CN109063854A - Intelligent O&M cloud platform system and its control method - Google Patents
Intelligent O&M cloud platform system and its control method Download PDFInfo
- Publication number
- CN109063854A CN109063854A CN201810969256.1A CN201810969256A CN109063854A CN 109063854 A CN109063854 A CN 109063854A CN 201810969256 A CN201810969256 A CN 201810969256A CN 109063854 A CN109063854 A CN 109063854A
- Authority
- CN
- China
- Prior art keywords
- layer
- cloud platform
- platform system
- state information
- intelligence
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Operations Research (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Quality & Reliability (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computer And Data Communications (AREA)
Abstract
The present invention provides a kind of intelligent O&M cloud platform system and its control methods, are related to intelligent O&M technical field.Intelligent O&M cloud platform in the embodiment of the present application realizes the test to headend equipment running state information, by calling the corresponding test environment of headend equipment so as to confirm whether headend equipment breaks down by running state information.The intelligence O&M cloud platform system can handle the running state information of a large amount of headend equipments simultaneously, improve equipment O&M efficiency.
Description
Technical field
The present invention relates to system O&M technical fields, in particular to a kind of intelligent O&M cloud platform system and its control
Method processed.
Background technique
During the operation and maintenance of various equipment, it is often necessary to determine whether equipment occurs according to the operating status of equipment
Failure.Will be more cumbersome for the maintenance work of large number of equipment, a large amount of operation information can not be timely handled, reduction is set
The efficiency of standby operation and maintenance.
Summary of the invention
In view of this, the present invention provides a kind of intelligent O&M cloud platform system and its control methods.
Technical solution provided by the invention is as follows:
A kind of control method of intelligence O&M cloud platform system, the intelligence O&M cloud platform system and at least one front end
Equipment connection, the control method include:
Obtain the running state information of at least one headend equipment；
According to the identification information of the headend equipment, set of state information corresponding with the headend equipment is established；
Test environment corresponding with the headend equipment is called, the set of state information is tested；
Determine whether the running state information with the presence or absence of fault message, is broken down with the determination headend equipment.
Further, the intelligent O&M cloud platform system uses small-sized convolution neural network and each front end in advance
The corresponding fault message set of equipment, the step that the set of state information is handled according to preset deep learning algorithm
Suddenly include:
Based on the fault message set, the set of state information is identified using large-scale convolutional neural networks；
It determines in the set of state information with the presence or absence of fault message.
Further, the intelligent O&M cloud platform system includes multiple cluster servers, the intelligence O&M cloud platform
System includes: using the method for corresponding with each headend equipment fault message set of small-sized convolution neural network in advance
Build convolutional neural networks model；
The convolutional neural networks model is trained using the cluster server, to obtain the small-sized convolution mind
Through network and large-scale convolutional neural networks.
Further, the convolutional neural networks model includes the first convolutional layer, the first maximum pond layer, first partial sound
Layer, the second convolutional layer, the second local acknowledgement normalization layer, the second maximum pond layer, first linear sharp based on amendment should be normalized
Full articulamentum living, the second full articulamentum and output function layer linearly activated based on amendment；Wherein:
First convolutional layer rectifies linear activation for realizing convolution sum, and first convolutional layer is for passing through filter
Each bar state information in the set of state information is filtered, the characteristic value of every bar state information is obtained；
Described first maximum pond layer is used in the status information of preset quantity, and selected characteristic is worth maximum value as defeated
It is worth out；
The first partial response normalization layer is for carrying out local acknowledgement's normalization；
Second convolutional layer is used to carry out the data Jing Guo normalized the linear activation of convolution sum rectification；
Second local acknowledgement normalization layer is used for by second convolutional layer, treated that data carry out part
Response normalization；
The second maximum pond layer is used to select from normalizing layer by second local acknowledgement treated in data
The maximum value of characteristic value is selected as output valve；
First convolutional layer, the first maximum pond layer, first partial response normalization layer, the second convolutional layer, second game
What response normalization layer in portion's was linearly activated based on the full articulamentum that linearly activates of amendment and second based on amendment by described first
Full articulamentum is connect with the output function layer；
The output function layer is used to carry out linear transformation to data to export result.
Further, the intelligent O&M cloud platform system further includes the client connecting with the cluster server, should
Method further include:
When determining that the headend equipment breaks down, generates fault cues corresponding with the headend equipment to break down and believe
Breath, so that the client shows the headend equipment to break down.
