CN106650932A - Intelligent fault classification method and device for data center monitoring system - Google Patents
Intelligent fault classification method and device for data center monitoring system Download PDFInfo
- Publication number
- CN106650932A CN106650932A CN201611206596.6A CN201611206596A CN106650932A CN 106650932 A CN106650932 A CN 106650932A CN 201611206596 A CN201611206596 A CN 201611206596A CN 106650932 A CN106650932 A CN 106650932A
- Authority
- CN
- China
- Prior art keywords
- layers
- neuron
- energy
- network
- output
- 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.)
- Granted
Links
Classifications
-
- 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
- G06N3/08—Learning methods
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0259—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterized by the response to fault detection
- G05B23/0275—Fault isolation and identification, e.g. classify fault; estimate cause or root of failure
- G05B23/0281—Quantitative, e.g. mathematical distance; Clustering; Neural networks; Statistical analysis
Abstract
The invention discloses an intelligent fault classification method and device for a data center monitoring system. The method comprises the steps that an input matrix of a development network is constructed according to the monitoring state of monitoring items of monitoring resources; the input matrix is adopted to perform learning training on the development network; the development network obtained after learning training is adopted to classify a fault of the monitoring state. According to the method, the input matrix of the network is constructed according to the specific monitoring state of the monitoring items of the monitoring resources, an intelligent network, namely the development network is adopted to realize intelligent fault classification on the monitoring resources, classification of the fault can be realized after learning training is performed on the development network, and therefore fault diagnosis efficiency is improved.
Description
Technical field
The present invention relates to data center's monitoring technology field, the intelligence event of more particularly to a kind of data center's monitoring system
Barrier sorting technique and device.
Background technology
At present, developing rapidly with internet, data center carries the work(such as collection, storage and the analysis of various data
Can, once equipment breaks down, staff needs to be gone to analyze failure according to the alarm details of the monitored item of monitoring, for experience
For abundant old employee, it may be possible to which the failure cause that finds quickly is solved, for general employee is likely to look for
To failure cause or take long enough to find the basic reason of failure, so greatly increase data center apparatus operation
Stability and security, it is impossible to enough ensure miscellaneous service normal operation, fault diagnosis it is less efficient.
The content of the invention
It is an object of the invention to provide the intelligent trouble sorting technique and device of a kind of data center's monitoring system, to realize
Lift fault diagnosis efficiency.
To solve above-mentioned technical problem, the present invention provides a kind of intelligent trouble sorting technique of data center's monitoring system,
The method includes：
According to the input matrix of the monitor state structure development network of the monitored item of monitoring resource；
Learning training is carried out to developing network using the input matrix；
The failure of monitor state is classified using the development network after learning training.
Preferably, the development network includes X layers, Y layers and Z layers.
Preferably, learning training is carried out to developing network using input matrix, including：
Using input matrix as X layers, the energy of each neuron of Y layers is calculated；
The maximum neuron j of energy is found out from all neurons of Y layers, the weights of neuron j are updated；
Using the output of Y layers as the input of Z layers, the neuron k for being responded is found out in the neuron from Z layers, it is right
The weights of neuron k are updated.
Preferably, the development network after the employing learning training is classified to the failure of monitor state, including：
According to the input matrix of X layers construction, the energy of neuron in Y layers is calculated, by energy in all neurons of Y layers most
The output of big neuron is set to 1, and the output of other neurons in Y layers in addition to the maximum neuron of energy is all provided with
It is set to 0；
By the output of Y layer neurons, as the input of Z layer neurons, energy is found out most in all of neuron of Z layers
Big neuron i, determines the fault type that the corresponding fault types of neuron i are monitor state.
The present invention also provides a kind of intelligent trouble sorter of data center's monitoring system, for realizing methods described,
Including：
Matrix construction module, for according to the input square of the monitor state structure development network of the monitored item of monitoring resource
Battle array；
Training module, for carrying out learning training to developing network using the input matrix；
Failure modes module, for being classified to the failure of monitor state using the development network after learning training.
Preferably, the development network includes X layers, Y layers and Z layers.
