CN117406160B - Intelligent ammeter fault diagnosis system based on historical state comparison - Google Patents
Intelligent ammeter fault diagnosis system based on historical state comparison Download PDFInfo
- Publication number
- CN117406160B CN117406160B CN202311379719.6A CN202311379719A CN117406160B CN 117406160 B CN117406160 B CN 117406160B CN 202311379719 A CN202311379719 A CN 202311379719A CN 117406160 B CN117406160 B CN 117406160B
- Authority
- CN
- China
- Prior art keywords
- interface
- module
- real
- electric wire
- features
- 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
- 238000003745 diagnosis Methods 0.000 title claims abstract description 55
- 230000002159 abnormal effect Effects 0.000 claims abstract description 32
- 238000000605 extraction Methods 0.000 claims description 22
- 238000004891 communication Methods 0.000 claims description 18
- 238000011156 evaluation Methods 0.000 claims description 14
- 238000012544 monitoring process Methods 0.000 claims description 13
- 230000005856 abnormality Effects 0.000 claims description 8
- 230000008447 perception Effects 0.000 claims description 8
- 238000001125 extrusion Methods 0.000 claims description 4
- 230000000007 visual effect Effects 0.000 claims description 3
- 230000000903 blocking effect Effects 0.000 claims description 2
- 238000000034 method Methods 0.000 abstract description 4
- 238000012423 maintenance Methods 0.000 description 8
- 238000012806 monitoring device Methods 0.000 description 7
- 239000000284 extract Substances 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 239000003086 colorant Substances 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 239000000428 dust Substances 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003628 erosive effect Effects 0.000 description 2
- 230000002349 favourable effect Effects 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 229910002056 binary alloy Inorganic materials 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000003014 reinforcing effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R35/00—Testing or calibrating of apparatus covered by the other groups of this subclass
- G01R35/04—Testing or calibrating of apparatus covered by the other groups of this subclass of instruments for measuring time integral of power or current
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Testing Of Short-Circuits, Discontinuities, Leakage, Or Incorrect Line Connections (AREA)
Abstract
The invention relates to the technical field of fault diagnosis, in particular to a fault diagnosis system of an intelligent ammeter based on historical state comparison. The system comprises a history state storage unit, an interface real-time acquisition unit, a difference degree comparison unit and a diagnosis reminding unit. According to the invention, the image of the electric meter interface in a firm state with the electric wire is recorded through the history state storage unit, the firm characteristic and the surface characteristic in the image are extracted, the subsequent difference degree comparison unit is convenient to extract the real-time characteristic of the image of the interface real-time acquisition unit, the real-time characteristic is compared with the history state characteristic, the difference degree of the history state data and the real-time characteristic is evaluated, the fault condition of the electric meter can be accurately judged, if the difference degree is more than or equal to the difference threshold value, an abnormal signal is output to remind a user, the fault diagnosis efficiency is improved through a history state comparison method, the need of manual intervention is reduced, the accuracy of the fixed diagnosis at the electric meter interface is improved, and the fault condition is timely found and treated.
Description
Technical Field
The invention relates to the technical field of fault diagnosis, in particular to a fault diagnosis system of an intelligent ammeter based on historical state comparison.
Background
The smart electric meter is one of the basic devices for data acquisition of the smart power grid, bears the tasks of original electric energy data acquisition, metering and transmission, is a foundation for realizing information integration, analysis optimization and information display, and most maintenance staff does not have the capability of maintaining all types of faults when the smart electric meter breaks down at present, so that the problems of uneven investment of operation and maintenance force, untimely maintenance of a fault meter and the like exist, the normal operation of the power grid and the electricity consumption experience of a user are negatively influenced, and in the prior art, when the fault diagnosis of the smart electric meter is carried out, the problems of: according to chinese patent application No. CN202110594563.8, there is provided a fault diagnosis system for a smart meter, comprising: a plurality of monitoring devices, wireless communication devices and monitoring hosts; each monitoring device collects influence factor data of each intelligent ammeter in a corresponding area of the monitoring device and sends the collected influence factor data to a monitoring host through the wireless communication device; the monitoring host trains to obtain a full-area fault diagnosis model according to the influence factor data collected by each monitoring device, and transmits weight coefficient data of the full-area fault diagnosis model to each monitoring device; and training by each monitoring device based on the influence factor data and the weight coefficient data of each intelligent ammeter in the corresponding area to obtain a fault diagnosis model of the corresponding area, and carrying out fault diagnosis on each intelligent ammeter in the corresponding area based on the fault diagnosis model of the corresponding area. The intelligent ammeter fault diagnosis system provided by the invention can improve the real-time performance and the accuracy of intelligent ammeter fault diagnosis;
when smart electric meter uses, interface department is the very fragile position, and the atress slope of especially easily leads to connecting badly, and interface department communicates with the external world for a long time, and external dust gets into the erosion interface easily and causes dirty, even damage, cause smart electric meter trouble, however when prior art carries out fault diagnosis, when confirming the fault cause through modes such as experiment, inconvenient priority carries out the diagnosis to interface department, the problem that can not directly perceivedly confirm the interface department appears influences the efficiency of fault determination, in view of this, we propose smart electric meter fault diagnosis system based on history state contrast.
