CN117232577B - Optical cable distributing box bearing interior monitoring method and system and optical cable distributing box - Google Patents
Optical cable distributing box bearing interior monitoring method and system and optical cable distributing box Download PDFInfo
- Publication number
- CN117232577B CN117232577B CN202311196241.3A CN202311196241A CN117232577B CN 117232577 B CN117232577 B CN 117232577B CN 202311196241 A CN202311196241 A CN 202311196241A CN 117232577 B CN117232577 B CN 117232577B
- Authority
- CN
- China
- Prior art keywords
- module
- data
- abnormal
- diagnosis
- picture
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 109
- 230000003287 optical effect Effects 0.000 title claims abstract description 85
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000003745 diagnosis Methods 0.000 claims abstract description 197
- 230000005540 biological transmission Effects 0.000 claims abstract description 52
- 230000002159 abnormal effect Effects 0.000 claims description 133
- 239000000779 smoke Substances 0.000 claims description 19
- 238000005457 optimization Methods 0.000 claims description 17
- 238000013136 deep learning model Methods 0.000 claims description 15
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 claims description 9
- 238000012423 maintenance Methods 0.000 abstract description 12
- 238000004891 communication Methods 0.000 abstract description 5
- 238000005516 engineering process Methods 0.000 abstract description 2
- 230000009545 invasion Effects 0.000 description 15
- 230000008569 process Effects 0.000 description 12
- 238000005070 sampling Methods 0.000 description 11
- 241000238631 Hexapoda Species 0.000 description 6
- 241000699666 Mus <mouse, genus> Species 0.000 description 6
- 238000000605 extraction Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 241000699670 Mus sp. Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000004171 remote diagnosis Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Alarm Systems (AREA)
Abstract
The invention discloses an optical cable cross connecting box bearing internal monitoring method, an optical cable cross connecting box bearing internal monitoring system and an optical cable cross connecting box, and belongs to the technical fields of communication technology and optical cable access equipment; according to the invention, whether faults occur or not is locally judged through the optical cable cross connecting cabinet, and compared with the operation and maintenance mode that a worker or a server discovers faults after uploading, the problem of inaccurate diagnosis results is avoided, the hysteresis of network transmission is avoided, and the operation and maintenance efficiency is improved; by combining the data acquired by the sensor module and the image acquisition module, fault judgment is performed, so that the accuracy of fault judgment is improved, misjudgment of a sensor or an image is avoided, and the reliability of operation and maintenance is ensured; by constructing a diagnosis model based on the multi-scale deep feature learning model and further performing fault diagnosis, the accuracy of the diagnosis result is further improved on the basis of guaranteeing the diagnosis efficiency compared with simple numerical comparison, so that the operation and maintenance efficiency is guaranteed.
Description
Technical Field
The invention relates to the technical field of communication technology and optical cable access equipment, in particular to a method and a system for monitoring the bearing interior of an optical cable cross connecting cabinet and the optical cable cross connecting cabinet.
Background
The optical cable cross connecting cabinet is cross connecting equipment for providing optical cable end forming and jump connection for the optical cable of the trunk layer and the optical cable of the distribution layer. Along with the continuous application of the optical cable cross connecting cabinet in network erection and installation, besides the requirement that the optical cable cross connecting cabinet can resist to severe climate and severe working environment, the internal components and parts of the optical cable cross connecting cabinet are required to be monitored, so that high-temperature invasion, rainwater invasion, insect and mouse invasion and impact damage occur, and operation and maintenance personnel can timely find and maintain the optical cable cross connecting cabinet.
The existing optical cable cross connecting cabinet is used for realizing internal monitoring only by arranging a sensor or a camera inside, so that internal monitoring data or pictures are acquired and uploaded.
However, those skilled in the art find that when internal monitoring data or pictures are uploaded to a background server or a worker, and then the worker or the server finds a fault, the problem of inaccurate diagnosis results not only occurs due to remote diagnosis, but also causes time lag of fault finding due to the hysteresis of network transmission, further causes hysteresis of operation and maintenance, thereby causing loss and increasing operation and maintenance cost.
Disclosure of Invention
In order to solve the problems in the prior art, the embodiment of the invention provides a method and a system for monitoring the bearing interior of an optical cable cross connecting cabinet and the optical cable cross connecting cabinet. The technical scheme is as follows:
In a first aspect, a method for monitoring the interior of an optical cable cross-connecting cabinet is provided, the method is applied to an optical cable cross-connecting cabinet bearing interior monitoring system, the system at least comprises a monitoring server and a plurality of optical cable cross-connecting cabinets, and the optical cable cross-connecting cabinets are at least provided with an image acquisition module, a sensor module and a transmission module; the image acquisition module, the sensor module and the transmission module are connected with a bearing platform arranged in the optical cable cross connecting cabinet through a universal interface; the sensor module comprises a temperature sensor, a humidity sensor, a smoke sensor and a monitoring unit for monitoring whether components and parts normally operate; the method comprises the following steps:
acquiring data perceived by the sensor module and the image acquisition module in real time, generating a monitoring log, and uploading and recording the monitoring log in real time;
when the sensor module detects abnormal data, a fault diagnosis model of the image acquisition module is started, and a diagnosis result is output;
the transmission module sets an abnormal event according to the abnormal data and transmits the abnormal event to the monitoring server, wherein the abnormal event at least comprises the abnormal data and a plurality of groups of data related to the abnormal data;
When the image acquisition module detects an abnormal picture, a fault diagnosis model of the sensor module is started, and a diagnosis result is output;
the transmission module acquires a difference image according to the abnormal picture and transmits the difference image to the monitoring server,
the transmission module uploads and records the diagnosis result to the monitoring server;
wherein the method further comprises setting the fault diagnosis model, comprising:
setting a fault diagnosis model based on a multi-scale depth feature learning model, and setting the abnormal picture and the abnormal data as feature data;
and optimizing and updating parameters of the fault diagnosis model based on an Adam optimization algorithm.
Optionally, the detecting abnormal data by the sensor module includes:
the judgment models are arranged corresponding to all the components;
calculating cross entropy of all components and optimizing the judgment model based on the cross entropy;
and judging whether the detected data is abnormal according to the judging model.
Optionally, the starting the diagnostic model of the image acquisition module and outputting a diagnostic result:
setting an identification target according to the output result of the judgment model;
Setting image characteristic elements corresponding to the identification targets;
identifying and extracting image characteristic elements in the image according to the fault diagnosis model;
optimizing the extracted image characteristic elements, diagnosing on the basis of the fault diagnosis model according to the optimized image characteristic elements, and outputting the diagnosis result.