Preferably, the training module includes：
Computing unit, as X layers, the energy of each neuron of Y layers is calculated for using input matrix；
First right value update unit, the neuron j maximum for finding out energy from all neurons of Y layers, by god
The weights of Jing units j are updated；
Second right value update unit, as the input of Z layers, finds out for using the output of Y layers in the neuron from Z layers
The weights of neuron k are updated by the neuron k for being responded.
Preferably, the failure modes module includes：
Output setting unit, for the input matrix constructed according to X layers, calculates the energy of neuron in Y layers, by Y layers
The output of the maximum neuron of energy in all neurons is set to 1, by its in Y layers in addition to the maximum neuron of energy
The output of its neuron is disposed as 0；
Failure determining unit, for by the output of Y layer neurons, as the input of Z layer neurons, in all of god of Z layers
The maximum neuron i of energy is found out during Jing is first, the fault type that the corresponding fault types of neuron i are monitor state is determined.
The intelligent trouble sorting technique and device of a kind of data center's monitoring system provided by the present invention, according to monitoring money
The input matrix of the monitor state structure development network of the monitored item in source；Learnt to developing network using the input matrix
Training；The failure of monitor state is classified using the development network after learning training.It can be seen that, according to the monitoring of monitoring resource
The concrete monitor state of item carries out the input matrix of tectonic network, develops network using a kind of intelligent network to realize to monitoring
The intelligent trouble classification of resource, after learning training is carried out to development network, you can realize the classification to failure, and in failure
During classification use, if the user thinks that the failure does not meet user's requirement, user can redefine failure, be learned
Practise, you can realization is classified to new failure, is not required to so as to reaching the process of an on-line study, and developing network training
Iterate, be greatly reduced the learning time of network, and realize a process of an online incremental learning, can
Meet the self-defined failure of user, so carrying out failure modes using development network, can quickly analyze failure cause,
And can realize that the self-defining intelligent trouble of user is classified.
Description of the drawings
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
The accompanying drawing to be used needed for having technology description is briefly described, it should be apparent that, drawings in the following description are only this
Inventive embodiment, for those of ordinary skill in the art, on the premise of not paying creative work, can be with basis
The accompanying drawing of offer obtains other accompanying drawings.
Fig. 1 is a kind of flow chart of the intelligent trouble sorting technique of data center's monitoring system provided by the present invention；
Fig. 2 is development network diagram；
Fig. 3 is failure modes implementation process schematic diagram；
Fig. 4 is a kind of flow chart of the intelligent trouble sorter of data center's monitoring system provided by the present invention.
Specific embodiment
The core of the present invention is to provide a kind of intelligent trouble sorting technique and device of data center's monitoring system, to realize
Lift fault diagnosis efficiency.
In order that those skilled in the art more fully understand the present invention program, below in conjunction with the embodiment of the present invention
Accompanying drawing, is clearly and completely described to the technical scheme in the embodiment of the present invention, it is clear that described embodiment is only
The a part of embodiment of the present invention, rather than the embodiment of whole.Based on the embodiment in the present invention, those of ordinary skill in the art
The every other embodiment obtained under the premise of creative work is not made, belongs to the scope of protection of the invention.
Fig. 1 is refer to, Fig. 1 is a kind of intelligent trouble sorting technique of data center's monitoring system provided by the present invention
Flow chart, the method includes：
S11：According to the input matrix of the monitor state structure development network of the monitored item of monitoring resource；
S12：Learning training is carried out to developing network using input matrix；
S13：The failure of monitor state is classified using the development network after learning training.
It can be seen that, the method carries out the input matrix of tectonic network according to the concrete monitor state of the monitored item of monitoring resource,
Network is developed using a kind of intelligent network to realize the intelligent trouble classification to monitoring resource, learning to developing network
After training, you can realize the classification to failure, and during failure modes use, if the user thinks that the failure does not meet
User requires that user can redefine failure, be learnt, you can realization is classified to new failure, so as to reach one
The process of individual on-line study, and develop network training and need not iterate, the learning time of network is greatly reduced, and
Realize a process of an online incremental learning, disclosure satisfy that the self-defined failure of user, thus using development network come
Failure modes are carried out, failure cause can be quickly analyzed, and the self-defining intelligent trouble classification of user can be realized.