Disclosure of Invention
The invention aims to provide a fault diagnosis system for a smart meter based on historical state comparison, so as to solve the problems in the background technology.
In order to achieve the above purpose, the invention provides a smart meter fault diagnosis system based on historical state comparison, which comprises a historical state storage unit, an interface real-time acquisition unit, a difference degree comparison unit and a diagnosis reminding unit;
The history state storage unit is used for recording images of the ammeter interface and the electric wire in a firm state, and extracting firm features and surface features in the images to serve as history state features for storage; the interface real-time acquisition unit is used for installing monitoring equipment at the interface of the intelligent ammeter and acquiring images of the connection part of the interface and the electric wire in real time; the difference degree comparison unit is used for extracting real-time characteristics of the image of the interface real-time acquisition unit, comparing the real-time characteristics with the historical state characteristics of the historical state storage unit, and evaluating the difference degree of the historical state data and the real-time characteristics; the diagnosis reminding unit is used for establishing a difference threshold, receiving the difference degree of the difference degree comparison unit and comparing the difference degree with the difference threshold, outputting a normal signal if the difference degree is smaller than the difference threshold, and outputting an abnormal signal to remind a user if the difference degree is larger than or equal to the difference threshold.
As a further improvement of the technical scheme, the history state storage unit comprises a fixed point marking module, an image storage module and a history feature extraction module;
the fixed point marking module is used for setting marking points in a standard state that an ammeter interface is electrically connected with an electric wire;
the image storage module is used for collecting images in a standard state that the ammeter interface is electrically connected with the electric wire, and displaying marking points of the fixed point marking module in the images;
the history feature extraction module is used for extracting history data features in images in the image storage module by adopting a computer vision algorithm, wherein the history data features comprise firm features and surface features, the firm features comprise offset distance features from marking points to an ammeter interface and extrusion dislocation features of the electric wires under the interface, and the surface features comprise damage features and dirt features.
As a further improvement of the technical scheme, the monitoring equipment of the interface real-time acquisition unit is installed inside the intelligent ammeter by adopting a camera, and the image of the connection part of the acquisition interface and the electric wire is stored in a memory of the camera.
As a further improvement of the technical scheme, the difference degree comparison unit comprises a real-time feature extraction module and a feature matching module;
the real-time feature extraction module is used for calling out images stored in the camera, and extracting real-time features of the images by adopting a computer vision algorithm, wherein the real-time features also comprise firm features and surface features;
The characteristic matching module is used for acquiring the historical data characteristic of the historical characteristic extraction module and matching the real-time characteristic in the real-time characteristic extraction module, calculating the similarity between the real-time characteristic and the historical data characteristic, and determining the difference degree through the similarity corresponding to each characteristic type.
As a further improvement of the technical scheme, the diagnosis reminding unit comprises a difference evaluation module and an early warning reminding module;
The difference evaluation module is used for comparing the similarity with a preset difference threshold value by adopting a numerical comparison algorithm, if the similarity is smaller than the difference threshold value, the interface is normally connected with the electric wire, a normal signal is sent out, and if the similarity is larger than or equal to the difference threshold value, the interface is abnormally connected with the electric wire, and an abnormal signal is sent out;
The early warning and reminding module is used for receiving abnormal signals of the difference evaluation module by adopting the audible and visual alarm to send out sound and light to remind a user.
