CN106952028A - Dynamoelectric equipment failure is examined and health control method and system in advance - Google Patents
Dynamoelectric equipment failure is examined and health control method and system in advance Download PDFInfo
- Publication number
- CN106952028A CN106952028A CN201710145942.2A CN201710145942A CN106952028A CN 106952028 A CN106952028 A CN 106952028A CN 201710145942 A CN201710145942 A CN 201710145942A CN 106952028 A CN106952028 A CN 106952028A
- Authority
- CN
- China
- Prior art keywords
- dynamoelectric
- dynamoelectric equipment
- equipment
- data
- health
- 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 OR CALCULATING; 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- General Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (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)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The present invention provides a kind of dynamoelectric equipment failure and examined in advance to be included with health control method and system, this method：Data acquisition, obtains the data message of dynamoelectric equipment；Self diagnosis, feature extraction is carried out to historical data information of a certain dynamoelectric equipment under different operational modes and health status and model is set up, the data message for recycling the model set up to obtain current state is compared with historical data information, the current health state of automatic identification this dynamoelectric equipment；Health status is predicted, the change of this dynamoelectric equipment future health status is predicted according to the current health state and history health status of this dynamoelectric equipment obtained after self diagnosis；Cluster analysis, is clustered and com-parison and analysis according to the current health state of separate unit dynamoelectric equipment to the data message of many dynamoelectric equipments in dynamoelectric equipment cluster, obtains health status grade and the risk distribution of many dynamoelectric equipments.
Description
Technical field
The present invention relates to the prognostic and health management field of equipment, and more particularly to a kind of dynamoelectric equipment failure is examined in advance
With health control method and system.
Background technology
With Chinese society's rapid development of economy, the performance of various dynamoelectric equipments is improved constantly, towards high speed, heavy duty
Change, intelligentized direction is continued to develop, system composition complexity is also continuously increased, and makes reliability, maintainability of dynamoelectric equipment etc.
Problem is outstanding day by day.The offline periodic inspection stage being rested on the current maintenance to dynamoelectric equipment, this method real-time is poor more,
Maintenance efficiency is relatively low, and the maintenance of " this, which is repaiied, does not repair, should not repair and but repair " can be caused not enough and excessive shortcoming is repaired.It is related both at home and abroad
Unit has done numerous studies work in terms of dynamoelectric equipment is based on State Maintenance and prospective maintenance, it is proposed that many dynamoelectric equipments
Failure predication and diagnostic method have simultaneously built related dynamoelectric equipment monitoring system.
However, these existing failure predications and diagnostic method are mostly to enter for single device under single or constant duty
Capable.And dynamoelectric equipment problems faced is to need to be monitored health status of the multiple devices under multi-state, compare at present
Compared with and prediction, traditional failure predication and diagnostic method have some limitations.Further, existing dynamoelectric equipment monitoring
Method and system only focuses on the status data of collecting device in data acquisition, and to many important information for example equipment is used when
Floor data, ambient parameter, maintaining record and performance class data there is no effective synchronous recording, cause the tune of these data
Become very difficult with mutual control, and when being acquired to running state data often using fixed and indifference
Acquisition strategies, cause the consumption most of the time to gather many useless information.Further, existing dynamoelectric equipment monitoring
Method and system can only provide the information such as alarm, maintenance direction suggestion according to analysis result, but be not based on these prisons
Measurement information carries out decision optimization and system reconfiguration.
Further, since needing to store to health status monitoring of the multiple devices under multi-state and prediction and handling substantial amounts of
Data, the simple real-time processing by the hardware configuration of raising computer to realize data becomes to be increasingly difficult to, and current
One of the problem of big data computational methods are present is to need the artificial calculation server number of nodes to configure processing data, time-consuming
Arduously.And rely on expertises many dynamoelectric equipment monitoring systems during analysis more, exist a large amount of manual analyzings,
Visually observe, parameter examination such as gathers at the defect.
The content of the invention
The present invention in order to overcome existing dynamoelectric equipment can not realize health status under multiple devices multi-state monitor with
And examine in advance there is provided a kind of dynamoelectric equipment failure suitable for many equipment multi-states the problem of prediction and health control method and be
System.
To achieve these goals, the present invention provides a kind of dynamoelectric equipment failure and examined in advance and health control method, this method
Including：
Data acquisition, obtains the data message of dynamoelectric equipment；
Self diagnosis, is carried out special to historical data information of a certain dynamoelectric equipment under different operational modes and health status
Levy extraction and model is set up, the data message for recycling the model set up to obtain current state is compared with historical data information
Compared with the current health state of automatic identification this dynamoelectric equipment；
Health status is predicted, according to the current health state of this dynamoelectric equipment obtained after self diagnosis and the healthy shape of history
State predicts the change of this dynamoelectric equipment future health status；
Cluster analysis, according to the current health state of separate unit dynamoelectric equipment to many dynamoelectric equipments in dynamoelectric equipment cluster
Data message clustered and com-parison and analysis, obtain health status grade and the risk distribution of many dynamoelectric equipments.
In one embodiment of the invention, data message is the Life cycle information of dynamoelectric equipment, Life cycle information
Including running state data.