The present invention also provides a kind of intelligent O&M cloud platform system, the intelligence O&M cloud platform system and at least one
Headend equipment connection, the intelligence O&M cloud platform system includes control device, which includes:
State information acquisition module, for obtaining the running state information of at least one headend equipment；
Set establishes module, for the identification information according to the headend equipment, establishes corresponding with the headend equipment
Set of state information；
Test module, for calling corresponding with headend equipment test environment, to the set of state information into
Row test；
Fault determination module, for determining the running state information with the presence or absence of fault message, with the determination front end
Whether equipment breaks down.
Further, the intelligent O&M cloud platform system uses small-sized convolution neural network and each front end in advance
The corresponding fault message set of equipment, the step that the set of state information is handled according to preset deep learning algorithm
Suddenly include:
Based on the fault message set, the set of state information is identified using large-scale convolutional neural networks；
It determines in the set of state information with the presence or absence of fault message.
Further, the intelligent O&M cloud platform system includes multiple cluster servers, the intelligence O&M cloud platform
System includes: using the method for corresponding with each headend equipment fault message set of small-sized convolution neural network in advance
Build convolutional neural networks model；
The convolutional neural networks model is trained using the cluster server, to obtain the small-sized convolution mind
Through network and large-scale convolutional neural networks.
Further, the convolutional neural networks model includes the first convolutional layer, the first maximum pond layer, first partial sound
Layer, the second convolutional layer, the second local acknowledgement normalization layer, the second maximum pond layer, first linear sharp based on amendment should be normalized
Full articulamentum living, the second full articulamentum and output function layer linearly activated based on amendment；Wherein:
First convolutional layer rectifies linear activation for realizing convolution sum, and first convolutional layer is for passing through filter
Each bar state information in the set of state information is filtered, the characteristic value of every bar state information is obtained；
Described first maximum pond layer is used in the status information of preset quantity, and selected characteristic is worth maximum value as defeated
It is worth out；
The first partial response normalization layer is for carrying out local acknowledgement's normalization；
Second convolutional layer is used to carry out the data Jing Guo normalized the linear activation of convolution sum rectification；
Second local acknowledgement normalization layer is used for by second convolutional layer, treated that data carry out part
Response normalization；
The second maximum pond layer is used to select from normalizing layer by second local acknowledgement treated in data
The maximum value of characteristic value is selected as output valve；
First convolutional layer, the first maximum pond layer, first partial response normalization layer, the second convolutional layer, second game
What response normalization layer in portion's was linearly activated based on the full articulamentum that linearly activates of amendment and second based on amendment by described first
Full articulamentum is connect with the output function layer；
The output function layer is used to carry out linear transformation to data to export result.
Further, the intelligent O&M cloud platform system further includes the client connecting with the cluster server, should
Intelligent O&M cloud platform system further include:
Display module, the headend equipment pair for when determining that the headend equipment breaks down, generating with breaking down
The fault cues information answered, so that the client shows the headend equipment to break down.
Intelligent O&M cloud platform in the embodiment of the present application, by calling the corresponding test environment of headend equipment, realization pair
The test of headend equipment running state information, so as to confirm whether headend equipment breaks down by running state information.
The intelligence O&M cloud platform system can handle the running state information of a large amount of headend equipments simultaneously, improve equipment O&M efficiency.
To enable the above objects, features and advantages of the present invention to be clearer and more comprehensible, preferred embodiment is cited below particularly, and cooperate
Appended attached drawing, is described in detail below.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only certain embodiments of the present invention, therefore is not construed as pair
The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 is a kind of system architecture schematic diagram of intelligent O&M cloud platform system provided in an embodiment of the present invention.
Fig. 2 is a kind of flow diagram of the control method of intelligent O&M cloud platform system provided in an embodiment of the present invention.
Fig. 3 is the son of step S104 in a kind of control method of intelligent O&M cloud platform system provided in an embodiment of the present invention
The flow diagram of step.
Fig. 4 is the functional module signal of control device in a kind of intelligent O&M cloud platform system provided in an embodiment of the present invention
Figure.
Icon: 100- control device；101- state information acquisition module；102- set establishes module；103- test module；
104- fault determination module.