As a further improvement of the technical scheme, the history state storage unit further comprises a fault classification module, wherein the fault classification module is used for establishing an abnormality determination model, extracting the feature types corresponding to the similarity from the difference evaluation module to evaluate the similarity to be greater than or equal to a difference threshold, inputting the abnormality determination model, and outputting the fault types corresponding to the feature types.
As a further improvement of the technical scheme, the monitoring equipment of the interface real-time acquisition unit further comprises a performance judging module, wherein one end of the output end of the performance judging module is connected with an ammeter interface, the other end of the output end of the performance judging module is electrically connected with an electric wire, and the monitoring equipment is used for detecting whether the ammeter interface and the electric wire are passages or not when an abnormal signal of the early warning reminding module is received;
if the signal is a passage, sending a communication signal, and blocking the abnormal signal of the early warning and reminding module from continuing to transmit;
If the signal is not the channel, sending an unconnected signal, and transmitting the unconnected signal to the early warning reminding module to indicate that the interface and the electric wire are abnormal.
As a further improvement of the technical scheme, the early warning reminding module further comprises a light perception module, wherein the light perception module is used for generating red, yellow and green light to display the connection state of the intelligent ammeter interface and the electric wire, and the early warning reminding module comprises the following situations:
The first scenario indicates that no abnormal signal, no communication signal and no communication signal are received when green light is emitted, and the connection between the intelligent ammeter interface and the electric wire is normal;
The second scenario shows that when yellow light is emitted, a communication signal is received, and the connection between the intelligent ammeter interface and the electric wire is abnormal, but normal use of the intelligent ammeter is not affected;
and thirdly, when red light is emitted, the condition that an unconnected signal is received is indicated, the connection of the intelligent ammeter interface and the electric wire is abnormal, and the normal use of the intelligent ammeter is affected.
Compared with the prior art, the invention has the beneficial effects that:
1. In the intelligent ammeter fault diagnosis system based on historical state comparison, images of an ammeter interface and an electric wire in a firm state are recorded through a historical state storage unit, firm features and surface features in the images are extracted and stored as historical state features, a subsequent difference degree comparison unit is convenient to extract real-time features of an interface real-time acquisition unit image, the real-time features are compared with the historical state features, the difference degree of historical state data and the real-time features is evaluated, the fault condition of the ammeter can be accurately judged, if the difference degree is greater than or equal to a difference threshold value, an abnormal signal is output to remind a user, the efficiency of fault diagnosis is improved through a historical state comparison method, the need of manual intervention is reduced, the accuracy of fixed diagnosis at the ammeter interface is improved, and the fault condition is timely found and processed.
2. In this smart electric meter fault diagnosis system based on history state contrast, produce red, yellow and green light through light perception module and show the connected state of smart electric meter interface and electric wire, represent different states through sending the light of different colours, help the user to know the connected condition of smart electric meter interface and electric wire rapidly, conveniently in time discover and handle the unusual problem of connection, user's security and convenience have been improved, the user can in time take action according to light instruction, reduce loss or inconvenience because of connecting the trouble causes, guarantee the normal clear of electric power use.
Drawings
FIG. 1 is a schematic block diagram of the overall structure of the present invention;
Fig. 2 is a functional block diagram of a fault classification module of the present invention.
The meaning of each reference sign in the figure is:
100. A history state storage unit; 200. an interface real-time acquisition unit; 300. a difference degree comparison unit; 400. and a diagnosis reminding unit.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The intelligent ammeter is one of basic equipment for intelligent power grid data acquisition, bears the tasks of original electric energy data acquisition, metering and transmission, is a foundation for realizing information integration, analysis optimization and information display, and most maintenance staff do not have the capability of maintaining all types of faults when the intelligent ammeter breaks down at present, so that the problems of uneven operation and maintenance force input, untimely maintenance of a fault table and the like exist, and negative effects are caused on normal operation of a power grid and power consumption experience of users;
When smart electric meter uses, interface department is the very fragile position, and the atress slope of especially easily leads to connecting badly, and interface department communicates with the external world for a long time, and external dust gets into the erosion interface easily and causes dirty, even damaged, causes smart electric meter trouble, however when prior art carries out fault diagnosis, when confirming the fault cause through modes such as experimental, inconvenient priority carries out the diagnosis to interface department, the problem that can not directly perceivedly confirm the interface department appears influences the efficiency of fault determination.