In one embodiment of the invention, upper strata Customization Tool and bottom are used during self diagnosis and health status prediction
Calls tool carries out feature extraction, model to the data message of a certain dynamoelectric equipment and set up and health status identification, upper strata
Customization Tool calls the data analysis of each tool storage room in bottom calls tool according to the data message of this dynamoelectric equipment automatically
Model.
In one embodiment of the invention, upper strata Customization Tool calls the data analysis of each tool storage room in bottom calls tool
The step of model, includes：
Upper strata Customization Tool is respectively by the importance degree of the running state data of dynamoelectric equipment He remaining Life cycle information
Grade is customized；
Calculated, obtained according to the importance degree grade of the running state data of dynamoelectric equipment and remaining Life cycle information
Obtain the weight of each Data Analysis Model in each tool storage room in bottom calls tool；
The maximum Data Analysis Model of weight in each tool storage room is chosen to divide the data message of this dynamoelectric equipment
Analysis.
In one embodiment of the invention, feature extraction tools storehouse, state estimation tool storage room, event are included in bottom calls tool
Hinder diagnostic tool storehouse, failure and life prediction tool storage room.
In one embodiment of the invention, obtain dynamoelectric equipment data message when according to event information, moving target and
Equipment state, which is automatically generated, to be met the data sampling control signal of information analysis demand to carry out data acquisition.
In one embodiment of the invention, during self diagnosis, health status prediction and cluster analysis, according to what is got
The amount of data message automatically configures the number of nodes of calculation server.
In one embodiment of the invention, dynamoelectric equipment failure is examined in advance also to be included according to many obtained with health control method
The health status grade of dynamoelectric equipment includes the control to separate unit dynamoelectric equipment to the via Self-reconfiguration of dynamoelectric equipment Controlling model, via Self-reconfiguration
The adjustment of simulation and/or the adjustment of Controlling model to dynamoelectric equipment cluster.
In one embodiment of the invention, using visual mode by the current health state of separate unit dynamoelectric equipment and/or
Health status is predicted and/or the health status grade of many dynamoelectric equipments pushes to client.
Another aspect of the present invention also provide a kind of dynamoelectric equipment failure examine in advance with it is health management system arranged, the system include data
Acquisition module, self diagnosis module, health status prediction module and cluster analysis module.Data acquisition module obtains dynamoelectric equipment
Data message.Self diagnosis module is entered to historical data information of a certain dynamoelectric equipment under different operational modes and health status
Row feature extraction and model are set up, and the data message for recycling the model set up to obtain current state enters with historical data information
Row compares, the current health state of automatic identification this dynamoelectric equipment.Health status prediction module is according to obtaining after self diagnosis
The current health state and history health status of this dynamoelectric equipment predict the change of this dynamoelectric equipment future health status.Collection
Cluster analysis module is according to the data of the current health state of separate unit dynamoelectric equipment to many dynamoelectric equipments in dynamoelectric equipment cluster
Information is clustered and com-parison and analysis, obtains health status grade and the risk distribution of many dynamoelectric equipments.
In summary, the dynamoelectric equipment failure that provides of the present invention examine in advance with health control method and system, in self diagnosis mistake
It is modeled in journey by historical data of the dynamoelectric equipment under different operational modes and health status, will using the model of foundation
The data message that current state is obtained is compared with historical data information, the current health shape of automatic identification this dynamoelectric equipment
State, and then carry out health status prediction and cluster analysis.Following health of dynamoelectric equipment can be obtained by being predicted by health status
State and variation tendency, cluster analysis are that the data message of the multiple devices in dynamoelectric equipment cluster is clustered and analyzed
Compare.
The present invention establishes health status sample of the separate unit dynamoelectric equipment in different time by the method for self diagnosis, each
The work condition state and health status of this dynamoelectric equipment are contained in individual health status sample.Machine of the cluster analysis to similar operating condition
Denso is standby to carry out cluster analysis, and the health parameter to the different dynamoelectric equipments under same time and identical service condition is entered
Row compares, and the equipment otherness and which equipment that can be oriented rapidly in dynamoelectric equipment cluster are in abnormal operation shape
State, realizes the analysis of dynamoelectric equipment health and makes the order of priority of maintenance, realize the health control of dynamoelectric equipment.
For above and other objects of the present invention, feature and advantage can be become apparent, preferred embodiment cited below particularly,
And coordinate accompanying drawing, it is described in detail below.
Brief description of the drawings
The dynamoelectric equipment failure that Fig. 1 show one embodiment of the invention offer examines flow chart with health control method in advance.
Fig. 2 show the self diagnosis that one embodiment of the invention provides and health status prediction process, and Customization Tool is adjusted at the middle and upper levels
With the structural representation of bottom calls tool.
The dynamoelectric equipment failure that Fig. 3 show one embodiment of the invention offer is examined and calculate node in health control method in advance
The flow chart that quantity is automatically configured.
The dynamoelectric equipment failure that Fig. 4 show one embodiment of the invention offer is examined and health management system arranged structural representation in advance
Figure.
