: For the modulated cable line electric field data at time t, For the cable line electric field data at time t,The electric field signal frequency of the cable line at the time t,For the electric field phase angle of the cable line at the time t,For the receiving end to receive the electric field data of the cable line at the time t,For the noise experienced in NB-IoT transmission signals,、The sine component and the cosine component after the low-pass filtering process respectively, the lowpass { } function represents low-pass filtering for extracting the baseband signal component in the function, the arg () function represents finding the largest sine and cosine component,For the cable line fault monitoring data after transmission over NB-IoT,For the cable line current data transmitted over NB-IoT,For the cable line voltage data transmitted over NB-IoT,For the cabling temperature data after transmission over NB-IoT,For the cabling wetness data after transmission over NB-IoT,For the cabling resistance data after transmission over NB-IoT,For the cabling vibration data after transmission over NB-IoT,For the cable line electric field data after transmission over NB-IoT,Cable line magnetic field data transmitted through NB-IoT;
the construction of the cable line fault detection model based on deep learning specifically comprises the following operations:
Marking the received cable line fault monitoring data to form a training sample of the deep learning model; training a sample by using a deep learning model, wherein the training comprises forward propagation and reverse propagation training processes, the prediction error of the deep learning model is minimized by adjusting the weight and the bias of a neural network, the performance of the deep learning model is estimated by using an independent test data set, and the final training forms a cable line fault detection model based on deep learning;
The cable line fault detection model based on deep learning comprises 8 inputs and 2 outputs, wherein the 8 inputs are respectively: cable line current data transmitted over NB-IoT Is a sample of the cable line voltage dataIs a sample of the cabling temperature dataIs a sample of the cable run humidity dataIs a sample of the cable run resistance dataIs a sample of the cable run vibration dataIs a sample of the cable run electric field dataIs a sample of the cabling magnetic field dataThe 2 outputs are respectively: in order for a fault to be present, To be fault-free;
The hidden layer of the deep learning model is provided with n neurons, and the neurons in the hidden layer The outputs of (2) are weighted and calculated by an activation function, and the expressions are shown in (8) - (9):
（8）；
（9）；
Wherein: Is a neuron of an hidden layer of the deep learning model, j is a neuron serial number, the range of values is 1-n, As an activation function of the deep learning model,Is a connection inputAnd neuronsIs used for the weight of the (c),Is a neuronH is the hidden layer output vector of the deep learning model,The input of the deep learning model is that i is the layer number of the deep learning model;
the output of the deep learning model is:
（10）；
Wherein: for the output of the deep learning model, To connect neuronsAnd output ofIs used for the weight of the (c),For outputtingIs included.
2. A method of cable fault sensing according to claim 1, wherein: the collected cable line fault monitoring data information expression is as follows:
（1）；
In the method, in the process of the invention, For the cable line fault monitoring data at time t,For the cabling current data at time t,For the cable line voltage data at time t,Is the temperature data of the cable line at the time t,The humidity data of the cable circuit at the moment t,The data of the resistance of the cable line at the time t,The vibration data of the cable line at the moment t,For the cable line electric field data at time t,And the magnetic field data of the cable line at the time t.
3. A method of cable fault sensing according to claim 1, wherein: the expression of the cable line fault detection deep learning model library is as follows:
（11）；
Wherein: a deep learning model for the kth cabling fault detection, In order to train the deep learning model well,And connecting weights from the input layer to the output layer of the trained deep learning model.