Example 1
Referring to fig. 1-2, the present embodiment provides a smart meter fault diagnosis system based on historical state comparison, which includes a historical state storage unit 100, an interface real-time acquisition unit 200, a difference degree comparison unit 300, and a diagnosis reminding unit 400;
The history state storage unit 100 is used for recording images of the ammeter interface and the electric wire in a firm state, extracting firm features and surface features in the images as history state features for storage, and facilitating comparison with history state data when the ammeter interface is different, wherein the history state data is an image of the ammeter interface when the ammeter interface is normally used, and is favorable for being used as evidence of interface fault judgment;
To record the image of the firm interface of the ammeter, the subsequent comparison is convenient, and the history state storage unit 100 comprises a fixed point marking module, an image storage module and a history feature extraction module;
the fixed point marking module is used for setting marking points in a standard state that the ammeter interface is electrically connected with the electric wire;
the image storage module is used for collecting images in a standard state that the ammeter interface is electrically connected with the electric wire, and displaying marking points of the fixed point marking module in the images;
the historical characteristic extraction module is used for extracting historical data characteristics in the images in the image storage module by adopting a computer vision algorithm, wherein the historical data characteristics comprise firm characteristics and surface characteristics, the firm characteristics comprise deviation distance characteristics from a mark point to an ammeter interface and extrusion dislocation characteristics of an electric wire under the interface, and the surface characteristics comprise damage characteristics and dirt characteristics;
The specific principle of the history state storage unit 100 is as follows: under the standard state that the ammeter interface is electrically connected with the electric wire, the optimal state that the ammeter interface is connected with the electric wire can be guaranteed, normal use of the intelligent ammeter can be guaranteed, the mark point is set through the fixed point mark module, after the image storage module collects images, the mark point is displayed in the images, whether the interface is inclined with the electric wire connection or not can be judged according to the fact that the mark point is used as a comparison, meanwhile, the historical feature extraction module extracts features in the images, comparison is convenient to conduct subsequently, favorable evidence is provided for fault diagnosis at the joint of the intelligent ammeter, and accuracy of subsequent diagnosis is improved.
The interface real-time acquisition unit 200 is used for installing monitoring equipment at the interface of the intelligent ammeter, acquiring images of the connection part of the interface and the electric wire in real time, and facilitating the subsequent technology to find faults through real-time acquisition;
Specifically, the monitoring device of the real-time interface acquisition unit 200 is installed inside the smart meter by using a camera, and images of the connection position of the acquisition interface and the electric wire are stored in a memory of the camera, where the images may include features and details of the interface of the meter, such as cable connection conditions, interface fixity, and the like.
The difference degree comparison unit 300 is used for extracting real-time features of the image of the interface real-time acquisition unit 200, comparing the real-time features with the historical state features of the historical state storage unit 100, evaluating the difference degree of the historical state data and the real-time features, and accurately judging the fault condition of the ammeter;
On the basis of the above, the difference degree comparison unit 300 includes a real-time feature extraction module and a feature matching module;
The real-time feature extraction module is used for calling out the image stored in the camera, and extracting real-time features of the image by adopting a computer vision algorithm, wherein the real-time features also comprise firm features and surface features;
The feature matching module is used for obtaining the historical data features of the historical feature extraction module and matching the real-time features in the real-time feature extraction module, calculating the similarity between the real-time features and the historical data features, determining the difference degree through the similarity corresponding to each feature type, specifically, when the features are matched, feature description such as SIFT, SURF and other matching algorithms can be used, the similarity between the real-time features and the corresponding features in the historical state data is calculated, firm features in the real-time features and firm features in the historical data features are in one-to-one correspondence, and the same surface features are also in one-to-one correspondence, so that the output of one similarity of each feature type is realized;
The method is characterized in that when the real-time feature extraction module extracts the real-time features in the image, the historical feature extraction module adopts computer vision algorithms, such as a local binary system mode, a gray level co-occurrence matrix or a convolutional neural network, and the like, when the historical feature extraction module extracts the historical data features in the image, and the algorithms can extract the features of textures, edges, colors and the like in the image.
The diagnosis reminding unit 400 is used for establishing a difference threshold, receiving the difference degree of the difference degree comparison unit 300, comparing the difference degree with the difference threshold, outputting a normal signal if the difference degree is smaller than the difference threshold, outputting an abnormal signal to remind a user if the difference degree is larger than or equal to the difference threshold, improving the efficiency of fault diagnosis through a historical state comparison method, reducing the need of manual intervention, improving the accuracy of fixed diagnosis at an ammeter interface, and finding and processing fault conditions in time.