Optionally, the detecting the abnormal image by the image acquisition module includes:
identifying difference data between the current picture and the previous picture acquired by the image acquisition module;
calculating the area of the abnormal picture in the whole picture based on the difference data;
based on the fault diagnosis model, a target within the region is identified.
Optionally, the starting the diagnostic model of the sensor module and outputting the diagnostic result include:
identifying fault description data according to the target; the fault description data comprise picture shake, spark or smoke generated in a picture and foreign matters appearing in the picture;
and identifying fault components and related components on the basis of the fault diagnosis model according to the fault description data and the data perceived by the sensor module, and outputting a diagnosis result.
Optionally, the multi-scale depth feature based learning model includes:
setting a feature extractor on the basis of a convolution kernel of multi-scale learning through a plurality of acceptance units;
based on the feature extractor, extracting features of monitoring data of key components in the optical cable cross connecting cabinet;
according to the extracted characteristic data, establishing a deep learning model corresponding to the key components;
and optimizing the deep learning model based on the cross entropy classification loss optimization target.
Optionally, the method further comprises:
and periodically updating the monitoring server and issuing the fault diagnosis model to the optical cable cross connecting cabinet.
On the other hand, an optical cable distributing box bearing internal monitoring system is provided, the system at least comprises a monitoring server and a plurality of optical cable distributing boxes, and the optical cable distributing boxes are at least provided with a diagnosis module, an image acquisition module, a sensor module and a transmission module; the image acquisition module, the sensor module and the transmission module are connected with a bearing platform arranged in the optical cable cross connecting cabinet through a universal interface; the sensor module comprises a temperature sensor, a humidity sensor, a smoke sensor and a monitoring unit for monitoring whether components and parts normally operate; wherein:
The diagnosis module is used for acquiring the data perceived by the sensor module and the image acquisition module in real time, generating a monitoring log, and uploading and recording the monitoring log in real time;
the diagnosis module is used for starting a fault diagnosis model of the image acquisition module and outputting a diagnosis result when the sensor module detects abnormal data;
the transmission module is used for setting an abnormal event according to the abnormal data and transmitting the abnormal event to the monitoring server, wherein the abnormal event at least comprises the abnormal data and a plurality of groups of data related to the abnormal data;
the diagnosis module is also used for starting a fault diagnosis model of the sensor module and outputting a diagnosis result when the image acquisition module detects an abnormal picture;
the transmission module is used for acquiring a difference image according to the abnormal picture and transmitting the difference image to the monitoring server,
the transmission module is used for uploading the diagnosis result to the monitoring server and recording the diagnosis result;
wherein, the diagnosis module is further used for:
setting a fault diagnosis model based on a multi-scale depth feature learning model, and setting the abnormal picture and the abnormal data as feature data;
And optimizing and updating parameters of the fault diagnosis model based on an Adam optimization algorithm.
Optionally, the diagnosis module is used for:
setting an identification target according to the output result of the judgment model;
setting image characteristic elements corresponding to the identification targets;
identifying and extracting image characteristic elements in the image according to the fault diagnosis model;
optimizing the extracted image characteristic elements, diagnosing on the basis of the fault diagnosis model according to the optimized image characteristic elements, and outputting the diagnosis result.
Optionally, the image acquisition module is used for:
identifying difference data between the current picture and the previous picture acquired by the image acquisition module;
calculating the area of the abnormal picture in the whole picture based on the difference data;
based on the fault diagnosis model, a target within the region is identified.
Optionally, the diagnosis module is used for:
identifying fault description data according to the target; the fault description data comprise picture shake, spark or smoke generated in a picture and foreign matters appearing in the picture;
and identifying fault components and related components on the basis of the fault diagnosis model according to the fault description data and the data perceived by the sensor module, and outputting a diagnosis result.
Optionally, the diagnostic module is further configured to:
setting a feature extractor on the basis of a convolution kernel of multi-scale learning through a plurality of acceptance units;
based on the feature extractor, extracting features of monitoring data of key components in the optical cable cross connecting cabinet;
according to the extracted characteristic data, establishing a deep learning model corresponding to the key components;
and optimizing the deep learning model based on the cross entropy classification loss optimization target.
Alternatively to this, the method may comprise,
the monitoring server is also used for periodically updating and issuing the fault diagnosis model to the optical cable cross connecting cabinet.
On the other hand, an optical cable cross-connecting box is provided, and the optical cable cross-connecting box comprises a diagnosis module, an image acquisition module, a sensor module and a transmission module; the image acquisition module, the sensor module and the transmission module are connected with a bearing platform arranged in the optical cable cross connecting cabinet through a universal interface; the sensor module comprises a temperature sensor, a humidity sensor, a smoke sensor and a monitoring unit for monitoring whether components and parts normally operate; wherein:
the diagnosis module is used for acquiring the data perceived by the sensor module and the image acquisition module in real time, generating a monitoring log, and uploading and recording the monitoring log in real time;
The diagnosis module is used for starting a fault diagnosis model of the image acquisition module and outputting a diagnosis result when the sensor module detects abnormal data;
the transmission module is used for setting an abnormal event according to the abnormal data and transmitting the abnormal event to the monitoring server, wherein the abnormal event at least comprises the abnormal data and a plurality of groups of data related to the abnormal data;
the diagnosis module is also used for starting a fault diagnosis model of the sensor module and outputting a diagnosis result when the image acquisition module detects an abnormal picture;
the transmission module is used for acquiring a difference image according to the abnormal picture and transmitting the difference image to the monitoring server,
the transmission module is used for uploading the diagnosis result to the monitoring server and recording the diagnosis result;
wherein, the diagnosis module is further used for:
setting a fault diagnosis model based on a multi-scale depth feature learning model, and setting the abnormal picture and the abnormal data as feature data;
and optimizing and updating parameters of the fault diagnosis model based on an Adam optimization algorithm.
Optionally, the loading platform with the optical cable distributing box can dismantle the connection, optical cable distributing box outside is provided with display module assembly and input module assembly, display module assembly with input module assembly with the loading platform passes through universal interface connection.
Optionally, the diagnosis module is used for:
setting an identification target according to the output result of the judgment model;
setting image characteristic elements corresponding to the identification targets;
identifying and extracting image characteristic elements in the image according to the fault diagnosis model;
optimizing the extracted image characteristic elements, diagnosing on the basis of the fault diagnosis model according to the optimized image characteristic elements, and outputting the diagnosis result.
Optionally, the image acquisition module is used for:
identifying difference data between the current picture and the previous picture acquired by the image acquisition module;
calculating the area of the abnormal picture in the whole picture based on the difference data;
based on the fault diagnosis model, a target within the region is identified.