4. The utility model provides a cable fault perception system which characterized in that: the system comprises an acquisition module, an NB-IoT transmission module, a model construction module, a model library construction and update module and an alarm module;
The acquisition module is used for acquiring fault monitoring data information of the cable line, including current data, voltage data, temperature data, humidity data, resistance data, vibration data, electric field data and magnetic field data of the cable;
The NB-IoT transmission module is configured to transmit cable line fault monitoring data information, and includes performing modulation and demodulation of the cable line fault monitoring data information by using a QPSK technology;
the model construction module is used for constructing a cable line fault detection model based on deep learning;
The model library constructing and updating module is used for extracting a connection weight and a threshold value from a cable line fault detection model based on deep learning, constructing a cable line fault detection deep learning model library, and updating the cable line fault detection deep learning model library into a cable line fault monitoring system;
The alarm module is used for giving an alarm when the cable line fault monitoring system detects a fault;
The NB-IoT transmission module includes the following operations: modulating the collected cable line fault monitoring data information, transmitting the modulated cable line fault monitoring data information by using an NB-IoT technology, demodulating the received cable line fault monitoring data information by using a receiving end of the NB-IoT technology, wherein the following formulas (13) - (17) are cable line electric field data NB-IoT transmission processing procedures, and the formula (18) is cable line fault monitoring data information obtained through NB-IoT transmission:
（13）；
（14）；
（15）；
（16）；
（17）；
（18）；
Wherein: For the modulated cable line electric field data at time t, For the cable line electric field data at time t,The electric field signal frequency of the cable line at the time t,For the electric field phase angle of the cable line at the time t,For the receiving end to receive the electric field data of the cable line at the time t,For the noise experienced in NB-IoT transmission signals,、The sine component and the cosine component after the low-pass filtering process respectively, the lowpass { } function represents low-pass filtering for extracting the baseband signal component in the function, the arg () function represents finding the largest sine and cosine component,For the cable line fault monitoring data after transmission over NB-IoT,For the cable line current data transmitted over NB-IoT,For the cable line voltage data transmitted over NB-IoT,For the cabling temperature data after transmission over NB-IoT,For the cabling wetness data after transmission over NB-IoT,For the cabling resistance data after transmission over NB-IoT,For the cabling vibration data after transmission over NB-IoT,For the cable line electric field data after transmission over NB-IoT,Cable line magnetic field data transmitted through NB-IoT;
the construction of the cable line fault detection model based on deep learning specifically comprises the following operations:
Marking the received cable line fault monitoring data to form a training sample of the deep learning model; training a sample by using a deep learning model, wherein the training comprises forward propagation and reverse propagation training processes, the prediction error of the deep learning model is minimized by adjusting the weight and the bias of a neural network, the performance of the deep learning model is estimated by using an independent test data set, and the final training forms a cable line fault detection model based on deep learning;
The cable line fault detection model based on deep learning comprises 8 inputs and 2 outputs, wherein the 8 inputs are respectively: cable line current data transmitted over NB-IoT Is a sample of the cable line voltage dataIs a sample of the cabling temperature dataIs a sample of the cable run humidity dataIs a sample of the cable run resistance dataIs a sample of the cable run vibration dataIs a sample of the cable run electric field dataIs a sample of the cabling magnetic field dataThe 2 outputs are respectively: in order for a fault to be present, To be fault-free;
The hidden layer of the deep learning model is provided with n neurons, and the neurons in the hidden layer The outputs of (2) are weighted and calculated by an activation function, and the expressions are shown in (8) - (9):
（19）；
（20）；
Wherein: Is a neuron of an hidden layer of the deep learning model, j is a neuron serial number, the range of values is 1-n, As an activation function of the deep learning model,Is a connection inputAnd neuronsIs used for the weight of the (c),Is a neuronH is the hidden layer output vector of the deep learning model,The input of the deep learning model is that i is the layer number of the deep learning model;
the output of the deep learning model is:
（21）；
Wherein: for the output of the deep learning model, To connect neuronsAnd output ofIs used for the weight of the (c),For outputtingIs included.
5. A cable fault sensing system according to claim 4, wherein: the collected cable line fault monitoring data information expression is as follows:
（12）；
In the method, in the process of the invention, For the cable line fault monitoring data at time t,For the cabling current data at time t,For the cable line voltage data at time t,Is the temperature data of the cable line at the time t,The humidity data of the cable circuit at the moment t,The data of the resistance of the cable line at the time t,The vibration data of the cable line at the moment t,For the cable line electric field data at time t,And the magnetic field data of the cable line at the time t.