Further, the diagnosis reminding unit 400 includes a difference evaluation module and an early warning reminding module;
The difference evaluation module is used for comparing the similarity with a preset difference threshold value by adopting a numerical comparison algorithm, if the similarity is smaller than the difference threshold value, the interface and the electric wire are indicated to be connected normally, a normal signal is sent, if the similarity is larger than or equal to the difference threshold value, the interface and the electric wire are indicated to be connected abnormally, an abnormal signal is sent, wherein the difference threshold value is a critical value for influencing poor contact between the interface and the electric wire, if the similarity is smaller than the difference threshold value, the interface and the electric wire of the intelligent electric meter are indicated to be electrically connected, and the intelligent electric meter can be used normally, otherwise, if the similarity is larger than or equal to the difference threshold value, the interface and the electric wire are indicated to be misplaced, offset and other reasons to cause poor contact, so that the normal use is influenced, the condition of the interface and the electric wire is conveniently and automatically monitored, the connection condition of the interface and the electric wire is quickly diagnosed when the intelligent electric meter is in fault, and the diagnosis efficiency is improved;
The early warning reminding module is used for sending out sound and light to remind a user by adopting the audible and visual alarm to receive the abnormal signal of the difference evaluation module, and is convenient for reminding the user at the first time to avoid affecting the normal use of the intelligent ammeter when abnormality occurs.
Example 2:
The reason that the interface and the electric wire are faulty can not be diagnosed rapidly when the interface and the electric wire are abnormal, so that the subsequent maintenance is inconvenient, and therefore, the history state storage unit 100 further comprises a fault classification module, the fault classification module is used for establishing an abnormality determination model, extracting the characteristic types corresponding to the similarity from the difference evaluation module to evaluate the similarity to be greater than or equal to a difference threshold, inputting the abnormality determination model into the characteristic types corresponding to the similarity, outputting the fault types corresponding to the characteristic types, for example, in the characteristic matching module, matching the firm characteristic in the real-time characteristic with the firm characteristic in the history data characteristic to obtain the similarity of the two, comparing the similarity with the difference evaluation module, and extracting the firm characteristic corresponding to the similarity from the fault classification module to be input into the abnormality determination model, outputting the deviation from the marking point on the electric wire corresponding to the firm characteristic to the electric meter interface and the fault type that the electric wire is extruded and misplaced by the interface, determining that the electric wire and the interface are in poor contact due to the deviation and extrusion misplacement, thereby facilitating the maintenance of the fault types and improving the diagnosis efficiency.
Example 3:
When the marked point on the electric wire and the electric meter interface deviate, the normal work of the current intelligent electric meter can not be influenced, so that the diagnosis of the fault is inaccurate only by judging the electric wire deviation, but the possibility of poor contact can be increased when the electric wire deviates, so that in order to improve the accuracy of the fault at the intelligent electric meter interface, the monitoring equipment of the interface real-time acquisition unit 200 further comprises a performance judging module, one end of the output end of the performance judging module is connected with the electric meter interface, and the other end of the output end of the performance judging module is electrically connected with the electric wire, and is used for detecting whether the electric meter interface and the electric wire are passages or not when an abnormal signal of the early warning reminding module is received;
If the intelligent ammeter is in the channel, a communication signal is sent out, and the abnormal signal of the early warning reminding module is blocked from being continuously transmitted, so that fault misjudgment is avoided under the condition that the deviation occurs but the normal use of the intelligent ammeter is not affected, and the accuracy of ammeter fault diagnosis is improved;
If the communication signal is not transmitted by the communication channel, the communication signal is transmitted to the early warning reminding module, the interface and the electric wire are abnormal, and when the difference evaluation module transmits an abnormal signal to enable the early warning reminding module to remind a user, the communication signal is not used for reinforcing the early warning reminding module again, so that the user can be reminded, and the effect of fault detection is improved.
In addition, when the early warning reminding module sends out the light and reminds the user, can not let the user know what the smart electric meter joint is in, consequently, make the early warning remind module still include light perception module, light perception module is used for producing red, yellow and green light and shows the connected state of smart electric meter interface and electric wire, includes following sight:
The first scenario indicates that no abnormal signal, no communication signal and no communication signal are received when green light is emitted, and the connection between the intelligent ammeter interface and the electric wire is normal;
The second scenario shows that when yellow light is emitted, a communication signal is received, and the connection between the intelligent ammeter interface and the electric wire is abnormal, but normal use of the intelligent ammeter is not affected;
Thirdly, when red light is emitted, the fact that an unconnected signal is received is indicated, the connection between the intelligent ammeter interface and the electric wire is abnormal, normal use of the intelligent ammeter is affected, and the fault condition of the intelligent ammeter interface is judged according to lamplight by a user;
Specifically, the working principle of the light perception module is that the connection state is judged according to the transmission condition of the connection signal, and different states are represented by emitting lights with different colors, so that a user is helped to quickly know the connection condition of the intelligent ammeter interface and the electric wire, the abnormal connection problem is conveniently and timely found and handled, the safety and convenience of the user are improved, the user can timely take actions according to the light indication, the loss or inconvenience caused by connection faults is reduced, and the normal operation of electric power use is ensured.
The foregoing has shown and described the basic principles, principal features and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the above-described embodiments, and that the above-described embodiments and descriptions are only preferred embodiments of the present invention, and are not intended to limit the invention, and that various changes and modifications may be made therein without departing from the spirit and scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (7)
1. Intelligent ammeter fault diagnosis system based on historical state contrast, its characterized in that: the system comprises a history state storage unit (100), an interface real-time acquisition unit (200), a difference degree comparison unit (300) and a diagnosis reminding unit (400);
The history state storage unit (100) is used for recording an image of the electric meter interface in a firm state with the electric wire, and extracting firm features and surface features in the image to serve as history state features for storage; the interface real-time acquisition unit (200) is used for installing monitoring equipment at the interface of the intelligent ammeter and acquiring images of the joint of the interface and the electric wire in real time; the difference degree comparison unit (300) is used for extracting real-time characteristics of the image of the interface real-time acquisition unit (200), comparing the real-time characteristics with the history state characteristics of the history state storage unit (100), and evaluating the difference degree of the history state data and the real-time characteristics; the diagnosis reminding unit (400) is used for establishing a difference threshold, receiving the difference degree of the difference degree comparison unit (300) and comparing the difference degree with the difference threshold, outputting a normal signal if the difference degree is smaller than the difference threshold, and outputting an abnormal signal to remind a user if the difference degree is larger than or equal to the difference threshold;
The history state storage unit (100) comprises a fixed point marking module, an image storage module and a history feature extraction module;
the fixed point marking module is used for setting marking points in a standard state that an ammeter interface is electrically connected with an electric wire;
the image storage module is used for collecting images in a standard state that the ammeter interface is electrically connected with the electric wire, and displaying marking points of the fixed point marking module in the images;
the history feature extraction module is used for extracting history data features in images in the image storage module by adopting a computer vision algorithm, wherein the history data features comprise firm features and surface features, the firm features comprise offset distance features from marking points to an ammeter interface and extrusion dislocation features of the electric wires under the interface, and the surface features comprise damage features and dirt features.
2. The intelligent ammeter fault diagnosis system based on historical state comparison according to claim 1, wherein: the monitoring equipment of the interface real-time acquisition unit (200) is installed inside the intelligent ammeter by adopting a camera, and an image of the connection part of the acquisition interface and the electric wire is stored in a memory of the camera.
3. The intelligent ammeter fault diagnosis system based on historical state comparison according to claim 2, wherein: the difference degree comparison unit (300) comprises a real-time feature extraction module and a feature matching module;
the real-time feature extraction module is used for calling out images stored in the camera, and extracting real-time features of the images by adopting a computer vision algorithm, wherein the real-time features also comprise firm features and surface features;
The characteristic matching module is used for acquiring the historical data characteristic of the historical characteristic extraction module and matching the real-time characteristic in the real-time characteristic extraction module, calculating the similarity between the real-time characteristic and the historical data characteristic, and determining the difference degree through the similarity corresponding to each characteristic type.