Specific embodiment
Below in conjunction with attached drawing in the embodiment of the present invention, technical solution in the embodiment of the present invention carries out clear, complete
Ground description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.Usually exist
The component of the embodiment of the present invention described and illustrated in attached drawing can be arranged and be designed with a variety of different configurations herein.Cause
This, is not intended to limit claimed invention to the detailed description of the embodiment of the present invention provided in the accompanying drawings below
Range, but it is merely representative of selected embodiment of the invention.Based on the embodiment of the present invention, those skilled in the art are not doing
Every other embodiment obtained under the premise of creative work out, shall fall within the protection scope of the present invention.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, does not then need that it is further defined and explained in subsequent attached drawing.Meanwhile of the invention
In description, term " first ", " second " etc. are only used for distinguishing description, are not understood to indicate or imply relative importance.
The embodiment of the present application provides a kind of control method of intelligent O&M cloud platform system, as shown in Figure 1, the intelligence
O&M cloud platform system is connect at least one headend equipment, as shown in Fig. 2, the control method includes the following steps S101 to step
Rapid S104.
Step S101 obtains the running state information of at least one headend equipment.
Intelligent O&M cloud platform system may include multiple cluster servers, by being deployed on multiple cluster servers
Intelligent O&M cloud platform realizes the control of cluster server, and headend equipment may include the video camera etc. being arranged on urban road
Capture apparatus.Running state information can be sent to intelligent O&M cloud platform by these headend equipments in the process of running, operation
Status information includes but is not limited to the identification information of equipment, the focus information of capture apparatus or wide-angle information, PTZ camera
Holder operating status etc..
Step S102 establishes status information corresponding with the headend equipment according to the identification information of the headend equipment
Set.
Since the headend equipment of intelligent O&M cloud platform system connection is large number of, if believed single a certain bar state
Breath, which carries out analysis, possibly can not determine the accurate status of headend equipment, and intelligent O&M cloud platform system can pass through headend equipment
All status informations of a certain headend equipment are combined into corresponding set of state information by identification information.
Step S103 calls test environment corresponding with the headend equipment, surveys to the set of state information
Examination.
Step S104, determine the running state information with the presence or absence of fault message, with the determination headend equipment whether
It breaks down.
Its use environment of different headend equipments and status information are different froms, in the state to a certain headend equipment
When information aggregate carries out accident analysis, need that corresponding test environment is called to be tested.It, can simultaneously when carrying out fault verification
To be trained in advance to the fault condition of headend equipment using deep learning, do well so as to be judged automatically by model
Fault message in information aggregate.
Detailed, the intelligence O&M cloud platform system is set using small-sized convolution neural network with each front end in advance
Standby corresponding fault message set, as shown in figure 3, the step can also include following sub-step.
Sub-step S141 is based on the fault message set, using large-scale convolutional neural networks to the status information collection
Conjunction is identified.
Intelligent O&M cloud platform system can be by building convolutional neural networks model in advance；Utilize the cluster server
The convolutional neural networks model is trained, to obtain the small-sized convolutional neural networks and large-scale convolutional neural networks.
The convolutional neural networks model includes the first convolutional layer, the first maximum pond layer, first partial response normalization
Full articulamentum that layer, the second convolutional layer, the second local acknowledgement normalization layer, first are linearly activated based on amendment, second are based on repairing
The full articulamentum and output function layer of linear positive activation；Wherein:
First convolutional layer rectifies linear activation for realizing convolution sum, and first convolutional layer is for passing through filter
Each bar state information in the set of state information is filtered, the characteristic value of every bar state information is obtained；Described first maximum pond
Change layer to be used in the status information of preset quantity, the maximum value of selected characteristic value is used as output valve；The first partial response
Normalization layer is for carrying out local acknowledgement's normalization；Second convolutional layer is for rolling up the data Jing Guo normalized
Product and the linear activation of rectification；Second local acknowledgement normalization layer is used for by second convolutional layer treated data
Carry out local acknowledgement's normalization；Described second maximum pond layer is used for from after second local acknowledgement normalization layer processing
Data in select the maximum value of characteristic value as output valve；First convolutional layer, the first maximum pond layer, first partial are rung
Layer, the second convolutional layer, the second local acknowledgement normalization layer should be normalized to connect entirely by described first based on what amendment linearly activated
Layer and second is connect to connect based on the full articulamentum linearly activated is corrected with the output function layer；The output function layer for pair
Data carry out linear transformation to export result.
After convolutional neural networks construct, it can use intelligent O&M cloud platform system and be trained, it is small-sized to obtain
Convolutional neural networks model and large-scale convolutional neural networks model.Intelligent O&M cloud platform carry out status information analysis when,
Multiple servers in cluster server can be divided into multiple groups, each group executes one or more status information collection
The processing of conjunction.Under usual state, a server executes the analysis of the set of state information of one or more headend equipments, thus
Realize the parallelization training and processing of deep learning training pattern.
Sub-step S142 is determined in the set of state information with the presence or absence of fault message.
Convolutional neural networks model based on cluster server foundation in the training process, can have training speed faster
Degree shortens the training time, and its accuracy rate when status information determines of the convolutional neural networks after training is also higher.
Study by convolutional neural networks model to fault message is input to by the set of state information of headend equipment
After convolutional neural networks model, it can be determined which status information in the information aggregate that does well is that occur under malfunction,
So as to judge headend equipment whether failure.
In another embodiment, the intelligent O&M cloud platform system further includes connecting with the cluster server
Client, this method are further comprising the steps of.
Step S105 is generated corresponding with the headend equipment to break down when determining that the headend equipment breaks down
Fault cues information, so that the client shows the headend equipment to break down.
After fault message has been determined by convolutional neural networks model, it can determine that event occurs in corresponding headend equipment
Barrier, intelligent O&M cloud platform system can be generated prompt information and is shown in client, so as to so that client can and
When understand headend equipment real-time status.
In conclusion the intelligent O&M cloud platform in the embodiment of the present application, by calling the corresponding test wrapper of headend equipment
The test to headend equipment running state information is realized in border, so as to whether confirm headend equipment by running state information
It breaks down.The intelligence O&M cloud platform system can handle the running state information of a large amount of headend equipments simultaneously, improve equipment
O&M efficiency.
The present invention also provides a kind of intelligent O&M cloud platform system, the intelligence O&M cloud platform system and at least one
Headend equipment connection, the intelligence O&M cloud platform system includes control device 100, as shown in figure 4, the control device 100 wraps
It includes:
State information acquisition module 101, for obtaining the running state information of at least one headend equipment；
Set establishes module 102, for the identification information according to the headend equipment, establishes corresponding with the headend equipment
Set of state information；
Test module 103, for calling test environment corresponding with the headend equipment, to the set of state information
It is tested；
Fault determination module 104, for determine the running state information with the presence or absence of fault message, with determination it is described before
Whether end equipment breaks down.
Further, the intelligent O&M cloud platform system uses small-sized convolution neural network and each front end in advance
The corresponding fault message set of equipment, the step that the set of state information is handled according to preset deep learning algorithm
Suddenly include:
Based on the fault message set, the set of state information is identified using large-scale convolutional neural networks；
It determines in the set of state information with the presence or absence of fault message.
Further, the intelligent O&M cloud platform system includes multiple cluster servers, the intelligence O&M cloud platform
System includes: using the method for corresponding with each headend equipment fault message set of small-sized convolution neural network in advance
Build convolutional neural networks model；
The convolutional neural networks model is trained using the cluster server, to obtain the small-sized convolution mind
Through network and large-scale convolutional neural networks.
Further, the convolutional neural networks model includes the first convolutional layer, the first maximum pond layer, first partial sound
Should normalize layer, the second convolutional layer, the second local acknowledgement normalization layer, first linearly activated based on amendment full articulamentum, the
Two full articulamentums and output function layer based on modified line activation；Wherein:
First convolutional layer rectifies linear activation for realizing convolution sum, and first convolutional layer is for passing through filter
Each bar state information in the set of state information is filtered, the characteristic value of every bar state information is obtained；
Described first maximum pond layer is used in the status information of preset quantity, and selected characteristic is worth maximum value as defeated
It is worth out；
The first partial response normalization layer is for carrying out local acknowledgement's normalization；
Second convolutional layer is used to carry out the data Jing Guo normalized the linear activation of convolution sum rectification；
Second local acknowledgement normalization layer is used for by second convolutional layer, treated that data carry out part
Response normalization；
The second maximum pond layer is used to select from normalizing layer by second local acknowledgement treated in data
The maximum value of characteristic value is selected as output valve；
First convolutional layer, the first maximum pond layer, first partial response normalization layer, the second convolutional layer, second game
What response normalization layer in portion's was linearly activated based on the full articulamentum that linearly activates of amendment and second based on amendment by described first
Full articulamentum is connect with the output function layer；
The output function layer is used to carry out linear transformation to data to export result.