6. A cable fault sensing system according to claim 4, wherein: the expression of the cable line fault detection deep learning model library is as follows:
（22）；
Wherein: a deep learning model for the kth cabling fault detection, In order to train the deep learning model well,And connecting weights from the input layer to the output layer of the trained deep learning model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410510585.5A CN118091331B (en) | 2024-04-26 | 2024-04-26 | Cable fault sensing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410510585.5A CN118091331B (en) | 2024-04-26 | 2024-04-26 | Cable fault sensing method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118091331A CN118091331A (en) | 2024-05-28 |
| CN118091331B true CN118091331B (en) | 2024-07-05 |
Family
ID=91155243
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410510585.5A Active CN118091331B (en) | 2024-04-26 | 2024-04-26 | Cable fault sensing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118091331B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110412411A (en) * | 2018-04-28 | 2019-11-05 | 蒲芳芳 | Artificial neural network system's failure cable position distance measuring method based on Internet of Things |
| AU2020103212A4 (en) * | 2020-11-04 | 2021-01-14 | Azam, Farooque MR | IoT AND MACHINE LEARNING-BASED POWER DISTRIBUTION MANAGEMENT SYSTEM |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210266875A1 (en) * | 2020-02-24 | 2021-08-26 | Qualcomm Incorporated | MACHINE LEARNING FOR ADDRESSING TRANSMIT (Tx) NON-LINEARITY |
| CN114611705A (en) * | 2020-11-23 | 2022-06-10 | 华为技术有限公司 | Data processing method, training method for machine learning, and related device and equipment |
| CN112734698B (en) * | 2020-12-24 | 2024-07-09 | 国网北京市电力公司 | Cable terminal abnormality diagnosis method and device based on infrared image |
| CN113364115B (en) * | 2021-04-25 | 2023-07-28 | 西安电子科技大学 | Power cable information comprehensive processing system and method |
| CN113379033A (en) * | 2021-06-11 | 2021-09-10 | 国网湖北省电力有限公司黄石供电公司 | Cable health state intelligent early warning method based on time-space network enhanced deep learning |
| US11892898B2 (en) * | 2021-08-09 | 2024-02-06 | Nvidia Corporation | Movement data for failure identification |
| JP7471339B2 (en) * | 2021-09-17 | 2024-04-19 | 株式会社プロテリアル | Cable Status Management System |
| CN116027158A (en) * | 2023-02-07 | 2023-04-28 | 国网辽宁省电力有限公司电力科学研究院 | High-voltage cable partial discharge fault prediction method and system |
| CN117708669A (en) * | 2023-12-14 | 2024-03-15 | 国网湖北省电力有限公司武汉供电公司 | Multi-source data-based adaptive probability neural network high-voltage cable state evaluation method |
-
2024
- 2024-04-26 CN CN202410510585.5A patent/CN118091331B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110412411A (en) * | 2018-04-28 | 2019-11-05 | 蒲芳芳 | Artificial neural network system's failure cable position distance measuring method based on Internet of Things |
| AU2020103212A4 (en) * | 2020-11-04 | 2021-01-14 | Azam, Farooque MR | IoT AND MACHINE LEARNING-BASED POWER DISTRIBUTION MANAGEMENT SYSTEM |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118091331A (en) | 2024-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101561081B (en) | Method for detecting and positioning leakage of oil-gas pipeline by utilizing autonomous navigation robot | |
| CN102436524B (en) | Fuzzy reasoning method for soft fault diagnosis for analog circuit | |
| CN109347579B (en) | Weak signal detection method under uncertain wireless channel fading condition | |
| CN111351567A (en) | Ship equipment vibration state monitoring device and method based on acceleration sensor | |
| CN113671361A (en) | High-voltage circuit breaker characteristic parameter prediction method and system based on multi-source signal fusion | |
| CN117406137B (en) | Method and system for monitoring lightning leakage current of power transmission line | |
| CN212513308U (en) | Vibration alarm device for water transport tool | |
| Huo et al. | Power Line Communication and Sensing Using Time Series Forecasting | |
| CN112949487A (en) | WiFi-based ship cab personnel number detection method and system | |
| JP2002090412A (en) | Partial-discharge measuring apparatus | |
| CN118091331B (en) | Cable fault sensing method and system | |
| CN110673000A (en) | Online monitoring method and device for partial discharge of oil-immersed current transformer | |
| CN113946920A (en) | Rolling bearing fault diagnosis method with unbalanced data and data set deviation | |
| CN201752138U (en) | Fault point diagnosing and positioning system for indoor wireless network | |
| CN104734793A (en) | Energy detection method based on p-power wireless cooperative spectrum sensing | |
| CN103078687A (en) | Train-mounted responder transmission unit wireless link interference monitoring device | |
| Ibrahim Gabr et al. | Hybrid detection algorithm for online faulty sensors identification in wireless sensor networks | |
| CN201229301Y (en) | Smoke detecting device | |
| CN108055096A (en) | The frequency spectrum sensing method detected based on signal and noise characteristic | |
| CN111257629A (en) | Portable new energy station power characteristic detection method, device and system | |
| CN113590413B (en) | UNIX server, and UNIX server fault early warning method and device | |
| CN116660688B (en) | Remote power line fault early warning and monitoring system and method | |
| CN117033983B (en) | Unmanned ship self-noise detection and identification method and system | |
| CN203104459U (en) | Wireless link interference monitoring device for train-mounted responder transmission unit | |
| CN208818252U (en) | Equipment state detection apparatus and system |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |