CN112462212A - Artificial intelligent partial discharge monitoring and distinguishing system and method based on cloud technology - Google Patents
Artificial intelligent partial discharge monitoring and distinguishing system and method based on cloud technology Download PDFInfo
- Publication number
- CN112462212A CN112462212A CN202011322977.7A CN202011322977A CN112462212A CN 112462212 A CN112462212 A CN 112462212A CN 202011322977 A CN202011322977 A CN 202011322977A CN 112462212 A CN112462212 A CN 112462212A
- Authority
- CN
- China
- Prior art keywords
- data
- partial discharge
- test
- cloud
- acquiring
- 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/12—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing
- G01R31/1227—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials
- G01R31/1263—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials of solid or fluid materials, e.g. insulation films, bulk material; of semiconductors or LV electronic components or parts; of cable, line or wire insulation
- G01R31/1272—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials of solid or fluid materials, e.g. insulation films, bulk material; of semiconductors or LV electronic components or parts; of cable, line or wire insulation of cable, line or wire insulation, e.g. using partial discharge measurements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/02—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP]
- H04L67/025—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP] for remote control or remote monitoring of applications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/06—Protocols specially adapted for file transfer, e.g. file transfer protocol [FTP]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
- H04W12/06—Authentication
Abstract
The invention provides an artificial intelligence partial discharge real-time monitoring and distinguishing method based on a cloud technology, which comprises the following steps of: s1, detecting partial discharge signals on the cable line in real time through a partial discharge sensor; s2, the local discharge local signal processing device acquires local discharge signals and processes the local discharge signals to form intermediate data; s3, obtaining the intermediate data through the cloud server, carrying out safety processing to form test data, and then carrying out storage analysis; and S4, acquiring and displaying the test data through the intelligent terminal. The method comprises the partial discharge sensor, the partial discharge local signal processing device, the cloud server and the intelligent terminal. The invention realizes the sharing of test data based on the cloud technology and the wireless transmission technology, partial discharge test experts in different areas can remotely support and judge partial discharge at any time, and the requirement on test personnel is not high.
Description
Technical Field
The invention relates to the technical field of partial discharge testing, in particular to an artificial intelligent partial discharge monitoring and distinguishing system and method based on a cloud technology.
Background
During the partial discharge test, because the measuring point area of the cable line is widely distributed, a movable detection method is often needed, the workload of workers is large, and because the partial discharge test experts are few and the difficulty in training the partial discharge testers is large, the professional partial discharge testers are insufficient, meanwhile, the test time of the test site is limited, the instantaneous reaction and the timely judgment of the testers are often needed, and the possibility of the reduction of the test quality and the erroneous judgment can be caused due to the insufficient professional knowledge of the testers. And for huge partial discharge data (2000 Mbps per second), it is difficult to transmit data resources to the company headquarters in time, so that experts in other areas are difficult to support on-site partial discharge diagnosis, and the accuracy and efficiency of partial discharge live detection are low. Meanwhile, in the field test process, only test data can be recorded, and huge test data cannot be used for sample learning comparison of partial discharge tests.
Meanwhile, in recent years, although some partial discharge detection devices have implemented wireless transmission of test data, for example, chinese patent CN104459487A discloses an "implementation method of a partial discharge real-time monitoring system based on 3G communication", which can remotely detect and monitor partial discharge signals of a plurality of remote cable terminals in real time, but because the existing partial discharge test data is large, it cannot transmit the detection large data to the background in time to share the detection data with testers or experts; in addition, most of the prior art methods use a public network for plaintext transmission, so that great hidden danger exists in the aspect of safety; and the data transmission by using the secure encryption mode is attempted, but the problems of dead halt, unsuccessful transmission of the partially amplified data, data decryption error, secure authentication and key error exist, and the like, which also causes that the partially amplified test work cannot be normally performed. In addition, as the number of times of comparison calculation increases with the increase of the automatic number of the partial discharge data discrimination databases, a problem occurs in that the calculation time increases to affect the calculation performance.
Disclosure of Invention
The invention provides an artificial intelligent partial discharge monitoring and judging system and method based on cloud technology, aiming at overcoming the problem that the existing partial discharge test data is large and the detection data cannot be transmitted to the background and shared with testers or experts in time. The invention realizes the sharing of test big data based on the cloud technology and the wireless transmission technology, partial discharge test experts in different areas can remotely support and judge partial discharge at any time, and the requirement on test personnel is not high.