Further, the intelligent O&M cloud platform system further includes the client connecting with the cluster server, should
Intelligent O&M cloud platform system further include:
Display module, the headend equipment pair for when determining that the headend equipment breaks down, generating with breaking down
The fault cues information answered, so that the client shows the headend equipment to break down.
In several embodiments provided herein, it should be understood that disclosed device and method can also pass through
Other modes are realized.The apparatus embodiments described above are merely exemplary, for example, flow chart and block diagram in attached drawing
Show the device of multiple embodiments according to the present invention, the architectural framework in the cards of method and computer program product,
Function and operation.In this regard, each box in flowchart or block diagram can represent the one of a module, section or code
Part, a part of the module, section or code, which includes that one or more is for implementing the specified logical function, to be held
Row instruction.It should also be noted that function marked in the box can also be to be different from some implementations as replacement
The sequence marked in attached drawing occurs.For example, two continuous boxes can actually be basically executed in parallel, they are sometimes
It can execute in the opposite order, this depends on the function involved.It is also noted that every in block diagram and or flow chart
The combination of box in a box and block diagram and or flow chart can use the dedicated base for executing defined function or movement
It realizes, or can realize using a combination of dedicated hardware and computer instructions in the system of hardware.
In addition, each functional module in each embodiment of the present invention can integrate one independent portion of formation together
Point, it is also possible to modules individualism, an independent part can also be integrated to form with two or more modules.
It, can be with if the function is realized and when sold or used as an independent product in the form of software function module
It is stored in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, server or network equipment etc.) it performs all or part of the steps of the method described in the various embodiments of the present invention.
And storage medium above-mentioned includes: that USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
The various media that can store program code such as reservoir (RAM, Random Access Memory), magnetic or disk.It needs
Illustrate, herein, relational terms such as first and second and the like be used merely to by an entity or operation with
Another entity or operation distinguish, and without necessarily requiring or implying between these entities or operation, there are any this realities
The relationship or sequence on border.Moreover, the terms "include", "comprise" or its any other variant are intended to the packet of nonexcludability
Contain, so that the process, method, article or equipment for including a series of elements not only includes those elements, but also including
Other elements that are not explicitly listed, or further include for elements inherent to such a process, method, article, or device.
In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including the element
Process, method, article or equipment in there is also other identical elements.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.It should also be noted that similar label and letter exist
Similar terms are indicated in following attached drawing, therefore, once being defined in a certain Xiang Yi attached drawing, are then not required in subsequent attached drawing
It is further defined and explained.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can easily think of the change or the replacement, and should all contain
Lid is within protection scope of the present invention.Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. a kind of control method of intelligence O&M cloud platform system, which is characterized in that the intelligence O&M cloud platform system with extremely
Few headend equipment connection, the control method include:
Obtain the running state information of at least one headend equipment；
According to the identification information of the headend equipment, set of state information corresponding with the headend equipment is established；
Test environment corresponding with the headend equipment is called, the set of state information is tested；
Determine whether the running state information with the presence or absence of fault message, is broken down with the determination headend equipment.
2. the control method of intelligence O&M cloud platform system according to claim 1, which is characterized in that the intelligence O&M
Cloud platform system uses small-sized convolution neural network fault message set corresponding with each headend equipment in advance, according to
The step of preset deep learning algorithm handles the set of state information include:
Based on the fault message set, the set of state information is identified using large-scale convolutional neural networks；
It determines in the set of state information with the presence or absence of fault message.
3. the control method of intelligence O&M cloud platform system according to claim 1, which is characterized in that the intelligence O&M
Cloud platform system includes multiple cluster servers, and the intelligence O&M cloud platform system is built using small-sized convolutional neural networks in advance
The method of vertical fault message set corresponding with each headend equipment includes:
Build convolutional neural networks model；
The convolutional neural networks model is trained using the cluster server, to obtain the small-sized convolution nerve net
Network and large-scale convolutional neural networks.
4. the control method of intelligence O&M cloud platform system according to claim 3, which is characterized in that the convolutional Neural
Network model includes the first convolutional layer, the first maximum pond layer, first partial response normalization layer, the second convolutional layer, second game
Full articulamentum that portion's response normalization layer, the second maximum pond layer, first are linearly activated based on amendment, second based on amendment linearly
The full articulamentum and output function layer of activation；Wherein:
First convolutional layer rectifies linear activation for realizing convolution sum, and first convolutional layer is used to filter by filter
Each bar state information in the set of state information, obtains the characteristic value of every bar state information；
Described first maximum pond layer is used in the status information of preset quantity, and selected characteristic is worth maximum value as output
Value；
The first partial response normalization layer is for carrying out local acknowledgement's normalization；
Second convolutional layer is used to carry out the data Jing Guo normalized the linear activation of convolution sum rectification；
Second local acknowledgement normalization layer is used for by second convolutional layer, treated that data carry out local acknowledgement
Normalization；
The second maximum pond layer is used for the selection spy from by second local acknowledgement normalization layer treated data
The maximum value of value indicative is used as output valve；
First convolutional layer, the first maximum pond layer, first partial response normalization layer, the second convolutional layer, the second part are rung
Layer should be normalized and connected entirely based on the full articulamentum and second that amendment linearly activates based on what amendment linearly activated by described first
Layer is connect to connect with the output function layer；
The output function layer is used to carry out linear transformation to data to export result.
5. the control method of intelligence O&M cloud platform system according to claim 3, which is characterized in that the intelligence O&M
Cloud platform system further includes the client connecting with the cluster server, this method further include:
When determining that the headend equipment breaks down, fault cues information corresponding with the headend equipment to break down is generated,
So that the client shows the headend equipment to break down.
6. a kind of intelligence O&M cloud platform system, which is characterized in that the intelligence O&M cloud platform system and at least one front end
Equipment connection, the intelligence O&M cloud platform system includes control device, which includes:
State information acquisition module, for obtaining the running state information of at least one headend equipment；
Set establishes module, for the identification information according to the headend equipment, establishes state corresponding with the headend equipment
Information aggregate；
Test module surveys the set of state information for calling test environment corresponding with the headend equipment
Examination；
Fault determination module, for determining the running state information with the presence or absence of fault message, with the determination headend equipment
Whether break down.
7. intelligence O&M cloud platform system according to claim 6, which is characterized in that the intelligence O&M cloud platform system
Small-sized convolution neural network fault message set corresponding with each headend equipment is used in advance, according to preset depth
The step of learning algorithm handles the set of state information include:
Based on the fault message set, the set of state information is identified using large-scale convolutional neural networks；
It determines in the set of state information with the presence or absence of fault message.
8. intelligence O&M cloud platform system according to claim 6, which is characterized in that the intelligence O&M cloud platform system
Including multiple cluster servers, the intelligence O&M cloud platform system use in advance small-sized convolution neural network and it is each before
The method of the corresponding fault message set of end equipment includes:
Build convolutional neural networks model；
The convolutional neural networks model is trained using the cluster server, to obtain the small-sized convolution nerve net
Network and large-scale convolutional neural networks.
9. intelligence O&M cloud platform system according to claim 8, which is characterized in that the convolutional neural networks model packet
Include the first convolutional layer, the first maximum pond layer, first partial response normalization layer, the second convolutional layer, second local acknowledgement's normalizing
Change layer, the second maximum pond layer, first linearly activated based on amendment full articulamentum, second complete connected based on what amendment linearly activated
Connect layer and output function layer；Wherein:
First convolutional layer rectifies linear activation for realizing convolution sum, and first convolutional layer is used to filter by filter
Each bar state information in the set of state information, obtains the characteristic value of every bar state information；
Described first maximum pond layer is used in the status information of preset quantity, and selected characteristic is worth maximum value as output
Value；
The first partial response normalization layer is for carrying out local acknowledgement's normalization；
Second convolutional layer is used to carry out the data Jing Guo normalized the linear activation of convolution sum rectification；
Second local acknowledgement normalization layer is used for by second convolutional layer, treated that data carry out local acknowledgement
Normalization；
The second maximum pond layer is used for the selection spy from by second local acknowledgement normalization layer treated data
The maximum value of value indicative is used as output valve；
First convolutional layer, the first maximum pond layer, first partial response normalization layer, the second convolutional layer, the second part are rung
Layer should be normalized and connected entirely based on the full articulamentum and second that amendment linearly activates based on what amendment linearly activated by described first
Layer is connect to connect with the output function layer；
The output function layer is used to carry out linear transformation to data to export result.