4. The intelligent ammeter fault diagnosis system based on historical state comparison according to claim 3, wherein: the diagnosis reminding unit (400) comprises a difference evaluation module and an early warning reminding module;
The difference evaluation module is used for comparing the similarity with a preset difference threshold value by adopting a numerical comparison algorithm, if the similarity is smaller than the difference threshold value, the interface is normally connected with the electric wire, a normal signal is sent out, and if the similarity is larger than or equal to the difference threshold value, the interface is abnormally connected with the electric wire, and an abnormal signal is sent out;
The early warning and reminding module is used for receiving abnormal signals of the difference evaluation module by adopting the audible and visual alarm to send out sound and light to remind a user.
5. The intelligent ammeter fault diagnosis system based on historical state comparison according to claim 4, wherein: the history state storage unit (100) further comprises a fault classification module, wherein the fault classification module is used for establishing an abnormality determination model, extracting the characteristic types corresponding to the similarity from the difference evaluation module to evaluate the similarity to be larger than or equal to a difference threshold, inputting the abnormality determination model, and outputting the fault types corresponding to the characteristic types.
6. The historical state comparison-based smart meter fault diagnosis system of claim 5, wherein: the monitoring equipment of the interface real-time acquisition unit (200) further comprises a performance judging module, wherein one end of the output end of the performance judging module is connected with an ammeter interface, the other end of the output end of the performance judging module is electrically connected with an electric wire, and the monitoring equipment is used for detecting whether the ammeter interface and the electric wire are passages or not when an abnormal signal of the early warning reminding module is received;
if the signal is a passage, sending a communication signal, and blocking the abnormal signal of the early warning and reminding module from continuing to transmit;
If the signal is not the channel, sending an unconnected signal, and transmitting the unconnected signal to the early warning reminding module to indicate that the interface and the electric wire are abnormal.
7. The historical state comparison-based smart meter fault diagnosis system of claim 6, wherein: the early warning reminding module further comprises a light perception module, wherein the light perception module is used for generating red, yellow and green light to display the connection state of the intelligent ammeter interface and the electric wire, and the early warning reminding module comprises the following situations:
The first scenario indicates that no abnormal signal, no communication signal and no communication signal are received when green light is emitted, and the connection between the intelligent ammeter interface and the electric wire is normal;
The second scenario shows that when yellow light is emitted, a communication signal is received, and the connection between the intelligent ammeter interface and the electric wire is abnormal, but normal use of the intelligent ammeter is not affected;
and thirdly, when red light is emitted, the condition that an unconnected signal is received is indicated, the connection of the intelligent ammeter interface and the electric wire is abnormal, and the normal use of the intelligent ammeter is affected.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311379719.6A CN117406160B (en) | 2023-10-23 | 2023-10-23 | Intelligent ammeter fault diagnosis system based on historical state comparison |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311379719.6A CN117406160B (en) | 2023-10-23 | 2023-10-23 | Intelligent ammeter fault diagnosis system based on historical state comparison |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117406160A CN117406160A (en) | 2024-01-16 |
| CN117406160B true CN117406160B (en) | 2024-05-17 |
Family
ID=89493920
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311379719.6A Active CN117406160B (en) | 2023-10-23 | 2023-10-23 | Intelligent ammeter fault diagnosis system based on historical state comparison |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117406160B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20080008000A (en) * | 2006-07-19 | 2008-01-23 | 주식회사 대우일렉트로닉스 | Apparatus for fixing the plug of image display device |
| CN102722166A (en) * | 2012-06-29 | 2012-10-10 | 山东电力集团公司电力科学研究院 | Intelligent vision detection system and state detection method of transformer substation device |
| CN106500593A (en) * | 2016-10-31 | 2017-03-15 | 哈尔滨工业大学 | Aviation electric connector contact pin position deviation detection method |
| CN109655469A (en) * | 2018-12-27 | 2019-04-19 | 深圳市燕麦科技股份有限公司 | A kind of the docking test device and its docking test method of flexible circuit board |