In order to solve the technical problems, the invention adopts the technical scheme that: an artificial intelligence partial discharge real-time monitoring and distinguishing method based on a cloud technology comprises the following steps:
s1, detecting partial discharge signals on the cable line in real time through a partial discharge sensor;
s2, a local discharge local signal processing device connected with the local discharge sensor acquires the local discharge signal and processes the local discharge signal to form intermediate data;
s3, acquiring the intermediate data through a cloud server in wireless communication connection with the local discharge local signal processing device, performing safety processing on the intermediate data to form test data, and then storing and analyzing the test data;
and S4, acquiring and displaying the test data through an intelligent terminal in wireless communication connection with the cloud server.
The partial discharge local signal processing device comprises:
the 100Msps ADC sampling module is connected with the partial discharge sensor and used for acquiring the partial discharge signal;
the processor module is connected with the 100MspsADC sampling module and is used for sequentially amplifying, filtering, detecting and carrying out analog-to-digital conversion on the partial discharge signal to form initial data;
and the wireless module is connected with the processor module and is used for acquiring the initial data, carrying out security authentication and encryption and decryption processing on the initial data, forming the intermediate data and then wirelessly transmitting the intermediate data to the cloud server.
The wireless module includes:
the encryption and decryption security chip is used for acquiring the initial data and encrypting the initial data to form the intermediate data;
MT7688 intelligent routing for wirelessly transmitting the intermediate data to the cloud server.
Further, in order to record only the test data and not use the huge test data for the sample learning comparison problem of the partial discharge test, the cloud server includes:
the local discharge application module is used for acquiring intermediate data transmitted by the local discharge signal device, automatically storing, automatically preprocessing, automatically calculating and judging the intermediate data to obtain test data, and wirelessly transmitting the test data to the intelligent terminal;
and the AI model training module is used for training and learning the test data, enabling the test data to become a new comparison sample, and updating the comparison sample in a sample library for standby in the next partial discharge test.
Further, in order to securely transmit data to the background, the encryption/decryption security chip needs to perform key agreement before the encryption process, and the key agreement includes:
s21, the first unit generates a random number r1 as:
a | ESkey1(H (r1)) of ECert2(r1), sending a to the second unit;
s22, the second unit decrypts A and verifies the signature of the first unit to generate a random number r2, which is: b ═ ECert1(r2) | ESkey2(H (r2)), sending B to the first unit;
safety protection of collection terminal
Synthesizing a session key: DK r1 ≦ r 2;
s23, the first unit decrypts B and verifies the signature of the second unit, and the following steps are carried out:
synthesizing a session key: DK r1 ≦ r2,
c ═ H (r1 ≦ r2), send C to the second unit;
the second unit is D ═ H (r1 ^ r2), and whether C is the same as D is compared;
if the two parties are the same, the identities of the two authenticated parties at the moment are verified, and the two authenticated parties hold a session key: DK r1 ≦ r 2; if the two units are different, the second unit gives out the warning information of negotiation failure, informs the first unit, and the first unit initiates the negotiation again.
Further, the encrypting step includes:
s31, filling 1-16 bytes in the data message of the initial data to enable the length of the data message to be multiple of 16, wherein the first byte filled is 0x80, and the content of the subsequent filling bytes is 0x 0; attaching header information and an initial vector IV of the encrypted message, wherein the IV is a 16-byte random number randomly generated by an encryption side;
and S32, encrypting the filled original message and the filled message by using the negotiated session key DK.
Furthermore, in order to solve the problem that the encryption and decryption security chip involved in the 4G/5G wireless module occasionally crashes at 224+ n × 256(0 ≦ n ≦ 7) bytes, the wireless module artificially adds 2 bytes of "0 x 80" and "0 x 00" at the end of the initial data and then encrypts the initial data.
Further, in order to solve the problem that the partially amplified data cannot be transmitted, the wireless module compresses the initial data into a data stream by using an LZO lossless decompression algorithm before encryption, and then divides the data stream into data blocks of 2048 bytes or less.
Further, in order to solve the problem that as the number of times of comparison calculation increases with the increase of the partial discharge data discriminators, the calculation time increases and the calculation performance is affected, the storage analysis of the cloud server includes the following steps:
s41, making a data discrimination library;
s42, data storage: calculating the characteristic value of the acquired data, comparing the characteristic value with each sample in a data discrimination library, and taking the library result value with the maximum similarity as the result value of the data; if the maximum similarity of the data is lower than a set threshold, automatically marking the data and adding the data into the data discrimination library as a sample;
s43, data analysis: and calculating the characteristic value of the data, generating a corresponding and unique data mark value while generating the characteristic value, comparing the sizes of the characteristic values and sequencing according to the sizes, wherein the different types of data mark values are different.
After the characteristic value of the data obtained by the cloud server is calculated, a data mark value is obtained at the same time, a database result value with the maximum similarity is quickly positioned by using a dichotomy search algorithm, the time for comparison calculation is shortened, and the comparison times are not different by 7 times even for millions and millions of data discrimination databases. Thus, although the number of data discrimination libraries is increased automatically, the calculation time is not increased, and the performance of the calculated data is not affected.
The artificial intelligence partial discharge real-time monitoring and distinguishing method based on the cloud technology comprises the following steps:
the partial discharge sensor is used for detecting a partial discharge signal on a cable line;
the partial discharge local signal processing device is connected with the partial discharge sensor and used for acquiring the partial discharge signal and processing the partial discharge signal to form intermediate data;
the cloud server is in wireless communication connection with the local discharge local signal processing device and is used for acquiring the intermediate data, carrying out safety processing on the intermediate data to form test data and then storing and analyzing the test data;
and the intelligent terminal is in wireless communication connection with the cloud server and is used for acquiring and displaying the test data.
Compared with the prior art, the beneficial effects are:
1. the invention realizes the sharing of test data based on the cloud technology and the wireless transmission technology, partial discharge test experts in different areas can remotely support and judge partial discharge at any time, and the requirement on test personnel is not high; and the data are classified and identified by the 4G/5G wireless module and various algorithm programs, and effective and useful data are packed, compressed and transmitted to the cloud server for testing big data sharing.
2. The invention carries out safety certification and encryption and decryption on the local test data, and ensures the safety transmission of the test data; based on various algorithms and programs, the problems of crash, incapability of transmitting big data, wrong encryption and decryption, incapability of passing safety certification and the like are solved, and correct and safe transmission of partial discharge test data is guaranteed.
3. Based on the strong storage and computing capability of the cloud technology, the invention not only can run the partial discharge application program, but also can carry the AI model training program, so that the learned sample can be immediately used for judging the partial discharge test; and a large amount of test data can be transmitted to the cloud server for storage, calculation and sample training, and the requirement on testing a computer is not high.
Drawings
FIG. 1 is a schematic view of example 1.
Fig. 2 is a schematic diagram of the local discharge local signal processing apparatus according to the present invention.
Fig. 3 is a flowchart of key agreement in embodiment 1.
Fig. 4 is a schematic flow chart of encryption in embodiment 1.
FIG. 5 is a flow chart illustrating the process of test data storage analysis in implementation 1.
FIG. 6 is a schematic view of example 1 in use.
FIG. 7 is a schematic flow chart of example 1 in use.
Detailed Description
The drawings are for illustrative purposes only and are not to be construed as limiting the patent; for the purpose of better illustrating the embodiments, certain features of the drawings may be omitted, enlarged or reduced, and do not represent the size of an actual product; it will be understood by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted. The positional relationships depicted in the drawings are for illustrative purposes only and are not to be construed as limiting the present patent.
Example 1
The embodiment provides an artificial intelligence partial discharge real-time monitoring and distinguishing method based on a cloud technology, which comprises the following steps:
s1, detecting and transmitting partial discharge signals on the cable line in real time through a partial discharge sensor;
s2, the partial discharge local signal processing device connected with the partial discharge sensor acquires partial discharge signals, processes the partial discharge signals to form intermediate data, and then wirelessly transmits the intermediate data;
s3, acquiring intermediate data through a cloud server in wireless communication connection with the local discharge local signal processing device, performing safety processing on the intermediate data to form test data, and performing storage analysis and wireless transmission on the test data;
and S4, acquiring and displaying the test data through the intelligent terminal in wireless communication connection with the cloud server.
As shown in fig. 2, the partial discharge local signal processing apparatus includes:
the 100Msps ADC sampling module is connected with the partial discharge sensor and used for acquiring a partial discharge signal;
the processor module is connected with the 100MspsADC sampling module and is used for sequentially amplifying, filtering, detecting and carrying out analog-to-digital conversion on the partial discharge signals to form initial data;
and the wireless module is connected with the processor module and used for acquiring the initial data, carrying out security authentication and encryption and decryption processing on the initial data, forming intermediate data and then wirelessly transmitting the intermediate data to the cloud server.
The wireless module is 4G/5G wireless module, and this wireless module includes:
the encryption and decryption security chip is used for acquiring initial data and encrypting the initial data to form intermediate data;
MT7688 intelligent routing, used for wireless transmission of intermediate data to cloud server.
In order to securely transmit data to the background, the encryption and decryption security chip needs to perform key agreement before the encryption process, and the steps of the key agreement are shown in fig. 3 and are summarized as follows:
s21, the first unit generates a random number r1 as:
a | ESkey1(H (r1)) of ECert2(r1), sending a to the second unit;
s22, the second unit decrypts A and verifies the signature of the first unit to generate a random number r2, which is: b ═ ECert1(r2) | ESkey2(H (r2)), sending B to the first unit;
safety protection of collection terminal
Synthesizing a session key: DK r1 ≦ r 2;
s23, the first unit decrypts B and verifies the signature of the second unit, and the following steps are carried out:
synthesizing a session key: DK r1 ≦ r2,
c ═ H (r1 ≦ r2), send C to the second unit;
the second unit is D ═ H (r1 ^ r2), and whether C is the same as D is compared;
if the two parties are the same, the identities of the two authenticated parties at the moment are verified, and the two authenticated parties hold a session key: DK r1 ≦ r 2; if the two units are different, the second unit gives out the warning information of negotiation failure, informs the first unit, and the first unit initiates the negotiation again.
In order to solve the problem that an SPI (serial Peripheral interface) interface of an encryption and decryption security chip and an M7768 router chip which is butted by a router must use a mode 3 of the encryption and decryption security chip, but the problem of random setting or resetting of an 8 th high-order byte occurs during use, so that the encryption and decryption data are wrong; therefore, in the embodiment, the SPI interface of the M7768 routing chip is not adopted in design, but the function of the SPI mode 3 is realized by using a program-simulated GPIO method, so that correct decryption of data is ensured.
The communication interface mode of the security chip has polarity represented as CPOL (clock polarity), phase represented as CPHA (clock phase), and 4 working modes formed by combining the polarity and the phase.
CPOL clock signal level at Idle (1: high level, 0: Low level)
CPHA clock edge sample (1: second edge start, 0: first edge start)
As shown in fig. 4, the step of encrypting includes:
s31, filling 1-16 bytes in the data message of the initial data to enable the length of the data message to be multiple of 16, wherein the first byte filled is 0x80, and the content of the subsequent filling bytes is 0x 0; adding header information and an initial vector IV of the encrypted message, wherein the IV is a 16-byte random number randomly generated by an encryption side;
and S32, encrypting the filled original message and the filled message by using the negotiated session key DK.
And the partial discharge application module in the cloud server is provided with a safety access module for acquiring intermediate data and decrypting the intermediate data. After the partial discharge application module obtains the intermediate data, the intermediate data needs to be decrypted, the decryption process of the intermediate data is the reverse process of encryption, and whether the filling message is correct or not needs to be checked after decryption.
In order to solve the problem that an encryption and decryption security chip related to a 4G/5G wireless module occasionally crashes at 224+ n × 256 (n is more than or equal to 0 and less than or equal to 7) bytes, the wireless module is encrypted after artificially adding 2 bytes of '0 x 80' and '0 x 00' at the end of initial data; after decryption, the tail '0 x 80' and '0 x 00' are removed, so that abnormal dead halt areas are skipped, and correct encryption and decryption of data are guaranteed.
In order to solve the problem that the partially amplified data cannot be transmitted, the wireless module compresses initial data into data flow by using an LZO lossless decompression algorithm before encryption, then divides the data flow into data blocks with the byte number less than or equal to 2048, finally encrypts the data blocks by using a national secret SM1 symmetric encryption algorithm, and then sends the data blocks to the cloud server.
In order to record test data only and not use huge test data for sample learning comparison of partial discharge tests, the cloud server comprises:
the local discharge application module is used for acquiring intermediate data transmitted by the local discharge signal device, performing storage analysis (namely, automatic storage, automatic preprocessing, automatic calculation and judgment) on the intermediate data to obtain test data, and wirelessly transmitting the test data to the intelligent terminal;
and the AI model training module is used for training and learning the test data, enabling the test data to become a new comparison sample, and updating the comparison sample in the sample library for standby in the next partial discharge test.
