CN110263811A - A kind of equipment running status monitoring method and system based on data fusion - Google Patents
A kind of equipment running status monitoring method and system based on data fusion Download PDFInfo
- Publication number
- CN110263811A CN110263811A CN201910421340.4A CN201910421340A CN110263811A CN 110263811 A CN110263811 A CN 110263811A CN 201910421340 A CN201910421340 A CN 201910421340A CN 110263811 A CN110263811 A CN 110263811A
- Authority
- CN
- China
- Prior art keywords
- equipment
- data
- feature
- running status
- distribution
- 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
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/251—Fusion techniques of input or preprocessed data
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses a kind of equipment running status monitoring method and system based on data fusion, comprising: the signal of collecting device sensor;Wherein, the signal includes equipment essential information, health status, communication state, behavior act, device parameter and environmental condition;The signal of pre-processing device sensor defines the status data of equipment;The equipment running status data defined are input to GMM model, the distribution of output equipment operating status feature and state feature;Analytical equipment operating status feature and its distribution, the abnormality period of output equipment.It is able to solve in the prior art aiming at the problem that signal characteristic has the characteristics that the big equipment of non-linear, isomery, redundancy, different scale can not obtain good monitoring effect.
Description
Technical field
The present invention relates to the equipment monitoring fields of industrial process more particularly to a kind of equipment based on data fusion to run shape
State monitors system and method.
Background technique
Recently as micro electro mechanical system (MEMS) technology, the rapid development of wireless communication technique, sensor technology, sensor network
Have many advantages, such as that building is quick, deployment is convenient, achievable a wide range of, multi-mode information collection and object automatic monitoring.In addition,
Mechanical equipment is increasingly enlarged and integrated, and working condition changes frequent and other equipment serious interference, so that vibration signal
With very strong non-linear, non-gaussian and dynamic, the signal characteristic of extraction also has non-linear, isomery, redundancy, different scale
The characteristics such as big, existing determination method Monitoring Performance is undesirable, and to non-linear, non-gaussian, multi-modal progress equipment fortune
The research of row monitoring, diagnosing is also fewer.
Summary of the invention
In view of the above-mentioned problems, the purpose of the present invention is to provide a kind of method based on data fusion and probability clustering, leads to
The running state data that sensing data obtains equipment is crossed, point of equipment running status feature and state feature is obtained by model
Cloth, thus the running abnormality of discovering device, with solve in the prior art for signal characteristic have non-linear, isomery,
The problem of equipment of the big feature of redundancy, different scale can not obtain good monitoring effect.
The embodiment of the invention provides a kind of equipment running status monitoring methods based on data fusion, which is characterized in that
Include:
The signal of collecting device sensor;Wherein, the signal include equipment essential information, health status, communication state,
Behavior act, device parameter and environmental condition;
The signal of pre-processing device sensor defines the status data of equipment;
The equipment running status data defined are input to GMM model, output equipment operating status feature and state are special
The distribution of sign;
Analytical equipment operating status feature and its distribution, the abnormality period of output equipment.
Specifically, the signal of the pre-processing device sensor, defines the concrete methods of realizing of the status data of equipment are as follows:
The current time value of all operating status sensors of any moment equipment is normalized, normalizing is calculated
Change result;Wherein, result=(current time value-history minimum value)/(history maximum value-history minimum value) is normalized;
Using the combination of the normalization result of all operating status sensors of any moment equipment as current time equipment
Status data.
Preferably, above-mentioned pretreatment operation further includes data cleansing.
Specifically, the equipment running status data defined are input to GMM model, output equipment operating status feature and
The concrete methods of realizing of the distribution of state feature are as follows:
1) Segmentation of Data Set:
Defined function split_dataset (A, n),
Wherein, it inputs as data set A, submodel quantity is that n randomly selects the length of its preset ratio for data set A
Data set and output, export as from data set set [A_1, A_2 ..., A_n];
2) model is generated:
Defined function cluster_action (A_i, stop_weight),
Wherein input is data set A_i, stops division weight stop_weight;
Data set A_i is input to standard GMM model, obtains probability distribution M_i;
The predicted value to A_i, M_i is exported, when predicted value is 0, data set A_i is classified as A_i0, when predicted value is 1
When, data set A_i is classified as A_i1;When the weight of A_i0, which is greater than, stops division weight stop_weight, A_i0 cluster is arrived
The left sibling of probability distribution M_i;When the weight of A_i1, which is greater than, stops division weight stop_weight, A_i1 is clustered to general
The right node of rate distribution M_i;
Export final probability distribution M_i;Wherein, the weight calculation mode of A_i0 is that the maximum value of data set A_i subtracts
Minimum value;
3) predictive information:
Defined function predict_action (T):
Wherein, it inputs and state feature number belonging to data is calculated for each M_i for prediction data T
[result] _ i and some data belong to probability [score] _ i of the state feature;
Output final result be result=[[result] _ 1, [result] _ 2 ..., [result] _ n], [[score] _
1,[score]_2,…,[score]_n]。
Specifically, the analytical equipment operating status feature and its distribution, the abnormality period of output equipment it is specific
Implementation method are as follows:
Using the ID of device history data as horizontal axis, quickly orients and set as the longitudinal axis using state feature number belonging to data
The obvious abnormal period is presented in standby state.
Preferably, after the abnormality period of output equipment, further includes:
It shows exception information, and sends the information to the communication apparatus of related management personnel.
Preferably, after the abnormality period of output equipment, further includes:
One or more processors are sent by the abnormal period information, the processor, which determines, is used for relevant device
Maintenance action suggestion.
The embodiment of the invention provides a kind of, and the equipment running status based on data fusion monitors system, which is characterized in that
Include:
Signal collection module, the signal for collecting device sensor;Wherein, the signal include equipment essential information,
Health status, communication state, behavior act, device parameter and environmental condition;
Preprocessing module defines the status data of equipment for the signal of pre-processing device sensor;
Equipment running status monitoring modular, the equipment running status data for will define are input to GMM model, output
The distribution of equipment running status feature and state feature;
Unit exception output module is used for analytical equipment operating status feature and its distribution, the abnormality of output equipment
Period.
Detailed description of the invention
In order to illustrate more clearly of technical solution of the present invention, attached drawing needed in embodiment will be made below
Simply introduce, it should be apparent that, the accompanying drawings in the following description is only some embodiments of the present invention, general for this field
For logical technical staff, without creative efforts, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is a kind of showing for equipment running status monitoring method based on data fusion that first embodiment of the invention provides
It is intended to;
Fig. 2 is a kind of showing for equipment running status monitoring system based on data fusion that second embodiment of the invention provides
It is intended to;
Fig. 3 is the schematic diagram for the equipment running status monitoring result that first embodiment of the invention provides.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
For the ease of clearly describing the technical solution of the embodiment of the present invention, in an embodiment of the present invention, use " the
One ", the printed words such as " second " distinguish function or the essentially identical identical entry of effect or similar item, and those skilled in the art can
Understand that the printed words such as " first ", " second " are not defined quantity and execution order.
The embodiment of the invention provides a kind of equipment running status monitoring methods based on data fusion, referring to Fig. 1,
In the present embodiment,
S101, the signal of collecting device sensor;Wherein, the signal includes equipment essential information, health status, communication
State, behavior act, device parameter and environmental condition;
In actual industrial process, the sensor signal is collected according to the actual situation, by taking above-mentioned signal as an example:
Essential information refers to name plate information, for quickly identifying equipment, including the description of device model, device, generation manufacturer, end
Mouth quantity, hardware version, firmware version, software version, IP address and MAC Address etc.;
Health status, comprising: power supply, CPU, software, memory, storage, clock etc.;
Communication state includes: port, optical power, flow and service condition etc.;
Behavior act includes: real-time record and real-time monitoring;
Device parameter includes device parameter and parameter state;
Environmental condition includes mal-condition and normal condition.
The general sensor of equipment includes: online infrared thermal imager, it is seen that light video surveillance devices, vibration measurement
Instrument, sonigauge, portable hardometer, gas detecting instrument, Diagnosing Faults of Electrical instrument, thermal technology/verification/electric measurement instrument
Table etc..
Multi-level operation is established for a variety of data, for multi-source data acquisition layer, multiple data sources can be counted
According to acquisition;Data interface tier is connected to multi-source data acquisition layer, corresponds to numerous types of data and is respectively equipped with multiple data and connects
Mouthful, and multi-source data is received using the data-interface of corresponding data type;Big data merges management level, respectively to data interface tier
Received data are stored respectively, big data calculates analysis etc..
Preferably, the data interface tier includes the SQOOP interface for being used for transmission relational data, is used for transmission in real time
The JMS interface of data flow and the FTP interface for being used for transmission routine data;
The big data fusion management level include Tool for Data Warehouse Hive, Hbase database, the inquiry of SQL big data
Tool Impala and Hadoop resource manager YARN;
It further include having extensive stream data processing frame Spark Streaming, for using Apache from R language
Language pack Spark R of Spark, machine learning algorithm library MLlib, the Spark GraphX for executing figure parallel computation and
Python programmed environment.
It preferably, further include open source algorithms library, such as space-time geoanalysis module, coverage analysis module, figure, which calculates, to be divided
Analyse module, incidence relation analysis module;
Preferably, the model access interface layer includes: Java database connecting interface JDBC, for executing SQL language
Sentence;Open CNC ODBC, for supporting sql like language;Spark SQL, for realizing the calculating to structural data;
HUE interface, for realizing the exploitation and debugging of the Hadoop ecosystem.
Above-mentioned multi-level operation enables equipment management personnel flexibly accurately to handle all types of signal datas, and just
Prompt use has statistical and analytical tool and carries out rapid modeling, generates simple or complicated analysis result.
S102, the signal of pre-processing device sensor define the status data of equipment;
Concrete methods of realizing are as follows:
The current time value of all operating status sensors of any moment equipment is normalized, normalizing is calculated
Change result;Wherein, result=(current time value-history minimum value)/(history maximum value-history minimum value) is normalized;
Using the combination of the normalization result of all operating status sensors of any moment equipment as current time equipment
Status data.
Normalized result is stored as array, matrix information etc. according to default rule, adopts use convenient for each model.
Preferably, data cleansing processing is carried out according to the actual situation before normalization.
The equipment running status data defined are input to GMM model, output equipment operating status feature and shape by S103
The distribution of state feature;
Concrete methods of realizing are as follows:
1) Segmentation of Data Set:
Defined function split_dataset (A, n),
Wherein, it inputs as data set A, submodel quantity is that n randomly selects the length of its preset ratio for data set A
Data set and output, export as from data set set [A_1, A_2 ..., A_n];
2) model is generated:
Defined function cluster_action (A_i, stop_weight),
Wherein input is data set A_i, stops division weight stop_weight;
Data set A_i is input to standard GMM model, obtains probability distribution M_i;
The predicted value to A_i, M_i is exported, when predicted value is 0, data set A_i is classified as A_i0, when predicted value is 1
When, data set A_i is classified as A_i1;When the weight of A_i0, which is greater than, stops division weight stop_weight, A_i0 cluster is arrived
The left sibling of probability distribution M_i;When the weight of A_i1, which is greater than, stops division weight stop_weight, A_i1 is clustered to general
The right node of rate distribution M_i;
Export final probability distribution M_i;Wherein, the weight calculation mode of A_i0 is that the maximum value of data set A_i subtracts
Minimum value;
3) predictive information:
Defined function predict_action (T):
Wherein, it inputs and state feature number belonging to data is calculated for each M_i for prediction data T
[result] _ i and some data belong to probability [score] _ i of the state feature;
Output final result be result=[[result] _ 1, [result] _ 2 ..., [result] _ n], [[score] _
1,[score]_2,…,[score]_n]。
Wherein, the standard GMM model algorithm popular as one, gauss hybrid models (Gaussian Mixture
Model), just assume that data obey Mixture Gaussian Distribution, in other words, data can be regarded as
It is generated from several Gaussian Distribution.In fact, can be seen that from central-limit theorem
It is that comparison is reasonable in fact that Gaussian, which is distributed this hypothesis, and in addition to this, computationally there are also very for Gaussian distribution
Good property.In addition, Mixture Model itself is also that can become arbitrarily complicated in fact, by for increasing Model
Number, we can arbitrarily approach any close distribution of continuous probability.
Each GMM is made of a Gaussian distribution, and each Gaussian is known as one " Component ", these
The linear addition of Component just constitutes the probability density function of GMM together:
It can actually be divided if we will randomly take a point from the distribution of GMM according to formula above
For two steps: as soon as randomly selecting among this Component first, each Component selected probability is actually
It is its coefficient, has selected Component and then individually consider to choose a point from the distribution of this Component
Can -- common Gaussian distribution has been had returned to here, has been converted for known problem.
Clustering is done using GMM, for existing data, it is assumed that they be generated by GMM Lai, then I
As long as according to data release GMM probability distribution come, then a Component of GMM actually correspondence
A cluster.It is commonly referred to as density estimation come prediction probability density according to data, particularly, when us
In known (or assume) form of probability density function, and to estimate the process of parameter therein and be referred to as " parameter Estimation ".
It is now assumed that there is a data point, and assume that they obey some distribution (being denoted as), is now to determine some of the inside
The value of parameter, for example, just it needs to be determined that and these parameters in GMM.Such one group of parameter is found, probability determined by it point
Cloth generates the maximum probability of these given data points, and this probability is actually equal to, this product is just referred to as likelihood
Function (Likelihood Function).The number of probability all very littles of usual a single point, many very littles is multiplied to get up calculating
Floating number underflow is easily caused in machine, therefore would generally take logarithm to it, and product is become to sum it up, obtains log-
likelihood function.Next, as long as by this function maximization, (common practice is derivation and derivative is enabled to be equal to
Zero, then solve equation), that is, such one group of parameter value is found, it allows likelihood function to obtain maximum value, and being considered as this at this time is most
Suitable parameter, this completes the processes of parameter Estimation.
Referring now to the log-likelihood function of GMM at a glance:
Due to having adduction again inside logarithmic function, maximum value directly directly cannot be acquired with the method that derivation solves equation.
In order to solve this problem, before taking from GMM random selecting point method: be divided into two steps,
The probability (being not the selected probability of each Component) that estimated data is generated by each Component: right
For each data, it is by the probability that the Component is generated
Due in formula and be also to need the value estimated, using iterative method, assume when calculating and it is known that will
Take the resulting value of last iteration (or initial value).
Estimate the parameter of each Component: it is now assumed that be exactly obtained in previous step correctly " data by
The probability that Component is generated ", the contribution that can also be done on generating this data as the Component, in other words,
It is considered as this value wherein to have this part being generated by Component.It concentrates and considers all data points, it is now practical
On be considered as Component and generate these points.Since each Component is the Gaussian distribution an of standard,
It can be easy to distribution and find out parameter value corresponding to maximum likelihood:
Wherein, and also it can be estimated as with following a well mapped-out plan.
Two step before iteration, until the value convergence of likelihood function.
It follows that being exported by the observation probability for improving each operating status feature of the available equipment of GMM model
Be equipment running status feature probability distribution.
S104, analytical equipment operating status feature and its distribution, the abnormality period of output equipment.
From the figure 3, it may be seen that one of realizing method is, using the ID of device history data as horizontal axis, with shape belonging to data
State feature number is the longitudinal axis, is quickly oriented the period that obvious exception is presented in equipment state, abnormal period such as black surround institute in Fig. 3
Show.
For those skilled in the art, any one passes through current device state feature distribution and historical plant status feature
The method of comparison is suitable for analyzing abnormality period result.
Preferably, after the abnormality period of output equipment, further includes:
It shows exception information, and sends the information to the communication apparatus of related management personnel.
Preferably, after the abnormality period of output equipment, further includes:
One or more processors are sent by the abnormal period information, the processor, which determines, is used for relevant device
Maintenance action suggestion.
The embodiment of the invention provides a kind of, and the equipment running status based on data fusion monitors system, comprising:
Signal collection module, the signal for collecting device sensor;Wherein, the signal include equipment essential information,
Health status, communication state, behavior act, device parameter and environmental condition;
Preprocessing module defines the status data of equipment for the signal of pre-processing device sensor;
Equipment running status monitoring modular, the equipment running status data for will define are input to GMM model, output
The distribution of equipment running status feature and state feature;
Unit exception output module is used for analytical equipment operating status feature and its distribution, the abnormality of output equipment
Period.
Above-mentioned module is common hardware handles device in technical solution of the present invention, at MCU, CPU, FPGA, image
Manage device GPU etc..
The above is a preferred embodiment of the present invention, it is noted that for those skilled in the art
For, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also considered as
Protection scope of the present invention.
Claims (7)
1. a kind of equipment running status monitoring method based on data fusion characterized by comprising
The signal of collecting device sensor;Wherein, the signal includes equipment essential information, health status, communication state, behavior
Movement, device parameter and environmental condition;
The signal of pre-processing device sensor defines the status data of equipment;
The equipment running status data defined are input to GMM model, output equipment operating status feature and state feature
Distribution;
Analytical equipment operating status feature and its distribution, the abnormality period of output equipment.
2. equipment running status monitoring method according to claim 1, which is characterized in that
The signal of the pre-processing device sensor, defines the concrete methods of realizing of the status data of equipment are as follows:
The current time value of all operating status sensors of any moment equipment is normalized, normalization knot is calculated
Fruit;Wherein, result=(current time value-history minimum value)/(history maximum value-history minimum value) is normalized;
Shape by the combination of the normalization result of all operating status sensors of any moment equipment as current time equipment
State data.
3. equipment running status monitoring method according to claim 1, which is characterized in that
The equipment running status data defined are input to GMM model, output equipment operating status feature and state feature
The concrete methods of realizing of distribution are as follows:
1) Segmentation of Data Set:
Defined function split_dataset (A, n),
Wherein, it inputs as data set A, submodel quantity is that n randomly selects the number of the length of its preset ratio for data set A
According to collecting and exporting, export as from data set set [A_1, A_2 ..., A_n];
2) model is generated:
Defined function cluster_action (A_i, stop_weight),
Wherein input is data set A_i, stops division weight stop_weight;
Data set A_i is input to standard GMM model, obtains probability distribution M_i;
The predicted value to A_i, M_i is exported, when predicted value is 0, data set A_i is classified as A_i0, it, will when predicted value is 1
Data set A_i is classified as A_i1;When the weight of A_i0, which is greater than, stops division weight stop_weight, by A_i0 cluster to probability
It is distributed the left sibling of M_i;When the weight of A_i1, which is greater than, stops division weight stop_weight, by A_i1 cluster to probability point
The right node of cloth M_i;
Export final probability distribution M_i;Wherein, the weight calculation mode of A_i0 is that the maximum value of data set A_i subtracts minimum
Value;
3) predictive information:
Defined function predict_action (T):
Wherein, it inputs and state feature number [result] _ i belonging to data is calculated for each M_i for prediction data T,
And some data belongs to probability [score] _ i of the state feature;
Output final result be result=[[result] _ 1, [result] _ 2 ..., [result] _ n], [[score] _ 1,
[score]_2,…,[score]_n]。
4. equipment running status monitoring method according to claim 3, which is characterized in that
The analytical equipment operating status feature and its distribution, the concrete methods of realizing of the abnormality period of output equipment are as follows:
Using the ID of device history data as horizontal axis, using state feature number belonging to data as the longitudinal axis, equipment shape is quickly oriented
The obvious abnormal period is presented in state.
5. equipment running status monitoring method according to claim 1, which is characterized in that in the abnormality of output equipment
After period, further includes:
It shows exception information, and sends the information to the communication apparatus of related management personnel.
6. equipment running status monitoring method according to claim 1, which is characterized in that in the abnormality of output equipment
After period, further includes:
One or more processors are sent by the abnormal period information, the processor determines the dimension for being used for relevant device
Movement is repaired to suggest.
7. a kind of equipment running status based on data fusion monitors system characterized by comprising
Signal collection module, the signal for collecting device sensor;Wherein, the signal includes equipment essential information, health
State, communication state, behavior act, device parameter and environmental condition;
Preprocessing module defines the status data of equipment for the signal of pre-processing device sensor;
Equipment running status monitoring modular, the equipment running status data for will define are input to GMM model, output equipment
The distribution of operating status feature and state feature;
Unit exception output module is used for analytical equipment operating status feature and its distribution, the abnormality period of output equipment.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910421340.4A CN110263811B (en) | 2019-05-21 | 2019-05-21 | Equipment running state monitoring method and system based on data fusion |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910421340.4A CN110263811B (en) | 2019-05-21 | 2019-05-21 | Equipment running state monitoring method and system based on data fusion |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110263811A true CN110263811A (en) | 2019-09-20 |
CN110263811B CN110263811B (en) | 2021-03-26 |
Family
ID=67914916
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910421340.4A Active CN110263811B (en) | 2019-05-21 | 2019-05-21 | Equipment running state monitoring method and system based on data fusion |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110263811B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111077876A (en) * | 2019-12-11 | 2020-04-28 | 湖南大唐先一科技有限公司 | Power station equipment state intelligent evaluation and early warning method, device and system |
Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2009175929A (en) * | 2008-01-23 | 2009-08-06 | Toyota Central R&D Labs Inc | Driver condition estimating device and program |
CN102361014A (en) * | 2011-10-20 | 2012-02-22 | 上海大学 | State monitoring and fault diagnosis method for large-scale semiconductor manufacture process |
WO2014092946A1 (en) * | 2012-12-14 | 2014-06-19 | Alcatel-Lucent Usa Inc. | Method and system for disaggregating thermostatically controlled appliance energy usage from other energy usage |
CN104595170A (en) * | 2014-12-18 | 2015-05-06 | 中国矿业大学 | Air compressor monitoring diagnosis system and method adopting adaptive kernel Gaussian hybrid model |
CN104902220A (en) * | 2014-12-09 | 2015-09-09 | 哈尔滨理工大学 | Equipment running state cloud monitoring device based on improved GMM (Gaussian Mixture Model) method |
CN106650122A (en) * | 2016-12-27 | 2017-05-10 | 宝鸡文理学院 | Equipment variable working condition operation risk evaluation method |
CN106651906A (en) * | 2015-10-30 | 2017-05-10 | 国网山西省电力公司电力科学研究院 | Test method for motion characteristic of high-voltage breaker based on improved Gaussian mixture model |
CN107478273A (en) * | 2017-08-14 | 2017-12-15 | 武汉科技大学 | Based on embedded and technology of Internet of things sewer monitoring system and method |
CN107610464A (en) * | 2017-08-11 | 2018-01-19 | 河海大学 | A kind of trajectory predictions method based on Gaussian Mixture time series models |
US20180101949A1 (en) * | 2016-10-07 | 2018-04-12 | Sony Corporation | Automated nuclei area/number estimation for ihc image analysis |
CN108199795A (en) * | 2017-12-29 | 2018-06-22 | 北京百分点信息科技有限公司 | The monitoring method and device of a kind of equipment state |
CN109029992A (en) * | 2018-06-15 | 2018-12-18 | 深圳大学 | The method and system of the bearing failure diagnosis of machine tool chief axis |
CN109405889A (en) * | 2018-12-13 | 2019-03-01 | 中国航空工业集团公司上海航空测控技术研究所 | System and method for for the prediction of development machine working arm decelerator trouble |
CN109702744A (en) * | 2019-01-15 | 2019-05-03 | 北京工业大学 | A method of the robot learning by imitation based on dynamic system model |
-
2019
- 2019-05-21 CN CN201910421340.4A patent/CN110263811B/en active Active
Patent Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2009175929A (en) * | 2008-01-23 | 2009-08-06 | Toyota Central R&D Labs Inc | Driver condition estimating device and program |
CN102361014A (en) * | 2011-10-20 | 2012-02-22 | 上海大学 | State monitoring and fault diagnosis method for large-scale semiconductor manufacture process |
WO2014092946A1 (en) * | 2012-12-14 | 2014-06-19 | Alcatel-Lucent Usa Inc. | Method and system for disaggregating thermostatically controlled appliance energy usage from other energy usage |
CN104902220A (en) * | 2014-12-09 | 2015-09-09 | 哈尔滨理工大学 | Equipment running state cloud monitoring device based on improved GMM (Gaussian Mixture Model) method |
CN104595170A (en) * | 2014-12-18 | 2015-05-06 | 中国矿业大学 | Air compressor monitoring diagnosis system and method adopting adaptive kernel Gaussian hybrid model |
CN106651906A (en) * | 2015-10-30 | 2017-05-10 | 国网山西省电力公司电力科学研究院 | Test method for motion characteristic of high-voltage breaker based on improved Gaussian mixture model |
US20180101949A1 (en) * | 2016-10-07 | 2018-04-12 | Sony Corporation | Automated nuclei area/number estimation for ihc image analysis |
CN106650122A (en) * | 2016-12-27 | 2017-05-10 | 宝鸡文理学院 | Equipment variable working condition operation risk evaluation method |
CN107610464A (en) * | 2017-08-11 | 2018-01-19 | 河海大学 | A kind of trajectory predictions method based on Gaussian Mixture time series models |
CN107478273A (en) * | 2017-08-14 | 2017-12-15 | 武汉科技大学 | Based on embedded and technology of Internet of things sewer monitoring system and method |
CN108199795A (en) * | 2017-12-29 | 2018-06-22 | 北京百分点信息科技有限公司 | The monitoring method and device of a kind of equipment state |
CN109029992A (en) * | 2018-06-15 | 2018-12-18 | 深圳大学 | The method and system of the bearing failure diagnosis of machine tool chief axis |
CN109405889A (en) * | 2018-12-13 | 2019-03-01 | 中国航空工业集团公司上海航空测控技术研究所 | System and method for for the prediction of development machine working arm decelerator trouble |
CN109702744A (en) * | 2019-01-15 | 2019-05-03 | 北京工业大学 | A method of the robot learning by imitation based on dynamic system model |
Non-Patent Citations (2)
Title |
---|
JONG M.HA 等: "Classification of operating conditions of wind turbines for a class-wise condition monitoring strategy", 《RENEWABLE ENERGY》 * |
王恒 等: "基于KPCA-GMM的球磨机状态监测与评估研究", 《矿山机械》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111077876A (en) * | 2019-12-11 | 2020-04-28 | 湖南大唐先一科技有限公司 | Power station equipment state intelligent evaluation and early warning method, device and system |
CN111077876B (en) * | 2019-12-11 | 2021-06-08 | 湖南大唐先一科技有限公司 | Power station equipment state intelligent evaluation and early warning method, device and system |
Also Published As
Publication number | Publication date |
---|---|
CN110263811B (en) | 2021-03-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111459700B (en) | Equipment fault diagnosis method, diagnosis device, diagnosis equipment and storage medium | |
KR102522005B1 (en) | Apparatus for VNF Anomaly Detection based on Machine Learning for Virtual Network Management and a method thereof | |
CN105488539B (en) | The predictor method and device of the generation method and device of disaggregated model, power system capacity | |
CN112817280A (en) | Implementation method for intelligent monitoring alarm system of thermal power plant | |
CN109587008A (en) | Detect the method, apparatus and storage medium of abnormal flow data | |
KR20180108446A (en) | System and method for management of ict infra | |
CN108647707B (en) | Probabilistic neural network creation method, failure diagnosis method and apparatus, and storage medium | |
CN107003992A (en) | Perception associative memory for neural language performance identifying system | |
CN108664700A (en) | Acceleration degradation information Fusion Modeling Method based on uncertain data Envelope Analysis | |
CN107679089A (en) | A kind of cleaning method for electric power sensing data, device and system | |
CN107423190A (en) | A kind of daily record data points to recognition methods and device extremely | |
CN108832478A (en) | A kind of efficient laser control system and control method | |
CN109063885A (en) | A kind of substation's exception metric data prediction technique | |
CN106030565A (en) | Computer performance prediction using search technologies | |
CN107111609A (en) | Lexical analyzer for neural language performance identifying system | |
Gupta et al. | A supervised deep learning framework for proactive anomaly detection in cloud workloads | |
CN115617784A (en) | Data processing system and processing method for informationized power distribution | |
CN113504996B (en) | Load balancing detection method, device, equipment and storage medium | |
CN111198979A (en) | Method and system for cleaning big data for power transmission and transformation reliability evaluation | |
CN117436846B (en) | Equipment predictive maintenance method and system based on neural network | |
CN110888850B (en) | Data quality detection method based on electric power Internet of things platform | |
CN110263811A (en) | A kind of equipment running status monitoring method and system based on data fusion | |
CN112118127B (en) | Service reliability guarantee method based on fault similarity | |
CN115878992A (en) | Monitoring method and monitoring system for comprehensive pipe rack power supply system | |
CN117421994A (en) | Edge application health monitoring method and system |
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 | ||
CB03 | Change of inventor or designer information | ||
CB03 | Change of inventor or designer information |
Inventor after: Liu Jian Inventor before: Liu Jian |