10. intelligence O&M cloud platform system according to claim 8, which is characterized in that the intelligence O&M cloud platform system
System further includes the client connecting with the cluster server, the intelligence O&M cloud platform system further include:
Display module, it is corresponding with the headend equipment to break down for generating when determining that the headend equipment breaks down
Fault cues information, so that the client shows the headend equipment to break down.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810969256.1A CN109063854A (en) | 2018-08-23 | 2018-08-23 | Intelligent O&M cloud platform system and its control method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810969256.1A CN109063854A (en) | 2018-08-23 | 2018-08-23 | Intelligent O&M cloud platform system and its control method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109063854A true CN109063854A (en) | 2018-12-21 |
Family
ID=64755980
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810969256.1A Pending CN109063854A (en) | 2018-08-23 | 2018-08-23 | Intelligent O&M cloud platform system and its control method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109063854A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110223411A (en) * | 2019-05-29 | 2019-09-10 | 张婧 | A kind of public water dispenser cruising inspection system and method |
| CN113691310A (en) * | 2021-08-13 | 2021-11-23 | 广东电网有限责任公司 | Fault monitoring method, device, equipment and storage medium of optical fiber link |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103914735A (en) * | 2014-04-17 | 2014-07-09 | 北京泰乐德信息技术有限公司 | Failure recognition method and system based on neural network self-learning |
| US20160300121A1 (en) * | 2014-04-01 | 2016-10-13 | Superfish Ltd. | Neural network image representation |
| CN106556427A (en) * | 2016-11-28 | 2017-04-05 | 国网山东省电力公司济宁供电公司 | A kind of transformer fault based reminding method and intelligent maintenance system |
| CN106650919A (en) * | 2016-12-23 | 2017-05-10 | 国家电网公司信息通信分公司 | Information system fault diagnosis method and device based on convolutional neural network |
| CN107506695A (en) * | 2017-07-28 | 2017-12-22 | 武汉理工大学 | Video monitoring equipment failure automatic detection method |
| KR101818394B1 (en) * | 2017-05-11 | 2018-01-12 | 울산대학교 산학협력단 | Method and apparatus for diagnosing facility condition |
| CN107679649A (en) * | 2017-09-13 | 2018-02-09 | 珠海格力电器股份有限公司 | Electric appliance fault prediction method and device, storage medium and electric appliance |
| CN107730017A (en) * | 2017-11-29 | 2018-02-23 | 马鞍山市科泰电气科技有限公司 | Intelligent metallurgical equipment operational diagnostics system |
| US20180082172A1 (en) * | 2015-03-12 | 2018-03-22 | William Marsh Rice University | Automated Compilation of Probabilistic Task Description into Executable Neural Network Specification |
| CN108107318A (en) * | 2017-11-03 | 2018-06-01 | 国网北京市电力公司 | The localization method and device of user malfunction |
| CN108319962A (en) * | 2018-01-29 | 2018-07-24 | 安徽大学 | A kind of Tool Wear Monitoring method based on convolutional neural networks |
| CN108337321A (en) * | 2018-03-14 | 2018-07-27 | 卡斯柯信号有限公司 | CBTC signalling arrangements cruising inspection system and method based on video intelligent identification |
| CN108376253A (en) * | 2018-03-05 | 2018-08-07 | 西南交通大学 | A kind of signal trouble monitoring method based on machine vision |
-
2018
- 2018-08-23 CN CN201810969256.1A patent/CN109063854A/en active Pending
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160300121A1 (en) * | 2014-04-01 | 2016-10-13 | Superfish Ltd. | Neural network image representation |
| CN103914735A (en) * | 2014-04-17 | 2014-07-09 | 北京泰乐德信息技术有限公司 | Failure recognition method and system based on neural network self-learning |
| US20180082172A1 (en) * | 2015-03-12 | 2018-03-22 | William Marsh Rice University | Automated Compilation of Probabilistic Task Description into Executable Neural Network Specification |
| CN106556427A (en) * | 2016-11-28 | 2017-04-05 | 国网山东省电力公司济宁供电公司 | A kind of transformer fault based reminding method and intelligent maintenance system |
| CN106650919A (en) * | 2016-12-23 | 2017-05-10 | 国家电网公司信息通信分公司 | Information system fault diagnosis method and device based on convolutional neural network |