Fig. 5 show the curve map for the performance degradation that dynamoelectric equipment is monitored using health value.
Fig. 6 is shown using in each critical component in healthy radar map monitoring separate unit dynamoelectric equipment or dynamoelectric equipment cluster
Each equipment decline distribution schematic diagram.
Fig. 7 show the schematic diagram that fault mode is identified using healthy map.
Embodiment
Include as shown in figure 1, the dynamoelectric equipment failure that the present embodiment is provided is examined in advance with health control method：Data acquisition,
Obtain the data message (step S1) of dynamoelectric equipment.Self diagnosis, to a certain dynamoelectric equipment in different operational modes and healthy shape
Historical data under state carries out feature extraction and model is set up, the data message for recycling the model set up to obtain current state
It is compared with historical data information, the current health state (step S2) of automatic identification this dynamoelectric equipment.Health status is pre-
Survey, this dynamoelectric equipment is predicted according to the current health state and history health status of this dynamoelectric equipment obtained after self diagnosis
The change (step S3) of future health status.Cluster analysis, according to the health status sample of separate unit dynamoelectric equipment to dynamoelectric equipment
The data message of many dynamoelectric equipments in cluster is clustered and com-parison and analysis, obtains health status of many dynamoelectric equipments etc.
Level and risk distribution (step S4).
This method starts from step S1, in this step, and data message is Life cycle information, Life cycle packet
Including running state data and floor data, ambient parameter, application scenarios, maintaining record, performance class data etc., remaining is complete raw
Order cycle information.
In the present embodiment, the running state data of dynamoelectric equipment is gathered using distributed embedded data collecting system,
Running state data can be obtained from the sensor and dynamoelectric equipment controller of installation.However, the present invention does not make any to this
Limit.In other embodiments, the running state data of dynamoelectric equipment can be gathered using other types of data acquisition equipment.Institute
State the signal values such as output voltage, output current, power output of the running state data including dynamoelectric equipment.
When carrying out the running state data collection of dynamoelectric equipment, what acquisition strategies fix and indiscriminate were collected
The data for only there was only fraction in mass data are useful, gather that consumed resource is many but utilization rates of data very
It is low.In the present embodiment, be arranged on collection dynamoelectric equipment data message when according to event information, moving target and equipment state
Automatically generate and meet the data sampling control signal of information analysis demand to carry out data acquisition.Specifically, in data acquisition
When acquisition condition is set, when the acquisition condition is triggered, system generating data acquisition control signal carry out data acquisition.As worked as
The virtual value of the output current of dynamoelectric equipment fluctuates log-on data during more than 20% and gathered；Or when a certain alarm signal is triggered
When turn-on data gather.The setting can effectively reduce the collection and transmission of hash significantly, improve the utilizability of data.
Remaining Life cycle information of dynamoelectric equipment includes the floor data in dynamoelectric equipment running, environment ginseng
The information such as number, application scenarios, maintaining record, performance class data.Floor data refers to the load of dynamoelectric equipment, rotating speed, operation
The conditions of work such as pattern, such data can be obtained from controller.Ambient parameter refer to be possible to influence dynamoelectric equipment performance and
The environmental information of running status, including but not limited to following information：Temperature, wind speed, state of weather etc..Ambient parameter information can
The rule for being easy to analysis machine Denso received shipment row affected by environment, by the performance change caused by dynamoelectric equipment state and environmental change
Make a distinction.Dynamoelectric equipment maintaining record includes examining a little in dynamoelectric equipment Life cycle, maintenance, repair and guarantor
Support and change record, the reference that these data update as dynamoelectric equipment state is mutually compareed with the status data of dynamoelectric equipment, can
Carry out the health forecast model of more new equipment as the more new node of dynamoelectric equipment state, these data can be from ERP, EAM, BOM etc.
Access and obtain in system.Dynamoelectric equipment performance class data refer to the performance related to dynamoelectric equipment operation and run shape to dynamoelectric equipment
The index class data that state is judged, can be pasted by the analysis to dynamoelectric equipment performance indicators to the status data of different time sections
The label of upper health, inferior health or failure, is easy to define the health degree of dynamoelectric equipment.
After running state data and remaining Life cycle information is obtained, work is customized using upper strata during self diagnosis
Tool and bottom calls tool are carried to carrying out feature to data of a certain dynamoelectric equipment under different operational modes and health status
Take, model is set up and health status identification, upper strata Customization Tool calls bottom automatically according to the data message of this dynamoelectric equipment
The Data Analysis Model of each tool storage room in layer calls tool.Describe in detail the process of self diagnosis below with reference to Fig. 2.
In the Customization Tool of upper strata, to the importance degree of the running state data of dynamoelectric equipment and remaining Life cycle information
Grade is configured.As shown in Fig. 2 in the present embodiment, selection signal feature carries out importance degree grade in running state data
Configuration, and select application scenarios to be configured in remaining Life cycle information, and represent importance degree grade successively from 1 to 5
Increase.However, the present invention is not limited in any way to this.In other embodiments, other running state datas can be used and other
One or more of Life cycle information carries out importance degree grade configuration.Match somebody with somebody in the importance degree grade of Fig. 2 signal characteristic
In putting, the signal analyzed is rich in high-frequency signal and non-stationary signal, therefore imparting high-frequency signal and non-stationary signal are higher
Importance degree grade, and the importance degree grade for assigning stationary signal and low frequency signal is relatively low.And in application scenarios insufficient system
System knowledge is the important attribute of system, therefore assigns higher importance degree grade, and high dynamic system and sufficient systematic knowledge with
And low cost is not then critically important, therefore assign relatively low importance degree grade.