Optionally, the diagnosis module is used for:
identifying fault description data according to the target; the fault description data comprise picture shake, spark or smoke generated in a picture and foreign matters appearing in the picture;
and identifying fault components and related components on the basis of the fault diagnosis model according to the fault description data and the data perceived by the sensor module, and outputting a diagnosis result.
Optionally, the diagnostic module is further configured to:
setting a feature extractor on the basis of a convolution kernel of multi-scale learning through a plurality of acceptance units;
based on the feature extractor, extracting features of monitoring data of key components in the optical cable cross connecting cabinet;
according to the extracted characteristic data, establishing a deep learning model corresponding to the key components;
and optimizing the deep learning model based on the cross entropy classification loss optimization target.
The invention has at least the following beneficial effects:
1. whether faults occur or not is locally judged through the optical cable cross connecting cabinet, and compared with the operation and maintenance mode that internal monitoring data or pictures are uploaded to a background server or a worker, the worker or the server discovers faults, so that the problem of inaccurate diagnosis results is avoided, the hysteresis of network transmission is avoided, and the operation and maintenance efficiency is improved;
2. by combining the data acquired by the sensor module and the image acquisition module, fault judgment is performed, so that the accuracy of fault judgment is improved, misjudgment of a sensor or an image is avoided, and the reliability of operation and maintenance is ensured;
3. by constructing a diagnosis model based on the multi-scale deep feature learning model and further performing fault diagnosis, the accuracy of the diagnosis result is further improved on the basis of guaranteeing the diagnosis efficiency compared with simple numerical comparison, so that the operation and maintenance efficiency is guaranteed.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a method for monitoring the load-bearing interior of an optical cable cross-connecting cabinet according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of an internal monitoring system for a cable cross-connect cabinet according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an optical cable cross-connecting box according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments of the present invention. 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 optical cable cross connecting cabinet bearing internal monitoring method is applied to an optical cable cross connecting cabinet bearing internal monitoring system, and the system at least comprises a monitoring server and a plurality of optical cable cross connecting cabinets, wherein the communication mode between the monitoring server and the optical cable cross connecting cabinets can be wireless communication based on the Internet of things, namely a transmission module of the optical cable cross connecting cabinet is at least provided with an Internet of things communication module (namely a transmission module), such as a 5G module and the like;
correspondingly, the optical cable cross connecting box is at least provided with an image acquisition module, a sensor module and a transmission module; the image acquisition module can be a monitoring camera, and in practical application, the monitoring camera can at least rotate freely; the image acquisition module, the sensor module and the transmission module are connected with a bearing platform arranged in the optical cable cross connecting cabinet through universal interfaces; the image acquisition module, the sensor module and the transmission module are plugged and used through the universal interface, so that the image acquisition module, the sensor module and the transmission module are convenient to replace when damaged or failed, or convenient to install when other modules are added;
In addition, the sensor module comprises a temperature sensor, a humidity sensor, a smoke sensor and a monitoring unit for monitoring whether components and parts normally operate; the above-mentioned sensor is merely exemplary, and in practical application, in order to better prevent high temperature invasion, rain invasion, insect and mouse invasion and impact damage, other sensors may be added, and the embodiment of the present invention is not limited to a specific sensor.
Referring to fig. 1, there is provided a method for monitoring the interior of a cable cross-connect cabinet, the method comprising:
101. acquiring data perceived by the sensor module and the image acquisition module in real time, generating a monitoring log, uploading the monitoring log in real time, and recording the monitoring log;
specifically, the data perceived by the sensor module and the image acquisition module are:
the sensor module is used for acquiring sensing data acquired by the sensor module and image data acquired by the image acquisition module.
102. When the sensor module detects abnormal data, a fault diagnosis model of the image acquisition module is started, and a diagnosis result is output;
103. the transmission module sets an abnormal event according to the abnormal data and transmits the abnormal event to the monitoring server, wherein the abnormal event at least comprises the abnormal data and a plurality of groups of data related to the abnormal data;
Specifically, the sets of data related to the abnormal data may be:
operation data of other components related to the component corresponding to the abnormal data; or,
operating data corresponding to a time period before the occurrence time of the abnormal data and a time period after the occurrence time of the abnormal data;
the comprehensive performance of data acquisition is improved, and the fault judgment is more accurately carried out by a monitoring server or operation and maintenance personnel.
104. When the image acquisition module detects an abnormal picture, a fault diagnosis model of the sensor module is started, and a diagnosis result is output;
105. the transmission module acquires the difference image according to the abnormal picture and transmits the difference image to the monitoring server;
specifically, the process of obtaining the difference image according to the abnormal image is the same as the manner described in step 104, and will not be described here again.
106. The transmission module uploads and records the diagnosis result to the monitoring server;
wherein prior to step 101, the method further comprises setting a fault diagnosis model, comprising:
107. setting a fault diagnosis model based on the multi-scale depth feature learning model, and setting an abnormal picture and abnormal data as feature data;
108. based on an Adam optimization algorithm, optimizing and updating parameters of the fault diagnosis model.
Optionally, detecting the abnormal data by the sensor module in step 102 includes:
201. the judgment models are arranged corresponding to all the components;
specifically, the process of setting the judgment model corresponding to the component may be:
setting an expected value set of operating parameters of the components, wherein the set at least comprises expected sampling time and an expected sampling value, and in practical application, the expected sampling value is a theoretical value;
setting an actual value set of operating parameters of the components; the set comprises at least the actual sampling time and the actual sampling value,
calculating a difference value between an expected value set and an actual value set, wherein the difference value is specifically a difference value between an actual sampling value and an expected sampling value when the actual sampling time is the same as the expected sampling time;
taking the difference value as a characteristic value set;
based on the decision tree model, a judgment model corresponding to the component is set, and the set of characteristic values is set as input values of the judgment model.
The output value is set to a failure type including, by way of example, high temperature invasion, rain invasion, insect and mouse invasion, and impact damage.
202. Calculating cross entropy of all components and parts, and optimizing a judgment model based on the cross entropy;
Specifically, for cross entropy between certain components, the calculation mode can be calculated by a discrete variable mode, and the calculation formula comprises:
wherein H (p, q) is cross entropy; and x is probability distribution corresponding to an expected value set and probability distribution corresponding to an actual value set of the component.
Based on the cross entropy, the process of optimizing the judgment model can be as follows:
and setting cross entropy as a loss function of the judgment model.
203. And judging whether the detected data is abnormal according to the judging model.
Specifically, according to the output result of the judgment model, whether the detected data is abnormal is judged, and the embodiment of the invention does not limit the specific process.