The embodiment deploys huge storage and calculation of the detection data on the cloud server based on the cloud technology, so that the calculation is faster, more stable and safer, and the requirement for testing a computer is not high. The local discharge application module and the AI model training module of the cloud server are provided with two sets of test programs, namely a local discharge application program and an AI model training program, the local discharge application program is used for local discharge test, signals transmitted by the local signal processing device are automatically stored, automatically preprocessed, automatically calculated and distinguished, and the distinguishing result is wirelessly transmitted to special software of a mobile phone or a tablet personal computer on a test site for viewing; the AI model training program mainly trains and learns test data to become a new comparison sample, improves the judgment accuracy rate of partial discharge, automatically starts the AI model training program after stopping the partial discharge test operation, calls field test data, starts the pretreatment of the sample, marks the processed sample data, marks the partial discharge as 0 and marks the non-partial discharge as 1, finds out sample parameters through training, updates the trained data serving as a new sample in a sample library, and calls the data in the sample library to perform intelligent partial discharge judgment during the partial discharge test.
In this embodiment, in order to solve the problem that as the number of times of comparison calculation increases with the increase of the partial discharge data discriminators, the calculation time increases and the calculation performance is affected, the storage analysis of the cloud server includes the following steps:
s41, making a data discrimination library;
s42, data storage: calculating the characteristic value of the acquired data, comparing the characteristic value with each sample in a data discrimination library, and taking the library result value with the maximum similarity as the result value of the data; if the maximum similarity of the data is lower than a set threshold, automatically marking the data and adding the data into a data discrimination library as a sample;
s43, data analysis: and calculating the characteristic value of the data, generating a corresponding and unique data mark value while generating the characteristic value, comparing the sizes of the characteristic values and sequencing according to the sizes, wherein the different types of data mark values are different.
Data needing to be stored, analyzed and processed in the cloud server needs to be stored, a cloud data analysis process is shown in fig. 5, firstly, a data discriminant is made, then, characteristic value calculation is carried out on the data obtained by the cloud, then, the characteristic value calculation is compared with each sample in the data discriminant, and a library result value with the maximum similarity is taken as a result value of the data. If the maximum similarity is below 60% (the threshold is adjustable), the data is automatically labeled and added to the data discrimination library. The method for calculating the characteristic values of the data needs to be adjusted during cloud data analysis, the characteristic values are generated while a corresponding data mark value is generated, the data mark values of different types are different, namely the data mark values are unique, the characteristic values are compared in size, and sorting is performed according to the size of the data. After the characteristic value of the data obtained by the cloud is calculated, a data mark value is obtained at the same time, a database result value with the maximum similarity is quickly positioned by utilizing a dichotomy search algorithm, the time for comparison calculation is shortened, and the comparison times are not different by 7 times even if the database is a million-level or ten-million-level data discrimination database. Thus, although the number of data discrimination libraries is increased automatically, the calculation time is not increased, and the performance of the calculated data is not affected.
The general working principle of the embodiment is as follows: as shown in fig. 6 and 7, the partial discharge live detection system is constructed, synchronous partial discharge detection can be performed on the intermediate joints and terminals of all cables with cable lines distributed at different positions, and each measuring point comprises a partial discharge sensor, a partial discharge local signal processing device, a cloud server and an expert background diagnosis center. The local discharge sensor is installed on a cable line to collect local discharge signals, the collected local discharge signals are transmitted to the local discharge local signal processing device through the coaxial cable to be processed, processed signal data are transmitted to the cloud server in a 4G/5G wireless transmission mode to be subjected to safe access, data storage, preprocessing and local discharge judgment, and a tablet personal computer for field test can check test data of all measuring points distributed on the cable line in a wireless mode. The remote expert remote control and remote measurement can also be carried out by connecting computers, tablet computers or mobile phones of expert background diagnosis centers distributed in different areas, different provinces and different countries in a wireless mode. And after exiting the field test process, an AI model training program is automatically started to carry out sample training, the AI model training program calls field test data to carry out sample preprocessing, marks the numerical value of the sample, trains out sample parameters, updates a sample library, and calls the sample library to carry out comparison and judgment in the field test process to give a judgment result.