Calculated by the importance degree grade of running state data in the Customization Tool of upper strata and remaining Life cycle information
Obtain the weight of each Data Analysis Model in each tool storage room in bottom calls tool.As shown in Fig. 2 bottom calls tool bag
Include in feature extraction, state estimation, fault diagnosis and failure and four tool storage rooms of life prediction, each tool storage room and contain four
Data Analysis Model.However, the present invention is not limited in any way to this.The method that computational methods use weighted arithmetic mean, with spy
Levy each in characteristics of signals and application scenarios in explanation exemplified by the weight calculation that time frequency signal is analyzed in extracting, upper strata Customization Tool
The weighing factor that sub- content is analyzed time frequency signal is respectively 0.05,0.06,0.07,0.05,0.05,0.05,0.06,
0.05, then time frequency signal analysis weight calculation be：
(0.05 × 1+0.06 × 5+0.07 × 5+0.05 × 1+0.05 × 1+0.05 × 1+0.06 × 5+0.05 × 1)/8=
0.15.However, the present invention is not limited in any way to computational methods.In the present embodiment, obtained after calculating feature extraction this
In one tool storage room, the weight of time frequency signal analysis is 0.15, and the weight of WAVELET PACKET DECOMPOSITION is 0.25, and the weight of autoregression model is
0.09, the weight of Fourier transformation is 0.13；In state estimation tool storage room, the weight of statistical regression is 0.09, Feature Mapping
Weight be 0.07, statistical model identification weight be 0.12, the weight of hidden Markov model is 0.08；In fault diagnosis work
Have in storehouse, the weight of SVMs is 0.09, and the weight of hidden Markov model is 0.08, the weight of bayesian belief networks
It is 0.06, the weight of adaptive resonance theory II is 0.12.
The maximum number of weight in each tool storage room is chosen after the weight of each Data Analysis Model in each database is obtained
The data message of dynamoelectric equipment is analyzed according to analysis model.In the present embodiment, using this model pair of WAVELET PACKET DECOMPOSITION
Historical data information of the dynamoelectric equipment got under different operational modes and health status carries out feature extraction, according to extraction
Feature the current state of dynamoelectric equipment is estimated using statistical-simulation spectrometry, afterwards in conjunction with historical data information use
Adaptive resonance theory II carries out fault diagnosis, obtains the current health state of this dynamoelectric equipment.
In the present embodiment, step S3 is performed after the current health state of this dynamoelectric equipment is obtained, using failure and
Life Prediction Model is predicted to the future health status of this dynamoelectric equipment.In the present embodiment, in health status prediction
When same call in bottom calls tool by the way of the Data Analysis Model of each tool storage room to obtain using upper strata Customization Tool
Failure and Life Prediction Model.In the present embodiment, failure and Life Prediction Model include four models, are that autoregression is slided respectively
Dynamic average, recurrent neural networks prediction, fuzzy logic prediction and SVMs.After the logical calculated in step S2
Obtain, the average weight of Regressive is 0.13, the weight of recurrent neural networks prediction is 0.15, the weight of fuzzy logic prediction
It is 0.12, the weight of SVMs is 0.09.Failure of the maximum recurrent neural networks prediction of weight selection to dynamoelectric equipment
And the life-span is predicted, the prediction of the health status of separate unit dynamoelectric equipment is realized.
In self diagnosis and health status prediction, each work in bottom calls tool is obtained by upper strata Customization Tool automatically
Most suitable Data Analysis Model in tool storehouse is analyzed come the data message to this dynamoelectric equipment, and the analysis of data is disobeyed
Rely in expertise, without manual analyzing and visually observing, substantially increase the accuracy that dynamoelectric equipment health status is examined in advance.It is logical
The mode for crossing self diagnosis is established in health status sample of the separate unit dynamoelectric equipment under different time, each health status sample
Contain the work condition state and health status of dynamoelectric equipment.
On the basis of self diagnosis, step S4 is performed, cluster analysis is filled to the electromechanical of similar operating condition in dynamoelectric equipment cluster
It is standby to be clustered and com-parison and analysis, to the health parameter of the different dynamoelectric equipments under same time and identical service condition
It is compared, the equipment otherness and which equipment that can be oriented rapidly in dynamoelectric equipment cluster are in abnormal operation
State, so as to obtain the health status grade of many dynamoelectric equipments, finally makes the order of priority of maintenance, realizes many machines
Electricity is equipped in the diagnosis of the health status under multi-state.
Very multidata calculating can be related to during self diagnosis, health status prediction and cluster analysis, to improve
Self diagnosis and the calculating speed of cluster analysis, in calculating process, system is automatically configured according to the amount of the data message got
The number of nodes of calculation server.Specific configuration process as shown in figure 3, be more than when the calculating time of current calculation server or
During equal to the desired calculating time, increase the number of nodes of calculation server.This is arranged on while meet user's computational efficiency
The waste of computing resource is not only reduced, while also avoid the shortcoming that traditional manual adjustment calculate node wastes time and energy.
In the present embodiment, dynamoelectric equipment failure is examined in advance also includes step S5 with health control method：It is many according to what is obtained
Via Self-reconfiguration of the health status grade of platform dynamoelectric equipment to dynamoelectric equipment Controlling model.Via Self-reconfiguration is included to separate unit dynamoelectric equipment
The adjustment of Controlling model and/or the adjustment of Controlling model to dynamoelectric equipment cluster.When to the Controlling model of separate unit dynamoelectric equipment
When being adjusted, the health status and/or maintenance direction opinion of this dynamoelectric equipment of acquisition are sent to this dynamoelectric equipment
Controller in, controller adjusts in this dynamoelectric equipment corresponding operation according to health status and/or maintenance direction opinion joins
Number, to extend the service life of this dynamoelectric equipment.When the Controlling model to dynamoelectric equipment cluster is adjusted, by cluster point
The health status and/or maintenance direction opinion of many dynamoelectric equipments obtained after analysis are sent to the controller of dynamoelectric equipment cluster
In, the Controlling model that controller readjusts dynamoelectric equipment cluster improves the operation load of healthy dynamoelectric equipment in cluster, and
There is the load reduction of the dynamoelectric equipment of decline in health, to ensure the fan-out capability of whole dynamoelectric equipment cluster.However, of the invention
Specific control mode to electromechanical cluster is not limited in any way.
Grasp the current health state and/or future health status of dynamoelectric equipment in real time for ease of user or manufacturer,
And the service life of dynamoelectric equipment, drop can be improved according to maintenance direction suggestion to the maintenance of being predicted property of dynamoelectric equipment and scheduling
Low fault-free downtime, in the present embodiment, on the one hand the data obtained after health status prediction or cluster analysis are carried out forever
Long property is preserved, and is such as preserved using Mongo dB, HBase NoSQL databases；On the other hand, will by application server
Data after cluster analysis are presented to subscription client in real time, and subscription client can use WEB client side, mobile phone A PP and AR/VR
One or more of combinations in are presented.In other embodiments, application server can also directly invoke NoSQL data
Data in storehouse are presented to subscription client.
When the data after by diagnostic analysis, health status prediction or cluster analysis are presented to subscription client, different layers
The dynamoelectric equipment health status of level is represented using different visualization presentation modes, user is readily appreciated and decision-making.Such as
The decline in health of critical component or single dynamoelectric equipment for dynamoelectric equipment is assessed and can expressed with health degree, and described is strong
Kang Du is the dimensionless between one 0~1, and 0, which represents decline, arrives unacceptable state, and 1 represents health status, as shown in Figure 5.
The risk distribution situation of decline distribution situation or dynamoelectric equipment cluster for each critical component in dynamoelectric equipment, can be used
Radar map (as shown in Figure 6) recognizes, each axle on described radar map represent in a dynamoelectric equipment each is crucial
Each equipment in part or dynamoelectric equipment cluster, as shown in the J1 to J6 in Fig. 6, each axle is the health degree between 0~1
Value, can help user to position the weak link in dynamoelectric equipment or cluster rapidly, and formulation safeguards priority ranking accordingly.
It can be recognized for the fault mode of each critical component in dynamoelectric equipment using healthy map (as shown in Figure 7), healthily
Figure is a grid chart being made up of many nodes, above each region correspond to a kind of fault mode respectively, according to healthy special
The current state of dynamoelectric equipment is incident upon on healthy map by the similitude levied, and the label in the region means that object currently strong
Health pattern.
Examine corresponding with health control method in advance with above-mentioned dynamoelectric equipment failure, the present embodiment also provides a kind of electromechanical dress
Standby failure examine in advance with it is health management system arranged, the system includes data acquisition module 10, self diagnosis module 20, health status and predicts mould
Block 30 and cluster analysis module 40.Data acquisition module 10 obtains the data message of dynamoelectric equipment.Self diagnosis module 20 is to a certain
Historical data information of the platform dynamoelectric equipment under different operational modes and health status carries out feature extraction and model is set up, then profit
The data message obtained with the model with current state is compared, the current health state of automatic identification this dynamoelectric equipment.
Health status prediction module is pre- according to the current health state and history health status of this dynamoelectric equipment obtained after self diagnosis
Survey the change of this dynamoelectric equipment future health status.Cluster analysis module 30 is according to the health status of separate unit dynamoelectric equipment to machine
Denso is clustered and com-parison and analysis for the data message of many dynamoelectric equipments in cluster, obtains the health of many dynamoelectric equipments
State grade and risk distribution.
In the present embodiment, data acquisition module 10 includes distributed embedded data collecting system 11 and edge device
12, the running state data of distributed embedded data collecting system 11 collection dynamoelectric equipment and by running state data transmit to
Edge device 12.The synchronous floor data obtained in dynamoelectric equipment running of edge device 12, ambient parameter, maintaining note
Remaining Life cycle information of the dynamoelectric equipments such as record, performance class data.The edge device 12 is according to the difference of application scenario
Can be distributed locomotive main frame (such as train, electric motor car), home server (blower fan, robot).
The one side of edge device 12 is by modes such as Wi-Fi, cellular network, satellites by the data information transfer of dynamoelectric equipment
To data relay module 100, on the other hand its own carries out characteristic that signal transacting obtains dynamoelectric equipment to these information
And monitoring index, characteristic is transmitted to data relay module 100 by modes such as Wi-Fi, cellular network, satellites, will be supervised
The subscription client 200 that survey index is transmitted to edge device is monitored alarm to the running status of dynamoelectric equipment.Data
Transit module 100 is the operation such as to be converged, cleaned, arranged to initial data, can be ordered using the distributed post of high-throughput
Read message system to be handled, such as Kafka systems.Convergence is by the Data Collection of separate sources to high in the clouds；Data cleansing
It is that redundancy, unworthy data such as are merged or deleted at the operation；Data preparation is according to certain to the data after cleaning
Rule such as time-sequencing, data type sort housekeeping operation is ranked up to facilitate the storage and analysis of follow-up data.
In the present embodiment, self diagnosis module 20, health status prediction module 30 and cluster analysis module 40 are integrated in greatly
In data calculating platform 300.Big data calculating platform be Map/Reduce off-line datas processing framework based on Hadoop or
Real-time distributed processing computing architecture based on Spark.However, the present invention is not limited in any way to this.
Using upper strata Customization Tool and bottom calls tool to a certain electromechanics during self diagnosis and health status prediction
The current data information of equipment is compared with historical data information, and upper strata Customization Tool is believed according to the data of this dynamoelectric equipment
Breath calls the Data Analysis Model of each tool storage room in bottom calls tool automatically.Specific step is：Upper strata Customization Tool point
The importance degree grade of the running state data of dynamoelectric equipment and remaining Life cycle information is not customized.According to electromechanics dress
Standby running state data and the importance degree grade of remaining Life cycle information obtain each tool storage room in bottom calls tool
The weight of interior each Data Analysis Model.The Data Analysis Model of weight maximum in each tool storage room is chosen to this dynamoelectric equipment
Data message analyzed.
After the completion of self diagnosis, health status prediction module is using failure with Life Prediction Model and according to the electromechanics of acquisition
The current health state of equipment predicts the change of dynamoelectric equipment future health status.
Further, after the completion of self diagnosis, cluster analysis module is filled to the electromechanical of similar operating condition in dynamoelectric equipment cluster
It is standby to be clustered and com-parison and analysis, to the health parameter of the different dynamoelectric equipments under same time and identical service condition
It is compared, the equipment otherness and which equipment that can be oriented rapidly in dynamoelectric equipment cluster are in abnormal operation
State, so as to obtain the health status grade of many dynamoelectric equipments, finally makes the order of priority of maintenance, realizes many machines
Electricity is equipped in the diagnosis of the health status under multi-state.
In the present embodiment, dynamoelectric equipment failure is examined in advance also includes memory module 50 with health management system arranged.In this implementation
In example, memory module 50 includes distributed file storage system 51, the database 52 based on internal memory, NoSQL databases 53.Distribution
Formula document storage system 51 can realize the storage and management of mass data, can realize in many dynamoelectric equipment Life cycle
Operation information storage, using the distributed file storage system HDFS based on Hadoop.Database 52 based on internal memory is used
The data storage methods such as Memcached, Redis, can greatly shorten the time that data arrive at subscription client, improve real-time
Property.NoSQL databases 53 are used to permanently store dynamoelectric equipment state of health data, using Mongo dB, HBase etc.
Storage and operation of the NoSQL database realizings to data.However, the present invention is not limited in any way to this.In other embodiments,
The data memory module of other structures can be used.
In the present embodiment, for the convenience of the user or manufacturer grasps the health status of dynamoelectric equipment, dynamoelectric equipment in real time
Failure is examined in advance also includes application server 60 with health management system arranged.Application server 60 is obtained in big data calculating platform 300
Self diagnosis, the data of health status prediction or cluster analysis or the data for calling the memory storage of memory module 50, and pass through data
Host-host protocol is by these data-pushings to subscription client 200.WEB client side, mobile phone A PP can be used in subscription client 200
And one or more of combinations in AR/VR etc. are presented.
In the present embodiment, dynamoelectric equipment failure is examined in advance also includes Self-Reconfigurable Module 70 with health management system arranged.Via Self-reconfiguration
Module 70 is according to the via Self-reconfiguration of the health status grades of many obtained dynamoelectric equipments to dynamoelectric equipment Controlling model.Via Self-reconfiguration bag
The adjustment to the Controlling model of separate unit dynamoelectric equipment and the adjustment of the Controlling model to dynamoelectric equipment cluster are included, via Self-reconfiguration can extend
The service life of separate unit dynamoelectric equipment or the fan-out capability for improving dynamoelectric equipment cluster.
In summary, the dynamoelectric equipment failure that provides of the present invention examine in advance with health control method and system, in self diagnosis mistake
It is modeled in journey by historical data of the dynamoelectric equipment under different operational modes and health status, will using the model of foundation
The data message that current state is obtained is compared with historical data information, the current health shape of automatic identification this dynamoelectric equipment
State, and then carry out health status prediction and cluster analysis.Following health of dynamoelectric equipment can be obtained by being predicted by health status
State and variation tendency, cluster analysis are that the data message of the multiple devices in dynamoelectric equipment cluster is clustered and analyzed
Compare.
The present invention establishes health status sample of the separate unit dynamoelectric equipment in different time by the method for self diagnosis, each
The work condition state and health status of this dynamoelectric equipment are contained in individual health status sample.Machine of the cluster analysis to similar operating condition
Denso is standby to be clustered and com-parison and analysis, to the health status of the different dynamoelectric equipments under same time and identical service condition
Parameter is compared, and the equipment otherness and which equipment that can be oriented rapidly in dynamoelectric equipment cluster are in exception
Running status, realizes the analysis of dynamoelectric equipment health and makes the order of priority of maintenance, realize the health pipe of dynamoelectric equipment
Reason.
It is any to know this skill although the present invention is disclosed above by preferred embodiment, but is not limited to the present invention
Skill person, without departing from the spirit and scope of the present invention, can make a little change and retouching, therefore protection scope of the present invention is worked as
It is defined depending on claims scope claimed.
Claims (10)
1. a kind of dynamoelectric equipment failure is examined and health control method in advance, it is characterised in that including：
Data acquisition, obtains the data message of dynamoelectric equipment；
Self diagnosis, carries out feature to historical data information of a certain dynamoelectric equipment under different operational modes and health status and carries
Take and set up with model, the data message for recycling the model set up to obtain current state is compared with historical data information,
The current health state of automatic identification this dynamoelectric equipment；
Health status is predicted, pre- according to the current health state and history health status of this dynamoelectric equipment obtained after self diagnosis
Survey the change of this dynamoelectric equipment future health status；
Cluster analysis, according to number of the current health state of separate unit dynamoelectric equipment to many dynamoelectric equipments in dynamoelectric equipment cluster
It is believed that breath is clustered and com-parison and analysis, health status grade and the risk distribution of many dynamoelectric equipments are obtained.
2. dynamoelectric equipment failure according to claim 1 is examined and health control method in advance, it is characterised in that the data letter
The Life cycle information for dynamoelectric equipment is ceased, the Life cycle information includes running state data.
3. dynamoelectric equipment failure according to claim 2 is examined and health control method in advance, it is characterised in that in self diagnosis and
The data message of a certain dynamoelectric equipment is entered using upper strata Customization Tool and bottom calls tool during health status prediction
Row feature extraction, model are set up and health status identification, upper strata Customization Tool according to the data message of this dynamoelectric equipment from
Move the Data Analysis Model for calling each tool storage room in bottom calls tool.
4. dynamoelectric equipment failure according to claim 3 is examined and health control method in advance, it is characterised in that upper strata customizes work
The step of tool calls the Data Analysis Model of each tool storage room in bottom calls tool includes：
Upper strata Customization Tool is respectively by the running state data of dynamoelectric equipment and the importance degree grade of remaining Life cycle information
It is customized；
Calculated according to the importance degree grade of the running state data of dynamoelectric equipment and remaining Life cycle information, obtain bottom
In layer calls tool in each tool storage room each Data Analysis Model weight；
The maximum Data Analysis Model of weight in each tool storage room is chosen to analyze the data message of this dynamoelectric equipment.
5. dynamoelectric equipment failure according to claim 3 is examined and health control method in advance, it is characterised in that bottom calls work
Feature extraction tools storehouse, state estimation tool storage room, failure diagnosis tool storehouse, failure and life prediction tool storage room are included in tool.
6. dynamoelectric equipment failure according to claim 1 is examined and health control method in advance, it is characterised in that electromechanical obtaining
The data for meeting information analysis demand are automatically generated during the data message of equipment according to event information, moving target and equipment state
Sampling control signal carries out data acquisition.
7. dynamoelectric equipment failure according to claim 1 is examined and health control method in advance, it is characterised in that self diagnosis,
Health status is predicted with during cluster analysis, and the node of calculation server is automatically configured according to the amount of the data message got
Quantity.
8. dynamoelectric equipment failure according to claim 1 is examined and health control method in advance, it is characterised in that the electromechanical dress
Standby failure is examined in advance also include the health status grade according to many obtained dynamoelectric equipments with health control method to dynamoelectric equipment
The via Self-reconfiguration of Controlling model, the via Self-reconfiguration includes the adjustment to the Controlling model of separate unit dynamoelectric equipment and/or to dynamoelectric equipment
The adjustment of the Controlling model of cluster.
9. dynamoelectric equipment failure according to claim 1 is examined and health control method in advance, it is characterised in that using visualization
Mode by the prediction of the current health state and/or health status of separate unit dynamoelectric equipment and/or the healthy shape of many dynamoelectric equipments
State grade pushes to client.