Optionally, in step 102, starting a diagnostic model of the image acquisition module, and outputting a diagnostic result includes:
301. setting an identification target according to the output result of the judgment model;
specifically, the output result (i.e. output value) is high temperature invasion, rainwater invasion, insect and mouse invasion and impact damage, and the above processes can be:
according to the output result, the identification target is set according to the display image on the picture, for example, the display image of rainwater invasion is a dark rainwater invasion part in the picture, the display picture of insect and mouse invasion is an insect and mouse in the picture, and the display image of impact damage is picture shaking or shaking.
302. Setting image characteristic elements corresponding to the identification targets;
specifically, the image feature element includes shape information, shape change duration, and shake or wobble in the screen.
303. Identifying and extracting image characteristic elements in the image according to the fault diagnosis model;
specifically, a large number of pictures in which the shape information is located, pictures in which the shape change duration is located, and pictures in shaking or shaking are obtained and used as training samples to train the fault diagnosis model;
the image is input to the failure diagnosis model, and the output result is an abnormal picture, namely a picture containing shape information, a picture containing shape change duration time and a picture when shaking or shaking.
304. Optimizing the extracted image characteristic elements, diagnosing on the basis of a fault diagnosis model according to the optimized image characteristic elements, and outputting a diagnosis result.
Specifically, the process of optimizing the extracted image feature elements may be:
clipping the picture to obtain an image only comprising shape information, a plurality of images only comprising shape changes (the shape information in the plurality of images is different in size and continuous in time), and a shaking picture;
The optimization process may be implemented by a depth recognition algorithm, which is not limited in the embodiment of the present invention.
Optionally, the detecting the abnormal image by the image acquisition module in step 104 includes:
401. identifying difference data between the current picture and the previous picture acquired by the image acquisition module;
specifically, the process may be implemented by identifying a difference in pixel value between a current picture and a previous picture, and the embodiment of the present invention is not limited to specific identification.
402. Calculating the area of the abnormal picture in the whole picture based on the difference data;
the above procedure is the same as that described in step 304, and will not be described again here.
403. Based on the fault diagnosis model, targets within the region are identified.
The above procedure is the same as that described in step 304, and will not be described again here.
Optionally, starting the diagnostic model of the sensor module in step 104, and outputting the diagnostic result includes:
501. identifying fault description data according to the target; the fault description data comprise picture shake, spark or smoke generated in the picture and foreign matters appearing on the picture, wherein the foreign matters comprise water stains and worm mice;
specifically, the process of generating the spark or the smoke in the frame is the same as that described in step 304, and will not be described again.
502. And identifying fault components and related components on the basis of a fault diagnosis model according to the fault description data and the data perceived by the sensor module, and outputting a diagnosis result.
Specifically, acquiring the occurrence time of the fault contained in the fault description data;
acquiring sampling time of abnormal data contained in data perceived by a sensor module;
and inputting the fault occurrence time and the sampling time into a fault diagnosis model, and outputting a fault component and a related component.
Optionally, the learning model based on the multi-scale depth feature in step 107 includes:
601. setting a feature extractor on the basis of a convolution kernel of multi-scale learning through a plurality of acceptance units;
specifically, for the multi-scale learning convolution kernel, the multi-scale learning convolution kernel is optimized through a plurality of acceptance units, and the optimized multi-scale learning convolution kernel is set as a feature extractor.
602. Based on the feature extractor, extracting features of monitoring data of key components in the optical distribution box;
specifically, the process of extracting the features of the above process includes text (data) extraction and image extraction, and the embodiment of the present invention does not limit the specific extraction manner.
603. According to the extracted characteristic data, establishing a deep learning model corresponding to the key components;
604. and optimizing the deep learning model based on the cross entropy classification loss optimization target.
Specifically, the cross entropy is set as a loss function of the deep learning model.
It should be noted that, the multi-scale deep feature learning model (i.e., the fault diagnosis model) in the embodiment of the present invention at least includes a multi-scale deep feature learning model based on text extraction and recognition, where the multi-scale deep feature learning model is mainly used for performing fault diagnosis with abnormal data as an input value;
in addition, the multi-scale deep feature learning model further comprises a multi-scale deep feature learning model based on image extraction and recognition, and the multi-scale deep feature learning model is mainly used for performing fault diagnosis by taking an abnormal picture as an input value.
Optionally, after step 106, the method further comprises:
the monitoring server periodically updates and issues the fault diagnosis model to the optical cable cross connecting cabinet, so that the accuracy and reliability of the fault diagnosis model identification are improved.
Referring to fig. 2, there is provided an optical cable cross-connecting box bearing internal monitoring system, at least including a monitoring server and a plurality of optical cable cross-connecting boxes, the optical cable cross-connecting boxes being configured with at least a diagnosis module, an image acquisition module, a sensor module and a transmission module; the image acquisition module, the sensor module and the transmission module are connected with a bearing platform arranged in the optical cable cross connecting cabinet through universal interfaces; the sensor module comprises a temperature sensor, a humidity sensor, a smoke sensor and a monitoring unit for monitoring whether components and parts are normally operated; wherein:
The diagnosis module is used for acquiring the data perceived by the sensor module and the image acquisition module in real time, generating a monitoring log, and uploading and recording the monitoring log in real time;
the diagnosis module is used for starting a fault diagnosis model of the image acquisition module when the sensor module detects abnormal data and outputting a diagnosis result;
the transmission module is used for setting an abnormal event according to the abnormal data and transmitting the abnormal event to the monitoring server, wherein the abnormal event at least comprises the abnormal data and a plurality of groups of data related to the abnormal data;
the diagnosis module is also used for starting a fault diagnosis model of the sensor module and outputting a diagnosis result when the image acquisition module detects an abnormal picture;
the transmission module is used for acquiring the difference image according to the abnormal picture and transmitting the difference image to the monitoring server,
the transmission module is used for uploading and recording the diagnosis result to the monitoring server;
wherein, the diagnosis module is still used for:
setting a fault diagnosis model based on the multi-scale depth feature learning model, and setting an abnormal picture and abnormal data as feature data;
based on an Adam optimization algorithm, optimizing and updating parameters of the fault diagnosis model.
Optionally, the diagnosis module is used for:
Setting an identification target according to the output result of the judgment model;
setting image characteristic elements corresponding to the identification targets;
identifying and extracting image characteristic elements in the image according to the fault diagnosis model;
optimizing the extracted image characteristic elements, diagnosing on the basis of a fault diagnosis model according to the optimized image characteristic elements, and outputting a diagnosis result.
Optionally, the image acquisition module is used for:
identifying difference data between the current picture and the previous picture acquired by the image acquisition module;
calculating the area of the abnormal picture in the whole picture based on the difference data;
based on the fault diagnosis model, targets within the region are identified.
Optionally, the diagnosis module is used for:
identifying fault description data according to the target; the fault description data comprises picture shake, spark or smoke generated in a picture and foreign matters appearing on the picture;
and identifying fault components and related components on the basis of a fault diagnosis model according to the fault description data and the data perceived by the sensor module, and outputting a diagnosis result.
Optionally, the diagnostic module is further configured to:
setting a feature extractor on the basis of a convolution kernel of multi-scale learning through a plurality of acceptance units;
Based on the feature extractor, extracting features of monitoring data of key components in the optical distribution box;
according to the extracted characteristic data, establishing a deep learning model corresponding to the key components;
and optimizing the deep learning model based on the cross entropy classification loss optimization target.
Alternatively to this, the method may comprise,
the monitoring server is also used for periodically updating and issuing a fault diagnosis model to the optical cable cross-connecting cabinet.
Referring to fig. 3, there is provided an optical cable cross-connect box including a diagnosis module, an image acquisition module, a sensor module, and a transmission module; the image acquisition module, the sensor module and the transmission module are connected with a bearing platform arranged in the optical cable cross connecting cabinet through universal interfaces; the sensor module comprises a temperature sensor, a humidity sensor, a smoke sensor and a monitoring unit for monitoring whether components and parts are normally operated; wherein:
the diagnosis module is used for acquiring the data perceived by the sensor module and the image acquisition module in real time, generating a monitoring log, and uploading and recording the monitoring log in real time;
the diagnosis module is used for starting a fault diagnosis model of the image acquisition module when the sensor module detects abnormal data and outputting a diagnosis result;
The transmission module is used for setting an abnormal event according to the abnormal data and transmitting the abnormal event to the monitoring server, wherein the abnormal event at least comprises the abnormal data and a plurality of groups of data related to the abnormal data;
the diagnosis module is also used for starting a fault diagnosis model of the sensor module and outputting a diagnosis result when the image acquisition module detects an abnormal picture;
the transmission module is used for acquiring the difference image according to the abnormal picture and transmitting the difference image to the monitoring server,
the transmission module is used for uploading and recording the diagnosis result to the monitoring server;
wherein, the diagnosis module is still used for:
setting a fault diagnosis model based on the multi-scale depth feature learning model, and setting an abnormal picture and abnormal data as feature data;
based on an Adam optimization algorithm, optimizing and updating parameters of the fault diagnosis model.
Optionally, the connection can be dismantled with the optical cable distributing box to load platform, and the optical cable distributing box outside is provided with display module assembly and input module assembly, and display module assembly and input module assembly pass through universal interface connection with load platform.
Optionally, the diagnosis module is used for:
setting an identification target according to the output result of the judgment model;
setting image characteristic elements corresponding to the identification targets;
Identifying and extracting image characteristic elements in the image according to the fault diagnosis model;
optimizing the extracted image characteristic elements, diagnosing on the basis of a fault diagnosis model according to the optimized image characteristic elements, and outputting a diagnosis result.
Optionally, the image acquisition module is used for:
identifying difference data between the current picture and the previous picture acquired by the image acquisition module;
calculating the area of the abnormal picture in the whole picture based on the difference data;
based on the fault diagnosis model, targets within the region are identified.
Optionally, the diagnosis module is used for:
identifying fault description data according to the target; the fault description data comprises picture shake, spark or smoke generated in a picture and foreign matters appearing on the picture;
and identifying fault components and related components on the basis of a fault diagnosis model according to the fault description data and the data perceived by the sensor module, and outputting a diagnosis result.
Optionally, the diagnostic module is further configured to:
setting a feature extractor on the basis of a convolution kernel of multi-scale learning through a plurality of acceptance units;
based on the feature extractor, extracting features of monitoring data of key components in the optical distribution box;
According to the extracted characteristic data, establishing a deep learning model corresponding to the key components;
and optimizing the deep learning model based on the cross entropy classification loss optimization target.
Any combination of the above optional solutions may be adopted to form an optional embodiment of the present invention, which is not described herein.
It should be noted that: when the optical cable cross-connecting box bearing internal monitoring system and the optical cable cross-connecting box provided by the embodiment execute the optical cable cross-connecting box bearing internal monitoring method, only the division of the functional modules is used for illustration, in practical application, the functional distribution can be completed by different functional modules according to the needs, namely, the internal structure of the system is divided into different functional modules so as to complete all or part of the functions described above. In addition, the system and method for monitoring the interior of the optical cable cross-connecting cabinet and the optical cable cross-connecting cabinet embodiment provided in the foregoing embodiments belong to the same concept, and detailed implementation processes of the system and method embodiments are detailed in the foregoing embodiments, and are not repeated here.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program for instructing relevant hardware, where the program may be stored in a computer readable storage medium, and the storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
Any combination of the technical features of the above embodiments may be performed (as long as there is no contradiction between the combination of the technical features), and for brevity of description, all of the possible combinations of the technical features of the above embodiments are not described; these examples, which are not explicitly written, should also be considered as being within the scope of the present description.
The invention has been described above with particularity and detail in connection with general description and specific embodiments. It should be noted that it is obvious that several variations and modifications can be made to these specific embodiments without departing from the spirit of the present invention, which are all within the scope of protection of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.
The foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the invention are intended to be included within the scope of the invention.
Claims (6)
1. The method is characterized by being applied to an optical cable cross connecting cabinet bearing internal monitoring system, wherein the system at least comprises a monitoring server and a plurality of optical cable cross connecting cabinets, and the optical cable cross connecting cabinets are at least provided with an image acquisition module, a sensor module and a transmission module; the image acquisition module, the sensor module and the transmission module are connected with a bearing platform arranged in the optical cable cross connecting cabinet through a universal interface; the sensor module comprises a temperature sensor, a humidity sensor, a smoke sensor and a monitoring unit for monitoring whether components and parts normally operate; the method comprises the following steps:
Acquiring data perceived by the sensor module and the image acquisition module in real time, generating a monitoring log, and uploading and recording the monitoring log in real time;
when the sensor module detects abnormal data, a fault diagnosis model of the image acquisition module is started, and a diagnosis result is output;
the transmission module sets an abnormal event according to the abnormal data and transmits the abnormal event to the monitoring server, wherein the abnormal event at least comprises the abnormal data and a plurality of groups of data related to the abnormal data;
when the image acquisition module detects an abnormal picture, a fault diagnosis model of the sensor module is started, and a diagnosis result is output;
the transmission module acquires a difference image according to the abnormal picture and transmits the difference image to the monitoring server,
the transmission module uploads and records the diagnosis result to the monitoring server;
wherein the method further comprises setting the fault diagnosis model, comprising:
setting a fault diagnosis model based on a multi-scale depth feature learning model, and setting the abnormal picture and the abnormal data as feature data;
Optimizing and updating parameters of the fault diagnosis model based on an Adam optimization algorithm;
the sensor module detecting abnormal data includes:
the judgment models are arranged corresponding to all the components;
calculating cross entropy of all components and optimizing the judgment model based on the cross entropy;
judging whether the detected data is abnormal or not according to the judging model;
starting a diagnosis model of the image acquisition module and outputting a diagnosis result:
setting an identification target according to the output result of the judgment model;
setting image characteristic elements corresponding to the identification targets;
identifying and extracting image characteristic elements in the image according to the fault diagnosis model;
optimizing the extracted image characteristic elements, diagnosing on the basis of the fault diagnosis model according to the optimized image characteristic elements, and outputting the diagnosis result;
the image acquisition module detecting the abnormal picture comprises the following steps:
identifying difference data between the current picture and the previous picture acquired by the image acquisition module;
calculating the area of the abnormal picture in the whole picture based on the difference data;
identifying a target within the region based on the fault diagnosis model;
The starting the diagnosis model of the sensor module and outputting the diagnosis result comprises the following steps:
identifying fault description data according to the target; the fault description data comprise picture shake, spark or smoke generated in a picture and foreign matters appearing in the picture;
and identifying fault components and related components on the basis of the fault diagnosis model according to the fault description data and the data perceived by the sensor module, and outputting a diagnosis result.
2. The method of claim 1, wherein the multi-scale depth feature based learning model comprises:
setting a feature extractor on the basis of a convolution kernel of multi-scale learning through a plurality of acceptance units;
based on the feature extractor, extracting features of monitoring data of key components in the optical cable cross connecting cabinet;
according to the extracted characteristic data, establishing a deep learning model corresponding to the key components;
and optimizing the deep learning model based on the cross entropy classification loss optimization target.
3. The method according to claim 2, characterized in that the method further comprises:
and periodically updating the monitoring server and issuing the fault diagnosis model to the optical cable cross connecting cabinet.
4. The system is characterized by at least comprising a monitoring server and a plurality of optical cable cross-connecting boxes, wherein the optical cable cross-connecting boxes are at least provided with a diagnosis module, an image acquisition module, a sensor module and a transmission module; the image acquisition module, the sensor module and the transmission module are connected with a bearing platform arranged in the optical cable cross connecting cabinet through a universal interface; the sensor module comprises a temperature sensor, a humidity sensor, a smoke sensor and a monitoring unit for monitoring whether components and parts normally operate; wherein:
the diagnosis module is used for acquiring the data perceived by the sensor module and the image acquisition module in real time, generating a monitoring log, and uploading and recording the monitoring log in real time;
the diagnosis module is used for starting a fault diagnosis model of the image acquisition module and outputting a diagnosis result when the sensor module detects abnormal data;
the transmission module is used for setting an abnormal event according to the abnormal data and transmitting the abnormal event to the monitoring server, wherein the abnormal event at least comprises the abnormal data and a plurality of groups of data related to the abnormal data;
The diagnosis module is also used for starting a fault diagnosis model of the sensor module and outputting a diagnosis result when the image acquisition module detects an abnormal picture;
the transmission module is used for acquiring a difference image according to the abnormal picture and transmitting the difference image to a monitoring server,
the transmission module is used for uploading the diagnosis result to the monitoring server and recording the diagnosis result;
wherein, the diagnosis module is further used for:
setting a fault diagnosis model based on a multi-scale depth feature learning model, and setting the abnormal picture and the abnormal data as feature data;
optimizing and updating parameters of the fault diagnosis model based on an Adam optimization algorithm;
the sensor module detecting abnormal data includes:
the judgment models are arranged corresponding to all the components;
calculating cross entropy of all components and optimizing the judgment model based on the cross entropy;
judging whether the detected data is abnormal or not according to the judging model;
starting a diagnosis model of the image acquisition module and outputting a diagnosis result:
setting an identification target according to the output result of the judgment model;
setting image characteristic elements corresponding to the identification targets;
Identifying and extracting image characteristic elements in the image according to the fault diagnosis model;
optimizing the extracted image characteristic elements, diagnosing on the basis of the fault diagnosis model according to the optimized image characteristic elements, and outputting the diagnosis result;
the image acquisition module detecting the abnormal picture comprises the following steps:
identifying difference data between the current picture and the previous picture acquired by the image acquisition module;
calculating the area of the abnormal picture in the whole picture based on the difference data;
identifying a target within the region based on the fault diagnosis model;
the starting the diagnosis model of the sensor module and outputting the diagnosis result comprises the following steps:
identifying fault description data according to the target; the fault description data comprise picture shake, spark or smoke generated in a picture and foreign matters appearing in the picture;
and identifying fault components and related components on the basis of the fault diagnosis model according to the fault description data and the data perceived by the sensor module, and outputting a diagnosis result.
5. The optical cable cross connecting box is characterized by comprising a diagnosis module, an image acquisition module, a sensor module and a transmission module; the image acquisition module, the sensor module and the transmission module are connected with a bearing platform arranged in the optical cable cross connecting cabinet through a universal interface; the sensor module comprises a temperature sensor, a humidity sensor, a smoke sensor and a monitoring unit for monitoring whether components and parts normally operate; wherein:
The diagnosis module is used for acquiring the data perceived by the sensor module and the image acquisition module in real time, generating a monitoring log, and uploading and recording the monitoring log in real time;
the diagnosis module is used for starting a fault diagnosis model of the image acquisition module and outputting a diagnosis result when the sensor module detects abnormal data;
the transmission module is used for setting an abnormal event according to the abnormal data and transmitting the abnormal event to the monitoring server, wherein the abnormal event at least comprises the abnormal data and a plurality of groups of data related to the abnormal data;
the diagnosis module is also used for starting a fault diagnosis model of the sensor module and outputting a diagnosis result when the image acquisition module detects an abnormal picture;
the transmission module is used for acquiring a difference image according to the abnormal picture and transmitting the difference image to the monitoring server,
the transmission module is used for uploading the diagnosis result to the monitoring server and recording the diagnosis result;
wherein, the diagnosis module is further used for:
setting a fault diagnosis model based on a multi-scale depth feature learning model, and setting the abnormal picture and the abnormal data as feature data;
Optimizing and updating parameters of the fault diagnosis model based on an Adam optimization algorithm;
the sensor module detecting abnormal data includes:
the judgment models are arranged corresponding to all the components;
calculating cross entropy of all components and optimizing the judgment model based on the cross entropy;
judging whether the detected data is abnormal or not according to the judging model;
starting a diagnosis model of the image acquisition module and outputting a diagnosis result:
setting an identification target according to the output result of the judgment model;
setting image characteristic elements corresponding to the identification targets;
identifying and extracting image characteristic elements in the image according to the fault diagnosis model;
optimizing the extracted image characteristic elements, diagnosing on the basis of the fault diagnosis model according to the optimized image characteristic elements, and outputting the diagnosis result;
the image acquisition module detecting the abnormal picture comprises the following steps:
identifying difference data between the current picture and the previous picture acquired by the image acquisition module;
calculating the area of the abnormal picture in the whole picture based on the difference data;
identifying a target within the region based on the fault diagnosis model;
The starting the diagnosis model of the sensor module and outputting the diagnosis result comprises the following steps:
identifying fault description data according to the target; the fault description data comprise picture shake, spark or smoke generated in a picture and foreign matters appearing in the picture;
and identifying fault components and related components on the basis of the fault diagnosis model according to the fault description data and the data perceived by the sensor module, and outputting a diagnosis result.
6. The optical cable cross-connecting cabinet of claim 5, wherein the bearing platform is detachably connected with the optical cable cross-connecting cabinet, a display module and an input module are arranged outside the optical cable cross-connecting cabinet, and the display module and the input module are connected with the bearing platform through a universal interface.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311196241.3A CN117232577B (en) | 2023-09-18 | 2023-09-18 | Optical cable distributing box bearing interior monitoring method and system and optical cable distributing box |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311196241.3A CN117232577B (en) | 2023-09-18 | 2023-09-18 | Optical cable distributing box bearing interior monitoring method and system and optical cable distributing box |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117232577A CN117232577A (en) | 2023-12-15 |
| CN117232577B true CN117232577B (en) | 2024-04-05 |
Family
ID=89090540
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311196241.3A Active CN117232577B (en) | 2023-09-18 | 2023-09-18 | Optical cable distributing box bearing interior monitoring method and system and optical cable distributing box |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117232577B (en) |
Citations (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101021474A (en) * | 2006-12-05 | 2007-08-22 | 中国科学院安徽光学精密机械研究所 | Opening gas multi-element monitoring instrument and monitoring method |
| CN105045256A (en) * | 2015-07-08 | 2015-11-11 | 北京泰乐德信息技术有限公司 | Rail traffic real-time fault diagnosis method and system based on data comparative analysis |
| CN111259921A (en) * | 2019-12-19 | 2020-06-09 | 杭州安脉盛智能技术有限公司 | Transformer sound anomaly detection method based on improved wavelet packet and deep learning |
| CN111985558A (en) * | 2020-08-19 | 2020-11-24 | 安徽蓝杰鑫信息科技有限公司 | Electric energy meter abnormity diagnosis method and system |
| CN111985561A (en) * | 2020-08-19 | 2020-11-24 | 安徽蓝杰鑫信息科技有限公司 | Fault diagnosis method and system for intelligent electric meter and electronic device |
| CN113298110A (en) * | 2021-03-24 | 2021-08-24 | 国网河北省电力有限公司沧州供电分公司 | Submarine cable fault diagnosis method, device and equipment |
| CN113469219A (en) * | 2021-06-08 | 2021-10-01 | 中国地质大学（武汉） | Rotary machine fault diagnosis method under complex working condition based on element transfer learning |
| CN114065613A (en) * | 2021-10-27 | 2022-02-18 | 中国华能集团清洁能源技术研究院有限公司 | Multi-working-condition process industrial fault detection and diagnosis method based on deep migration learning |
| WO2022077605A1 (en) * | 2020-10-15 | 2022-04-21 | 青岛理工大学 | Wind turbine blade image-based damage detection and localization method |
| CN114492642A (en) * | 2022-01-27 | 2022-05-13 | 洛阳中重自动化工程有限责任公司 | Mechanical fault online diagnosis method for multi-scale element depth residual shrinkage network |
| CN115204368A (en) * | 2022-07-14 | 2022-10-18 | 绍兴羊羽智能芯片有限公司 | Aircraft engine fault diagnosis method based on intelligent chip technology |
| KR102477088B1 (en) * | 2022-04-07 | 2022-12-14 | 세이지리서치 주식회사 | A method for adjusting an inspection area and a device for adjusting an inspection area |
| CN115560983A (en) * | 2022-09-30 | 2023-01-03 | 哈尔滨理工大学 | Rolling bearing fault diagnosis method and system under different working conditions based on federal feature transfer learning |
| CN115828088A (en) * | 2022-11-14 | 2023-03-21 | 国网安徽省电力有限公司电力科学研究院 | High-voltage shunt reactor vibration abnormity fault diagnosis method based on deep learning |
| CN115865630A (en) * | 2023-02-28 | 2023-03-28 | 广东名阳信息科技有限公司 | Network equipment fault diagnosis method and system based on deep learning |
| CN116026593A (en) * | 2022-12-19 | 2023-04-28 | 山东大学 | Cross-working-condition rolling bearing fault targeted migration diagnosis method and system |
| CN116152179A (en) * | 2022-12-30 | 2023-05-23 | 中国电信股份有限公司 | Method, device, equipment and storage medium for detecting optical cable cross connecting cabinet |
| CN116244646A (en) * | 2022-12-29 | 2023-06-09 | 浪潮云信息技术股份公司 | Machine learning-based big data platform fault diagnosis method and system |
| CN116292147A (en) * | 2023-04-14 | 2023-06-23 | 华能(福建连城)新能源有限公司 | Fan transmission system fault diagnosis device and method |
| CN116541771A (en) * | 2023-04-04 | 2023-08-04 | 河北工业大学 | Unbalanced sample bearing fault diagnosis method based on multi-scale feature fusion |
| CN116560341A (en) * | 2023-05-25 | 2023-08-08 | 重庆大学 | Industrial robot fault diagnosis model and fault diagnosis method |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110954312B (en) * | 2020-02-19 | 2020-11-20 | 北京化工大学 | Reciprocating mechanical fault diagnosis method based on keyless phase whole-cycle signal |
| CN111751763B (en) * | 2020-06-08 | 2021-08-10 | 武汉大学 | Power transformer winding fault diagnosis method based on GSMallat-NIN-CNN network |
-
2023
- 2023-09-18 CN CN202311196241.3A patent/CN117232577B/en active Active
Patent Citations (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101021474A (en) * | 2006-12-05 | 2007-08-22 | 中国科学院安徽光学精密机械研究所 | Opening gas multi-element monitoring instrument and monitoring method |
| CN105045256A (en) * | 2015-07-08 | 2015-11-11 | 北京泰乐德信息技术有限公司 | Rail traffic real-time fault diagnosis method and system based on data comparative analysis |
| CN111259921A (en) * | 2019-12-19 | 2020-06-09 | 杭州安脉盛智能技术有限公司 | Transformer sound anomaly detection method based on improved wavelet packet and deep learning |
| CN111985558A (en) * | 2020-08-19 | 2020-11-24 | 安徽蓝杰鑫信息科技有限公司 | Electric energy meter abnormity diagnosis method and system |