In the embodiment, the data are classified and identified by the 4G/5G wireless module and various algorithm programs, and effective and useful data are packed, compressed and transmitted to the cloud server for test big data sharing; test data sharing is realized based on a cloud technology and a wireless transmission technology, partial discharge test experts in different areas can remotely support and judge partial discharge at any time, and the requirement on test personnel is not high; moreover, the security certification and encryption and decryption are carried out on the test data of the local player, so that the security transmission of the test data is guaranteed; based on various algorithms and programs, the problems of crash, incapability of transmitting big data, wrong encryption and decryption, incapability of passing safety certification and the like are solved, and correct and safe transmission of partial discharge test data is guaranteed. In addition, based on the strong storage and computing capability of the cloud technology, the embodiment not only can run the partial discharge application program, but also can carry the AI model training program, so that the learned sample can be immediately used for judging the partial discharge test; according to the embodiment, a large amount of test data are transmitted to the cloud server for storage, calculation and sample training, and the requirement for testing a computer is not high.
Example 2
The embodiment provides an artificial intelligence partial discharge monitoring and distinguishing system based on a cloud technology, which utilizes the artificial intelligence partial discharge real-time monitoring and distinguishing method in the embodiment 1, and mainly comprises the following steps:
the partial discharge sensor is used for detecting and transmitting partial discharge signals on a cable line;
the local discharge local signal processing device is connected with the local discharge sensor and used for acquiring a local discharge signal, processing the local discharge signal to form intermediate data and then performing wireless transmission on the intermediate data;
the cloud server is in wireless communication connection with the local discharge local signal processing device and is used for acquiring intermediate data, carrying out safety processing on the intermediate data to form test data, and then carrying out storage analysis and wireless transmission on the test data;
and the intelligent terminal is in wireless communication connection with the cloud server and is used for acquiring and displaying the test data.
It should be understood that the above-described embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the claims of the present invention.
Claims (10)
1. An artificial intelligence partial discharge real-time monitoring and distinguishing method based on a cloud technology is characterized by comprising the following steps:
s1, detecting partial discharge signals on the cable line in real time through a partial discharge sensor;
s2, acquiring the partial discharge signal through a partial discharge local signal processing device connected with the partial discharge sensor and processing the partial discharge signal to form intermediate data;
s3, acquiring the intermediate data through a cloud server in wireless communication connection with the local discharge local signal processing device, performing safety processing on the intermediate data to form test data, and then storing and analyzing the test data;
and S4, acquiring and displaying the test data through an intelligent terminal in wireless communication connection with the cloud server.
2. The method for real-time monitoring and distinguishing of the artificial intelligence partial discharge based on the cloud technology according to claim 1, wherein the partial discharge local signal processing device comprises:
the 100Msps ADC sampling module is connected with the partial discharge sensor and used for acquiring the partial discharge signal;
the processor module is connected with the 100MspsADC sampling module and is used for sequentially amplifying, filtering, detecting and carrying out analog-to-digital conversion on the partial discharge signal to form initial data;
and the wireless module is connected with the processor module and is used for acquiring the initial data, carrying out security authentication and encryption and decryption processing on the initial data, forming the intermediate data and then wirelessly transmitting the intermediate data to the cloud server.
3. The cloud-technology-based artificial intelligence partial discharge real-time monitoring and distinguishing method according to claim 2, wherein the wireless module comprises:
the encryption and decryption security chip is used for acquiring the initial data and encrypting the initial data to form the intermediate data;
MT7688 intelligent routing for wirelessly transmitting the intermediate data to the cloud server.
4. The method for real-time monitoring and distinguishing the artificial intelligence partial discharge based on the cloud technology according to claim 1, wherein the cloud server comprises:
the local discharge application module is used for acquiring intermediate data transmitted by the local discharge signal device, storing and analyzing the intermediate data to obtain the test data, and wirelessly transmitting the test data to the intelligent terminal;
and the AI model training module is used for training and learning the test data, enabling the test data to become a new comparison sample, and updating the comparison sample in a sample library for standby in the next partial discharge test.