Based on said method, specifically, development network includes X layers, Y layers and Z layers.
Further, step S12 is comprised the following steps：
S21：Using input matrix as X layers, the energy of each neuron of Y layers is calculated；
S22：The maximum neuron j of energy is found out from all neurons of Y layers, the weights of neuron j are carried out more
Newly；
S23：Using the output of Y layers as the input of Z layers, the neuron for being responded is found out in the neuron from Z layers
The weights of neuron k are updated by k.
Further, step S13 is comprised the following steps：
S31：According to the input matrix of X layers construction, the energy of neuron in Y layers is calculated, by energy in all neurons of Y layers
The output of the maximum neuron of amount is set to 1, by the output of other neurons in Y layers in addition to the maximum neuron of energy
It is disposed as 0；
S32：By the output of Y layer neurons, as the input of Z layer neurons, in all of neuron of Z layers energy is found out
The maximum neuron i of amount, determines the fault type that the corresponding fault types of neuron i are monitor state.
Detailed, this method is using the law of development of the state university professor Weng Juyang simulation human brain of Michigan, United States
A kind of intelligent network for proposing --- develop network to realize the intelligent trouble classification to monitoring resource.Based on this method, failure
Assorting process mainly includes：(1) input matrix, (2) development network training and failure modes are constructed.
(1) input matrix is constructed：It is that the monitored item of a certain resource of monitoring is classified according to certain mode classification,
State to belonging to the monitored item of a classification does "AND" process, the i.e. monitored item under same classification, if one
It is abnormal, it is believed that the category is abnormal, if all normal, it is believed that the category is normal, afterwards the monitored item of resource
The state of classification lines up column vector or row vector according to what a certain aligning method was fixed.
(2) network training and failure modes are developed：It uses development network.
Wherein, it is that state university professor Weng Juyang of Michigan, United States simulates the law of development of human brain and carries to develop network
A kind of intelligent network for going out.
The development network has 3 regions, X, Y and Z, these three regions similar to general neuroid input layer, it is hidden
Containing layer and output layer, but signal transmission direction and inner workings and general neuroid are completely different, and network is illustrated
Figure is as shown in Figure 2.X is contacted usually as sensor with external environment, any sensor type can be modeled and (such as be regarded
Feel, the sense of hearing or tactile), both can also be used as output as input.Y layers typically imply as the brain of development network
(being closed in " skull "), it is impossible to directly contact with external environment, information can only be obtained by connection with X, Z region.Z
Layer is generally as actuator layer, you can be input can also be output, when Z is in extraneous monitor state, now Z is network
Input, otherwise, Z provides an output vector to drive actuator (muscle or body of gland) to act on real world.Three regions
Order from low to high is X, Y, Z, for example, X layers provide from low to high input to Y layers, Z layers provide inputing to from high to low
Y layers.Z region is mankind's design or teaches in Fig. 2, and Y regions are autonomous generations (natural or development).The development network
Concrete operating principle be described as follows：
(1) at the t=0 moment, to any region in A={ X, Y, Z }, initialize its self adaptation part N=(V, G) and
Reaction vector r, wherein V is synaptic weight, and G is the age of neuron.
(2) in t=1,2 ... at the moment, to any region in A, constantly repeat following two step：
1. it is calculated as below using area function f：
(r ', N ')=f (b, t, N) (1)
Wherein b (bottom-up) and t (top-down) are respectively that corresponding region comes from current network response vector r
From bottom to top with top-down input, r ' is its new response vector；
2. substituted as follows:N←N′,r←r′.
If X is sensor interface, x ∈ X are constantly in the state supervised by external environment, if Z is carried out device interface, only
Have in the case that " teacher " selects, z ∈ Z are just in supervised state, otherwise Z provides the output of actuator.Only work as X, Y and
After tri- regions of Z all at least update once, whole development network just completes once to update.When whole development network updates two
Secondary, for specific context (x, z), it completes the prediction of one bout, because development network needs to carry out 2 areas
The parallel renewal of area update, Y area updates and X and Z region, the data transfer of (x, z) carries out the data in Y regions to after Y layers
Update, the data transfer in the Y regions after renewal complete X, Z region to X, Z region in corresponding data renewal.