| CN111562540A (en) * | 2020-05-17 | 2020-08-21 | 宁夏隆基宁光仪表股份有限公司 | Electric energy meter detection monitoring method based on dynamic image recognition and analysis |
| CN114037673A (en) * | 2021-11-03 | 2022-02-11 | 深圳市创科自动化控制技术有限公司 | Hardware connection interface monitoring method and system based on machine vision |
| CN114594102A (en) * | 2022-03-29 | 2022-06-07 | 吉安易巴克电子科技有限公司 | Machine vision-based data line interface automatic detection method |
| CN116659577A (en) * | 2023-05-31 | 2023-08-29 | 费莱(浙江)科技有限公司 | Intelligent detection method for full life cycle of motor |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP7042216B2 (en) * | 2016-05-03 | 2022-03-25 | アフェラ， インコーポレイテッド | Display of anatomical model |
-
2023
- 2023-10-23 CN CN202311379719.6A patent/CN117406160B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20080008000A (en) * | 2006-07-19 | 2008-01-23 | 주식회사 대우일렉트로닉스 | Apparatus for fixing the plug of image display device |
| CN102722166A (en) * | 2012-06-29 | 2012-10-10 | 山东电力集团公司电力科学研究院 | Intelligent vision detection system and state detection method of transformer substation device |
| CN106500593A (en) * | 2016-10-31 | 2017-03-15 | 哈尔滨工业大学 | Aviation electric connector contact pin position deviation detection method |
| CN109655469A (en) * | 2018-12-27 | 2019-04-19 | 深圳市燕麦科技股份有限公司 | A kind of the docking test device and its docking test method of flexible circuit board |
| CN111562540A (en) * | 2020-05-17 | 2020-08-21 | 宁夏隆基宁光仪表股份有限公司 | Electric energy meter detection monitoring method based on dynamic image recognition and analysis |
| CN114037673A (en) * | 2021-11-03 | 2022-02-11 | 深圳市创科自动化控制技术有限公司 | Hardware connection interface monitoring method and system based on machine vision |
| CN114594102A (en) * | 2022-03-29 | 2022-06-07 | 吉安易巴克电子科技有限公司 | Machine vision-based data line interface automatic detection method |
| CN116659577A (en) * | 2023-05-31 | 2023-08-29 | 费莱(浙江)科技有限公司 | Intelligent detection method for full life cycle of motor |
Non-Patent Citations (2)
| Title |
|---|
| 基于图像特征提取的飞行器故障诊断系统设计;陈思;贺志伟;;计算机测量与控制;20181023(10);全文 * |
| 基于数据挖掘的智能电能表在线监测方法;王新刚;吴颖;张垠;;电测与仪表;20160710(13);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117406160A (en) | 2024-01-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110807460B (en) | Transformer substation intelligent patrol system based on image recognition and application method thereof | |
| CN116394794B (en) | High security intelligence fills electric pile | |
| CN107592371A (en) | A kind of electric power construction field informationization supervision system based on wireless sensor network | |
| CN113177646B (en) | Power distribution equipment online monitoring method and system based on self-adaptive edge proxy | |
| CN112147438A (en) | Fault pre-diagnosis system of high-voltage frequency converter | |
| CN110738289A (en) | Multi-dimensional linkage comprehensive studying and judging device for electric power operation standardization and using method thereof | |
| CN111341063A (en) | Intelligent control system, method and device for safety early warning and monitoring of electric equipment and terminal equipment | |
| CN112564291A (en) | Power equipment pressing plate state monitoring system and monitoring method | |
| CN107784801A (en) | Navigation mark remote measuring and controlling alarm system and its realizing method | |
| CN213715353U (en) | Fault detection system for high-voltage distribution board | |
| CN117406160B (en) | Intelligent ammeter fault diagnosis system based on historical state comparison | |
| CN110728212A (en) | Road well lid monitoring device and method based on computer vision | |
| CN117938625A (en) | Internet of things card fault diagnosis system based on data analysis | |
| CN117129796A (en) | Power grid fault identification system based on big data | |
| CN117061555A (en) | Intelligent sensing data monitoring system based on power distribution communication network | |
| CN108149257B (en) | Impressed current cathodic protection monitoring control system for offshore jacket platform | |
| CN113516091B (en) | Method for identifying electric spark image of transformer substation | |
| CN115586458A (en) | Method and system for monitoring mistaken hanging prevention of ground wire in contact network maintenance operation | |
| CN115061012A (en) | Intelligent monitoring and diagnosing system and method based on edge computing power supply grid | |
| CN114264902A (en) | Method and system for monitoring working state of lightning protection box, electronic equipment and storage medium | |
| CN211060960U (en) | Electric power operation site monitoring device | |
| CN112067934A (en) | Electrical control cabinet fault monitoring system | |
| CN112145142A (en) | Three-dimensional deployment system of fracturing well site | |
| CN112433488A (en) | Equipment safety management system | |
| CN215640188U (en) | Unit performance analysis and optimized operation management platform |
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 |