5. The method for real-time monitoring and distinguishing of the artificial intelligence partial discharge based on the cloud technology according to claim 3, wherein the encryption and decryption security chip further needs to perform key agreement before the encryption process, and the key agreement step includes:
s21, the first unit generates a random number r1 as:
a = ECert2(r 1)/ESkey 1(H (r1)), sending a to the second unit;
s22, the second unit decrypts A and verifies the signature of the first unit to generate a random number r2, which is: b ═ ECert1(r 2)/ESkey 2(H (r2)), sending B to the first unit;
safety protection of collection terminal
Synthesizing a session key: DK r1 ≦ r 2;
s23, the first unit decrypts B and verifies the signature of the second unit, and the following steps are carried out:
synthesizing a session key: DK r1 ≦ r2,
c ═ H (r1 ≦ r2), send C to the second unit;
the second unit is D ═ H (r1 ^ r2), and whether C is the same as D is compared;
if the two parties are the same, the identities of the two authenticated parties at the moment are verified, and the two authenticated parties hold a session key: DK r1 ≦ r 2; if the two units are different, the second unit gives out the warning information of negotiation failure, informs the first unit, and the first unit initiates the negotiation again.
6. The method for real-time monitoring and distinguishing of the artificial intelligence partial discharge based on the cloud technology as claimed in claim 5, wherein the encrypting step comprises:
s31, filling 1-16 bytes in the data message of the initial data to enable the length of the data message to be multiple of 16, wherein the first byte filled is 0x80, and the content of the subsequent filling bytes is 0x 0; attaching header information and an initial vector IV of the encrypted message, wherein the IV is a 16-byte random number randomly generated by an encryption side;
and S32, encrypting the filled original message and the filled message by using the negotiated session key DK.
7. The method for real-time monitoring and distinguishing the artificial intelligence partial discharge based on the cloud technology as claimed in claim 6, wherein the wireless module encrypts the initial data after artificially adding 2 bytes of "0 x 80" and "0 x 00" at the end of the initial data.
8. The method for real-time monitoring and distinguishing the artificial intelligence partial discharge based on the cloud technology of claim 7, wherein the wireless module compresses the initial data into a data stream by using an LZO lossless decompression algorithm before encryption, and then divides the data stream into data blocks of 2048 bytes or less.
9. The method for real-time monitoring and distinguishing the artificial intelligence partial discharge based on the cloud technology according to claim 1, wherein the storage analysis of the cloud server comprises the following steps:
s41, making a data discrimination library;
s42, data storage: calculating the characteristic value of the acquired data, comparing the characteristic value with each sample in a data discrimination library, and taking the library result value with the maximum similarity as the result value of the data; if the maximum similarity of the data is lower than a set threshold, automatically marking the data and adding the data into the data discrimination library as a sample;
s43, data analysis: and calculating the characteristic value of the data, generating a corresponding and unique data mark value while generating the characteristic value, comparing the sizes of the characteristic values and sequencing according to the sizes, wherein the different types of data mark values are different.
10. The utility model provides an artificial intelligence partial discharge monitoring discrimination system based on cloud, its characterized in that includes:
the partial discharge sensor is used for detecting a partial discharge signal on a cable line;
the partial discharge local signal processing device is connected with the partial discharge sensor and used for acquiring the partial discharge signal and processing the partial discharge signal to form intermediate data;
the cloud server is in wireless communication connection with the local discharge local signal processing device and is used for acquiring the intermediate data, carrying out safety processing on the intermediate data to form test data and then storing and analyzing the test data;
and the intelligent terminal is in wireless communication connection with the cloud server and is used for acquiring and displaying the test data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011322977.7A CN112462212A (en) | 2020-11-23 | 2020-11-23 | Artificial intelligent partial discharge monitoring and distinguishing system and method based on cloud technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011322977.7A CN112462212A (en) | 2020-11-23 | 2020-11-23 | Artificial intelligent partial discharge monitoring and distinguishing system and method based on cloud technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112462212A true CN112462212A (en) | 2021-03-09 |
Family
ID=74799968