| CN111985561A (en) * | 2020-08-19 | 2020-11-24 | 安徽蓝杰鑫信息科技有限公司 | Fault diagnosis method and system for intelligent electric meter and electronic device |
| WO2022077605A1 (en) * | 2020-10-15 | 2022-04-21 | 青岛理工大学 | Wind turbine blade image-based damage detection and localization method |
| CN113298110A (en) * | 2021-03-24 | 2021-08-24 | 国网河北省电力有限公司沧州供电分公司 | Submarine cable fault diagnosis method, device and equipment |
| CN113469219A (en) * | 2021-06-08 | 2021-10-01 | 中国地质大学（武汉） | Rotary machine fault diagnosis method under complex working condition based on element transfer learning |
| CN114065613A (en) * | 2021-10-27 | 2022-02-18 | 中国华能集团清洁能源技术研究院有限公司 | Multi-working-condition process industrial fault detection and diagnosis method based on deep migration learning |
| CN114492642A (en) * | 2022-01-27 | 2022-05-13 | 洛阳中重自动化工程有限责任公司 | Mechanical fault online diagnosis method for multi-scale element depth residual shrinkage network |
| KR102477088B1 (en) * | 2022-04-07 | 2022-12-14 | 세이지리서치 주식회사 | A method for adjusting an inspection area and a device for adjusting an inspection area |
| CN115204368A (en) * | 2022-07-14 | 2022-10-18 | 绍兴羊羽智能芯片有限公司 | Aircraft engine fault diagnosis method based on intelligent chip technology |
| CN115560983A (en) * | 2022-09-30 | 2023-01-03 | 哈尔滨理工大学 | Rolling bearing fault diagnosis method and system under different working conditions based on federal feature transfer learning |
| CN115828088A (en) * | 2022-11-14 | 2023-03-21 | 国网安徽省电力有限公司电力科学研究院 | High-voltage shunt reactor vibration abnormity fault diagnosis method based on deep learning |
| CN116026593A (en) * | 2022-12-19 | 2023-04-28 | 山东大学 | Cross-working-condition rolling bearing fault targeted migration diagnosis method and system |
| CN116244646A (en) * | 2022-12-29 | 2023-06-09 | 浪潮云信息技术股份公司 | Machine learning-based big data platform fault diagnosis method and system |
| CN116152179A (en) * | 2022-12-30 | 2023-05-23 | 中国电信股份有限公司 | Method, device, equipment and storage medium for detecting optical cable cross connecting cabinet |
| CN115865630A (en) * | 2023-02-28 | 2023-03-28 | 广东名阳信息科技有限公司 | Network equipment fault diagnosis method and system based on deep learning |
| CN116541771A (en) * | 2023-04-04 | 2023-08-04 | 河北工业大学 | Unbalanced sample bearing fault diagnosis method based on multi-scale feature fusion |
| CN116292147A (en) * | 2023-04-14 | 2023-06-23 | 华能(福建连城)新能源有限公司 | Fan transmission system fault diagnosis device and method |
| CN116560341A (en) * | 2023-05-25 | 2023-08-08 | 重庆大学 | Industrial robot fault diagnosis model and fault diagnosis method |
Non-Patent Citations (4)
| Title |
|---|
| 基于多尺度排列熵和支持向量机的风力发电机组齿轮箱振动故障诊断;刘骊;贾嵘;李涛涛;尹浩霖;马喜平;郭泽维;;电网与清洁能源;20170525(第05期);全文 * |
| 基于深度学习的输变电设备异常发热点红外图片目标检测方法;刘云鹏;裴少通;武建华;纪欣欣;梁利辉;;南方电网技术;20190220(第02期);全文 * |
| 综合性SDG故障诊断架构;吕宁;熊智华;王雄;;计算机与应用化学;20100128(第01期);全文 * |
| 钻进参数实时监测与故障诊断技术;王江萍;孟祥芹;鲍泽富;;钻采工艺;20080125(第01期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117232577A (en) | 2023-12-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7312919B2 (en) | Method and Apparatus, Device and Storage Medium for Determining Operational State of Photovoltaic Array | |
| EP3531386A1 (en) | Fire monitoring system | |
| CN110084165B (en) | Intelligent identification and early warning method for abnormal events in open scene of power field based on edge calculation | |
| CN115527203A (en) | Grain drying remote control method and system based on Internet of things | |
| CN112924471B (en) | Equipment fault diagnosis system and diagnosis method thereof | |
| KR101825725B1 (en) | Method and device for diagnosing deterioration of solar cell module | |
| CN111446920A (en) | Photovoltaic power station monitoring method, device and system | |
| CN116055690B (en) | Method and equipment for processing machine room monitoring video | |
| CN113343779B (en) | Environment abnormality detection method, device, computer equipment and storage medium | |
| CN113419298B (en) | Multi-parameter hydrological meteorological data acquisition device | |
| CN111045889A (en) | Closed network equipment state monitoring system, method and device and readable storage medium | |
| CN117232577B (en) | Optical cable distributing box bearing interior monitoring method and system and optical cable distributing box | |
| CN111400114A (en) | Deep recursion network-based big data computer system fault detection method and system | |
| CN113807227A (en) | Safety monitoring method, device and equipment based on image recognition and storage medium | |
| CN113066070A (en) | Multi-source data fusion interaction method in three-dimensional scene | |
| CN115988182B (en) | Digital twinning-oriented remote video monitoring method | |
| CN112524077A (en) | Method, device and system for detecting fan fault | |
| CN113850144A (en) | Video reliability automatic inspection system based on image recognition | |
| CN111885349B (en) | Pipe gallery abnormality detection system and method | |
| CN116823233B (en) | User data processing method and system based on full-period operation and maintenance | |
| CN115937877A (en) | Information collection method and device, electronic equipment and information collection system | |
| Pandya et al. | Sensor Data Validation for IoT Applications | |
| KR20230059945A (en) | Diagnostic kits for installation enviroment of energy storage system based on deep-learning | |
| CN116591911A (en) | Intelligent detection operation and maintenance system and method facing to offshore wind turbine generator set | |
| JP2022120480A (en) | Analysis system, analysis device, analysis method, and program |
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 |