Arbitrary neuron in for region A has weights vector v=(vb,vt), corresponding to region input be p=(b,
t).For region Y, there are input b from bottom to top and top-down input t, region X there was only top-down input t, region
Z only has input b from bottom to top.Two normalization as follows of energy definition in region before each neuronal activation
The sum of inner product of vectors afterwards：
Wherein：It is the cynapse vector after normalizationUnit vector,It is the input vector after normalizationUnit vector.Inner product measures two unit vectorsWithThe degree of matching, because r is (vb,b,vt, t)=cos
θ, θ are two unit vectorsWithBetween angle.Energy value before activation is between [- 1,1].
Lateral suppression (lateral inhibitions) in simulate any region A, only front top-k triumph
Neuron can be activated and be updated.Consider k=1, (being activated) neuron of triumph can be carried out in the following way
Identification：
For k=1, only unique victor just can be activated, its response yj=1, other neurons are not swashed
It is living.All connections in development network are all based on what Hebbian learning rules were learnt：The pre-synapse of activation neuron is lived
It is dynamicActivate simultaneously with post-synapse activity y.By taking Y regions as an example (learning method in other regions is similar with Y), if pre-synapse is last
End and post-synapse end are activated together, and the cynapse vector of neuron has a cynapse gainOther nerves not being activated
Unit does not change its state.After a neuron j is activated, its weights is as follows according to similar Hebbian Policy Updates：
Wherein, ω2(nj) be and activation age (activation number of times) related learning rate, ω1(nj) it is to maintain rate, also, ω1
(nj)+ω2(nj)≡1。ω2(nj) simplest form be ω2(nj)=1/n, this equation gives inputThe recurrence of sampling average
Computational methods：
Wherein, tiIt is the activationary time of neuron, the age of triumph neuron adds 1, i.e. nj←nj+1。
Based on this method, the detailed process for developing network training and failure modes is as follows：
(1) network training is developed：Such as Fig. 2, X layers are the input matrix of construction, Y layers and the nerve that Z layers are random initializtion
Unit.
The training of the development network of the structure, is divided into two steps：Calculating between X layers and Y layers, the meter between Y layers and Z layers
Calculate.
The calculating of X layers and Y layers is first according to formula 2, seeks the energy of each neuron of Y layers, then according to formula 3, obtains Y
Maximum that neuron j of energy in layer neuron, it is believed that neuron j is activated, next to that the neuron j of the Y layers being activated
Weights, be updated weights according to formula 4, other neurons do not carry out any operation, and the age of last neuron j adds 1.
Now, the output of the neuron of Y layers only has neuron j to be output as 1, and other neurons are output as 0, used as the input of Z layers.
The calculating of Y layers and Z layers：Now, input of the output of Y layers as Z layers, it is assumed that what training was specified is that k-th of Z layers are refreshing
The response of Jing units, then Z layers neuron k, according to formula 4 weights are updated, and other neurons are not updated, last neuron k
Age add 1.
(2) network failure classification is developed：In the failure modes stage, the weights for developing network are not changing, according to the structure of X layers
The input matrix made, carries out calculating the energy of Y layer neurons according to formula 2, then according to formula 3, calculates energy maximum
The position of that neuron, the secondly output of the maximum neuron of Y layers energy is set to 1, and the output of other neurons is arranged
For 0, the output of Y layer neurons, used as the input of Z layer neurons, then, Z layers neuron calculates Z layers most according to formula 3
The position i of that big neuron, then it is assumed that final failure modes are the corresponding fault types of Z layer neuron i.
Based on this method, in specific implementation process, need to construct input matrix, such as Fig. 3, server has multiclass sensor bag
The sensors such as temperature, voltage, hard disk, fan are included, and each class sensor has multiple, and the state of identical sensor is carried out
"AND" is calculated, and finally each class sensor is ranked up, and is configured to input matrix.In development network training process, such as Fig. 3,
If the input matrix of construction is X layers, Y layers and Z layers for random initializtion neuron, Y layers are hidden layer, and Z layers are output layer.
Fig. 4 is refer to, Fig. 4 is a kind of intelligent trouble sorter of data center's monitoring system provided by the present invention
Structural representation, for realizing said method, the device includes：
Matrix construction module 101, for according to the input of the monitor state structure development network of the monitored item of monitoring resource
Matrix；
Training module 102, for carrying out learning training to developing network using input matrix；
Failure modes module 103, for being classified to the failure of monitor state using the development network after learning training.
It can be seen that, the device carries out the input matrix of tectonic network according to the concrete monitor state of the monitored item of monitoring resource,
Network is developed using a kind of intelligent network to realize the intelligent trouble classification to monitoring resource, learning to developing network
After training, you can realize the classification to failure, and during failure modes use, if the user thinks that the failure does not meet
User requires that user can redefine failure, be learnt, you can realization is classified to new failure, so as to reach one
The process of individual on-line study, and develop network training and need not iterate, the learning time of network is greatly reduced, and
Realize a process of an online incremental learning, disclosure satisfy that the self-defined failure of user, thus using development network come
Failure modes are carried out, failure cause can be quickly analyzed, and the self-defining intelligent trouble classification of user can be realized.
Based on said apparatus, specifically, development network includes X layers, Y layers and Z layers.
Further, training module includes：
Computing unit, as X layers, the energy of each neuron of Y layers is calculated for using input matrix；
First right value update unit, the neuron j maximum for finding out energy from all neurons of Y layers, by god
The weights of Jing units j are updated；
Second right value update unit, as the input of Z layers, finds out for using the output of Y layers in the neuron from Z layers
The weights of neuron k are updated by the neuron k for being responded.
Further, failure modes module includes：
Output setting unit, for the input matrix constructed according to X layers, calculates the energy of neuron in Y layers, by Y layers
The output of the maximum neuron of energy in all neurons is set to 1, by its in Y layers in addition to the maximum neuron of energy
The output of its neuron is disposed as 0；
Failure determining unit, for by the output of Y layer neurons, as the input of Z layer neurons, in all of god of Z layers
The maximum neuron i of energy is found out during Jing is first, the fault type that the corresponding fault types of neuron i are monitor state is determined.
A kind of intelligent trouble sorter of data center's monitoring system provided by the present invention has been carried out in detail above
Introduce.Specific case used herein is set forth to the principle and embodiment of the present invention, the explanation of above example
It is only intended to help and understands the method for the present invention and its core concept.It should be pointed out that for the ordinary skill people of the art
Member for, under the premise without departing from the principles of the invention, some improvement and modification can also be carried out to the present invention, these improve and
Modification is also fallen in the protection domain of the claims in the present invention.
Claims (8)
1. a kind of intelligent trouble sorting technique of data center's monitoring system, it is characterised in that include：
According to the input matrix of the monitor state structure development network of the monitored item of monitoring resource；
Learning training is carried out to developing network using the input matrix；
The failure of monitor state is classified using the development network after learning training.
2. the method for claim 1, it is characterised in that the development network includes X layers, Y layers and Z layers.
3. method as claimed in claim 2, it is characterised in that carry out learning training to developing network using input matrix, wraps
Include：
Using input matrix as X layers, the energy of each neuron of Y layers is calculated；
The maximum neuron j of energy is found out from all neurons of Y layers, the weights of neuron j are updated；
Using the output of Y layers as the input of Z layers, the neuron k for being responded is found out in the neuron from Z layers, to nerve
The weights of first k are updated.
4. method as claimed in claim 2, it is characterised in that the development network after the employing learning training is to monitor state
Failure classified, including：
According to the input matrix of X layers construction, the energy of neuron in Y layers is calculated, energy in all neurons of Y layers is maximum
The output of neuron is set to 1, and the output of other neurons in Y layers in addition to the maximum neuron of energy is disposed as
0；
By the output of Y layer neurons, as the input of Z layer neurons, energy maximum is found out in all of neuron of Z layers
Neuron i, determines the fault type that the corresponding fault types of neuron i are monitor state.
5. a kind of intelligent trouble sorter of data center's monitoring system, it is characterised in that for realize as claim 1 to
Method in 4 described in any one, including：
Matrix construction module, for according to the input matrix of the monitor state structure development network of the monitored item of monitoring resource；
Training module, for carrying out learning training to developing network using the input matrix；
Failure modes module, for being classified to the failure of monitor state using the development network after learning training.
6. device as claimed in claim 5, it is characterised in that the development network includes X layers, Y layers and Z layers.
7. device as claimed in claim 6, it is characterised in that the training module includes：
Computing unit, as X layers, the energy of each neuron of Y layers is calculated for using input matrix；
First right value update unit, the neuron j maximum for finding out energy from all neurons of Y layers, by neuron j
Weights be updated；
Second right value update unit, for using the output of Y layers as Z layers input, finding out in the neuron from Z layers is carried out
The weights of neuron k are updated by the neuron k of response.
8. device as claimed in claim 6, it is characterised in that the failure modes module includes：
Output setting unit, for the input matrix constructed according to X layers, calculates the energy of neuron in Y layers, by all of Y layers
The output of the maximum neuron of energy in neuron is set to 1, by other god in Y layers in addition to the maximum neuron of energy
The output of Jing units is disposed as 0；
Failure determining unit, for by the output of Y layer neurons, as the input of Z layer neurons, in all of neuron of Z layers
In find out the maximum neuron i of energy, determine the fault type that the corresponding fault types of neuron i are monitor state.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611206596.6A CN106650932B (en) | 2016-12-23 | 2016-12-23 | A kind of the intelligent trouble classification method and device of data center's monitoring system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611206596.6A CN106650932B (en) | 2016-12-23 | 2016-12-23 | A kind of the intelligent trouble classification method and device of data center's monitoring system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106650932A true CN106650932A (en) | 2017-05-10 |
| CN106650932B CN106650932B (en) | 2019-05-28 |
Family
ID=58827281
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611206596.6A Active CN106650932B (en) | 2016-12-23 | 2016-12-23 | A kind of the intelligent trouble classification method and device of data center's monitoring system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106650932B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107247653A (en) * | 2017-06-02 | 2017-10-13 | 郑州云海信息技术有限公司 | A kind of Fault Classification and device of data center's monitoring system |
| CN107396094A (en) * | 2017-08-17 | 2017-11-24 | 上海大学 | The automatic testing method of single camera damage towards in multi-cam monitoring system |
| CN109361539A (en) * | 2018-10-16 | 2019-02-19 | 郑州云海信息技术有限公司 | A kind of performance alarm method and apparatus based on development network |
| CN110000781A (en) * | 2019-03-29 | 2019-07-12 | 郑州大学 | Moveable robot movement direction pre-decision method based on development network |
| CN110399238A (en) * | 2019-06-27 | 2019-11-01 | 浪潮电子信息产业股份有限公司 | A kind of disk failure method for early warning, device, equipment and readable storage medium storing program for executing |
| CN112988437A (en) * | 2019-12-17 | 2021-06-18 | 深信服科技股份有限公司 | Fault prediction method and device, electronic equipment and storage medium |
Citations (3)
| 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 |
| CN105630648A (en) * | 2015-12-02 | 2016-06-01 | 武汉物联远科技有限公司 | Multidimensional data deep learning-based data center intelligent control method and system |
| CN105782071A (en) * | 2016-03-04 | 2016-07-20 | 长沙有色冶金设计研究院有限公司 | Water isolation pulp pump fault diagnosis method based on probabilistic neural network |
-
2016
- 2016-12-23 CN CN201611206596.6A patent/CN106650932B/en active Active
Patent Citations (3)
| 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 |
| CN105630648A (en) * | 2015-12-02 | 2016-06-01 | 武汉物联远科技有限公司 | Multidimensional data deep learning-based data center intelligent control method and system |
| CN105782071A (en) * | 2016-03-04 | 2016-07-20 | 长沙有色冶金设计研究院有限公司 | Water isolation pulp pump fault diagnosis method based on probabilistic neural network |
Non-Patent Citations (1)
| Title |
|---|
| 段谊海: "基于发育网络的语音图像双模态共发育系统研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107247653A (en) * | 2017-06-02 | 2017-10-13 | 郑州云海信息技术有限公司 | A kind of Fault Classification and device of data center's monitoring system |
| CN107396094A (en) * | 2017-08-17 | 2017-11-24 | 上海大学 | The automatic testing method of single camera damage towards in multi-cam monitoring system |
| CN107396094B (en) * | 2017-08-17 | 2019-02-22 | 上海大学 | Automatic testing method towards camera single in multi-cam monitoring system damage |
| CN109361539A (en) * | 2018-10-16 | 2019-02-19 | 郑州云海信息技术有限公司 | A kind of performance alarm method and apparatus based on development network |
| CN110000781A (en) * | 2019-03-29 | 2019-07-12 | 郑州大学 | Moveable robot movement direction pre-decision method based on development network |
| CN110399238A (en) * | 2019-06-27 | 2019-11-01 | 浪潮电子信息产业股份有限公司 | A kind of disk failure method for early warning, device, equipment and readable storage medium storing program for executing |
| CN110399238B (en) * | 2019-06-27 | 2023-09-22 | 浪潮电子信息产业股份有限公司 | Disk fault early warning method, device, equipment and readable storage medium |
| CN112988437A (en) * | 2019-12-17 | 2021-06-18 | 深信服科技股份有限公司 | Fault prediction method and device, electronic equipment and storage medium |
| CN112988437B (en) * | 2019-12-17 | 2023-12-29 | 深信服科技股份有限公司 | Fault prediction method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106650932B (en) | 2019-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chui et al. | Predicting at-risk university students in a virtual learning environment via a machine learning algorithm | |
| CN106650932B (en) | A kind of the intelligent trouble classification method and device of data center's monitoring system | |
| Thanga Selvi et al. | RETRACTED ARTICLE: An optimal artificial neural network based big data application for heart disease diagnosis and classification model | |
| Thai-Nghe et al. | Factorization Models for Forecasting Student Performance. | |
| Whittlestone et al. | The societal implications of deep reinforcement learning | |
| CN110213244A (en) | A kind of network inbreak detection method based on space-time characteristic fusion | |
| Luo et al. | A new kernel extreme learning machine framework for somatization disorder diagnosis | |
| Tang et al. | Variable predictive model class discrimination using novel predictive models and adaptive feature selection for bearing fault identification | |
| CN110399238A (en) | A kind of disk failure method for early warning, device, equipment and readable storage medium storing program for executing | |
| CN108768750A (en) | Communication network failure localization method and device | |
| Lou et al. | Classification-based prediction of network connectivity robustness | |
| Liang et al. | Ensemble learning based on fitness Euclidean-distance ratio differential evolution for classification | |
| Ma et al. | Multiple costs based decision making with back-propagation neural networks | |
| Aishath Murshida et al. | Survey on artificial intelligence | |
| CN109361539A (en) | A kind of performance alarm method and apparatus based on development network | |
| Reddy et al. | Neural networks for prediction of loan default using attribute relevance analysis | |
| Poczeta et al. | Application of fuzzy cognitive maps with evolutionary learning algorithm to model decision support systems based on real-life and historical data | |
| Valsamidis et al. | An approach for LMS assessment | |
| Hamade et al. | Toward predicting the performance of novice CAD users based on their profiled technical attributes | |
| Naidoo et al. | Analysing University at-Risk Students in a Virtual Learning Environment using Machine Learning Algorithms | |
| Voleti | Unfolding the evolution of machine learning and its expediency | |
| Ajiboye et al. | Using an enhanced feed-forward BP network for predictive model building from students’ data | |
| Wei et al. | Study on battlefield situation assessment model of simulation entity based on stacked auto-encoder network | |
| Raja | A conceptual overview and systematic review on artificial intelligence and its approaches | |
| Ke et al. | An incremental optimal weight learning machine of single-layer neural networks |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20191128 Address after: 250001 North Zone, floor 3, building S05, Inspur Science Park, No. 1036, Inspur Road, high tech Zone, Jinan City, Shandong Province Patentee after: Shandong Yingxin Computer Technology Co., Ltd. Address before: 450018 Henan province Zheng Dong New District of Zhengzhou City Xinyi Road No. 278 16 floor room 1601 Patentee before: Zhengzhou Yunhai Information Technology Co. Ltd. |