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011322977.7A Pending CN112462212A (en) | 2020-11-23 | 2020-11-23 | Artificial intelligent partial discharge monitoring and distinguishing system and method based on cloud technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112462212A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113301147A (en) * | 2021-05-21 | 2021-08-24 | 广东电网有限责任公司 | Partial discharge data processing system based on data transmission |
| CN114006787A (en) * | 2021-12-31 | 2022-02-01 | 山东产研鲲云人工智能研究院有限公司 | Data transmission method, device and computer readable storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102298107A (en) * | 2011-05-20 | 2011-12-28 | 华南理工大学 | Portable ultrasonic wave and cloud detection apparatus for partial discharge |
| CN205647589U (en) * | 2015-11-19 | 2016-10-12 | 国网新疆电力公司电力科学研究院 | Data on -line measuring network architecture is put in office based on ethernet and cloud |
| CN108335468A (en) * | 2017-12-12 | 2018-07-27 | 中科（深圳）能源物联网有限公司 | A kind of cable monitoring system |
| CN108693454A (en) * | 2018-05-22 | 2018-10-23 | 南京中高知识产权股份有限公司 | A kind of GIS partial discharges monitoring system and its working method |
| CN110753344A (en) * | 2019-11-04 | 2020-02-04 | 信联科技(南京)有限公司 | NB-IoT-based smart meter secure access system |
| CN111811666A (en) * | 2020-08-12 | 2020-10-23 | 广东电网有限责任公司广州供电局 | Electric power Internet of things infrared switch temperature measurement method and device |
-
2020
- 2020-11-23 CN CN202011322977.7A patent/CN112462212A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102298107A (en) * | 2011-05-20 | 2011-12-28 | 华南理工大学 | Portable ultrasonic wave and cloud detection apparatus for partial discharge |
| CN205647589U (en) * | 2015-11-19 | 2016-10-12 | 国网新疆电力公司电力科学研究院 | Data on -line measuring network architecture is put in office based on ethernet and cloud |
| CN108335468A (en) * | 2017-12-12 | 2018-07-27 | 中科（深圳）能源物联网有限公司 | A kind of cable monitoring system |
| CN108693454A (en) * | 2018-05-22 | 2018-10-23 | 南京中高知识产权股份有限公司 | A kind of GIS partial discharges monitoring system and its working method |
| CN110753344A (en) * | 2019-11-04 | 2020-02-04 | 信联科技(南京)有限公司 | NB-IoT-based smart meter secure access system |
| CN111811666A (en) * | 2020-08-12 | 2020-10-23 | 广东电网有限责任公司广州供电局 | Electric power Internet of things infrared switch temperature measurement method and device |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113301147A (en) * | 2021-05-21 | 2021-08-24 | 广东电网有限责任公司 | Partial discharge data processing system based on data transmission |
| CN114006787A (en) * | 2021-12-31 | 2022-02-01 | 山东产研鲲云人工智能研究院有限公司 | Data transmission method, device and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112462212A (en) | Artificial intelligent partial discharge monitoring and distinguishing system and method based on cloud technology | |
| CN109982037A (en) | Intelligent patrol detection device | |
| CN112688822B (en) | Edge computing fault or security threat monitoring system and method based on multi-point cooperation | |
| CN112804348B (en) | Method for judging repeatability of reported data of edge computing node by cloud monitoring center | |
| CN105786702A (en) | Computer software analysis system | |
| WO2024002160A1 (en) | Data processing method and apparatus, and electronic device and storage medium | |
| CN111245783A (en) | Isolated environment data transmission device and method based on digital encryption technology | |
| CN112149551A (en) | Safety helmet identification method based on embedded equipment and deep learning | |
| CN111416960B (en) | Video monitoring system based on cloud service | |
| CN110264723A (en) | A kind of traffic engineering construction intelligent Warning Systrm and method | |
| CN114444096A (en) | Network data storage encryption detection system based on data analysis | |
| KR101808695B1 (en) | Signature Extraction Module, Data Verification Module and integrity monitoring System for Sequence Data | |
| CN110636077A (en) | Network security protection system and method based on unified platform | |
| CN115208928B (en) | Remote monitoring method and device for fuel cell | |
| CN116189706A (en) | Data transmission method, device, electronic equipment and computer readable storage medium | |
| CN109976709A (en) | Randomness detecting method, device, equipment and computer readable storage medium | |
| CN114584370A (en) | Server data interaction network security system | |
| CN112969154B (en) | 5G communication method for electric power distribution safety control | |
| CN112087301A (en) | Gas meter safety certification system based on state cryptographic algorithm | |
| CN109753010A (en) | A kind of real-time level monitoring data acquisition early warning system | |
| CN117149590B (en) | Data center system with data security monitoring module and monitoring method | |
| CN117319517B (en) | Multi-protocol-based water supply equipment data integration and forwarding method | |
| CN116820896B (en) | Physical signal-based non-invasive industrial control terminal abnormality detection method | |
| CN117424763B (en) | Data rapid transmission authentication method and system for intelligent antioxidant bond alloy wire equipment | |
| CN111738873A (en) | Electric power communication safety monitoring system based on data acquisition |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210309 |