| KR101818394B1 (en) * | 2017-05-11 | 2018-01-12 | 울산대학교 산학협력단 | Method and apparatus for diagnosing facility condition |
| CN107506695A (en) * | 2017-07-28 | 2017-12-22 | 武汉理工大学 | Video monitoring equipment failure automatic detection method |
| CN107679649A (en) * | 2017-09-13 | 2018-02-09 | 珠海格力电器股份有限公司 | Electric appliance fault prediction method and device, storage medium and electric appliance |
| CN108107318A (en) * | 2017-11-03 | 2018-06-01 | 国网北京市电力公司 | The localization method and device of user malfunction |
| CN107730017A (en) * | 2017-11-29 | 2018-02-23 | 马鞍山市科泰电气科技有限公司 | Intelligent metallurgical equipment operational diagnostics system |
| CN108319962A (en) * | 2018-01-29 | 2018-07-24 | 安徽大学 | A kind of Tool Wear Monitoring method based on convolutional neural networks |
| CN108376253A (en) * | 2018-03-05 | 2018-08-07 | 西南交通大学 | A kind of signal trouble monitoring method based on machine vision |
| CN108337321A (en) * | 2018-03-14 | 2018-07-27 | 卡斯柯信号有限公司 | CBTC signalling arrangements cruising inspection system and method based on video intelligent identification |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110223411A (en) * | 2019-05-29 | 2019-09-10 | 张婧 | A kind of public water dispenser cruising inspection system and method |
| CN113691310A (en) * | 2021-08-13 | 2021-11-23 | 广东电网有限责任公司 | Fault monitoring method, device, equipment and storage medium of optical fiber link |
| CN113691310B (en) * | 2021-08-13 | 2022-07-29 | 广东电网有限责任公司 | Fault monitoring method, device, equipment and storage medium of optical fiber link |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110674790B (en) | Abnormal scene processing method and system in video monitoring | |
| CN109101933A (en) | A kind of emotion-directed behavior visual analysis method based on artificial intelligence | |
| CN109446936A (en) | A kind of personal identification method and device for monitoring scene | |
| CN107169426A (en) | A kind of detection of crowd's abnormal feeling and localization method based on deep neural network | |
| CN105208325B (en) | The land resources monitoring and early warning method captured and compare analysis is pinpointed based on image | |
| CN105989268A (en) | Safety access method and system for human-computer identification | |
| CN109889538A (en) | User's anomaly detection method and system | |
| CN107527012A (en) | Make a dash across the red light monitoring method, device and monitoring processing equipment | |
| CN109141453A (en) | A kind of route guiding method and system | |
| CN109389146A (en) | Equipment state feedback method and system based on neural network image sorting algorithm | |
| CN109063977A (en) | A kind of no-induction transaction risk monitoring method and device | |
| CN109831648A (en) | Antitheft long-distance monitoring method, device, equipment and storage medium | |
| CN109063854A (en) | Intelligent O&M cloud platform system and its control method | |
| CN110390232A (en) | Confirm method, apparatus, server and the system of irregular driving | |
| CN106130762A (en) | A kind of network training comprehensive analysis method based on finite automaton | |
| CN113596844A (en) | Early warning method, device, medium and electronic equipment based on data information | |
| CN109743286A (en) | A kind of IP type mark method and apparatus based on figure convolutional neural networks | |
| CN111125290A (en) | Intelligent river patrol method and device based on river growth system and storage medium | |
| CN109561281A (en) | Industrial equipment method for safety monitoring, device, control device and readable storage medium storing program for executing | |
| CN113065026A (en) | Intelligent abnormal event detection system, method and medium based on security micro-service architecture | |
| CN116012762A (en) | Traffic intersection video image analysis method and system for power equipment | |
| Novikova et al. | Autoencoder anomaly detection on large CAN bus data | |
| CN114881665A (en) | Method and system for identifying electricity stealing suspected user based on target identification algorithm | |
| CN116189063B (en) | Key frame optimization method and device for intelligent video monitoring | |
| CN112257545A (en) | Violation real-time monitoring and analyzing method and device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181221 |