10. a kind of dynamoelectric equipment failure examine in advance with it is health management system arranged, it is characterised in that including：
Data acquisition module, obtains the data message of dynamoelectric equipment；
Self diagnosis module, is carried out special to historical data information of a certain dynamoelectric equipment under different operational modes and health status
Levy extraction and model is set up, the data message for recycling the model set up to obtain current state is compared with historical data information
Compared with the current health state of automatic identification this dynamoelectric equipment；
Health status prediction module, according to the current health state of this dynamoelectric equipment obtained after self diagnosis and the healthy shape of history
State predicts the change of this dynamoelectric equipment future health status；
Cluster analysis module, according to the current health state of separate unit dynamoelectric equipment to many dynamoelectric equipments in dynamoelectric equipment cluster
Data message clustered and com-parison and analysis, obtain health status grade and the risk distribution of many dynamoelectric equipments.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710145942.2A CN106952028A (en) | 2017-03-13 | 2017-03-13 | Dynamoelectric equipment failure is examined and health control method and system in advance |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710145942.2A CN106952028A (en) | 2017-03-13 | 2017-03-13 | Dynamoelectric equipment failure is examined and health control method and system in advance |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106952028A true CN106952028A (en) | 2017-07-14 |
Family
ID=59466891
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710145942.2A Pending CN106952028A (en) | 2017-03-13 | 2017-03-13 | Dynamoelectric equipment failure is examined and health control method and system in advance |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106952028A (en) |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107464023A (en) * | 2017-08-16 | 2017-12-12 | 新疆金风科技股份有限公司 | The on-line study method and apparatus of life cycle forecast model |
| CN107767056A (en) * | 2017-10-25 | 2018-03-06 | 上海电气上重碾磨特装设备有限公司 | A kind of condition monitoring for power station coal pulverizer with it is health management system arranged |
| CN108062603A (en) * | 2017-12-29 | 2018-05-22 | 国网福建省电力有限公司 | Based on distribution power automation terminal life period of an equipment life-span prediction method and system |
| CN108280543A (en) * | 2018-01-17 | 2018-07-13 | 杭州安脉盛智能技术有限公司 | The adaptive equipment health degree appraisal procedure of operating mode based on classification Regression Model |
| CN108398934A (en) * | 2018-02-05 | 2018-08-14 | 常州高清信息技术有限公司 | The system that a kind of equipment fault for rail traffic monitors |
| CN108564236A (en) * | 2017-09-27 | 2018-09-21 | 国网安徽省电力有限公司 | A kind of dual protection equipment Risk discrimination method based on big data Distributed Calculation |
| CN108591104A (en) * | 2018-04-18 | 2018-09-28 | 广东寰球智能科技有限公司 | A kind of Research on Fan Fault Forecasting based on cloud platform and health management system arranged, method |
| CN109214529A (en) * | 2018-08-31 | 2019-01-15 | 深圳市紫衡技术有限公司 | A kind of Mechatronic Systems preventive maintenance method and system, equipment, storage medium |
| CN109242356A (en) * | 2018-10-25 | 2019-01-18 | 黎泽芝 | Construction of the highway safe production management system based on mobile Internet |
| CN109582657A (en) * | 2018-11-28 | 2019-04-05 | 国家电网有限公司 | Capacitor faults prediction technique based on machine learning and big data analysis |
| CN110474979A (en) * | 2019-08-13 | 2019-11-19 | 北京软通智城科技有限公司 | A kind of remote assisting system, method, platform and storage medium |
| CN110737732A (en) * | 2019-10-25 | 2020-01-31 | 广西交通科学研究院有限公司 | electromechanical equipment fault early warning method |
| CN111105074A (en) * | 2019-11-22 | 2020-05-05 | 江南机电设计研究所 | Fault prediction method based on improved deep belief learning |
| CN111325397A (en) * | 2020-02-19 | 2020-06-23 | 国网山东省电力公司宁阳县供电公司 | Data analysis system based on power data backup state |
| CN112149791A (en) * | 2020-09-22 | 2020-12-29 | 国网河南省电力公司鹤壁供电公司 | Low-voltage risk assessment system based on neural network recognition and fuzzy analysis |
| CN112152698A (en) * | 2020-09-24 | 2020-12-29 | 中国科学院空天信息创新研究院 | Health monitoring system and method for remote sensing satellite ground station |
| CN112308300A (en) * | 2020-10-19 | 2021-02-02 | 中国电子科技集团公司第三十八研究所 | Large-scale electronic product state prediction management system |
| CN112348209A (en) * | 2020-10-26 | 2021-02-09 | 中车工业研究院有限公司 | Train group operation and maintenance system and method, electronic device and readable storage medium |
| CN113126571A (en) * | 2019-12-31 | 2021-07-16 | 东芝三菱电机工业系统(中国)有限公司 | Electric transmission device health diagnosis system and method and central control device |
| CN115244555A (en) * | 2019-12-11 | 2022-10-25 | 品质控制有限责任公司 | Method and apparatus for assessing overall asset condition |
| CN115936294A (en) * | 2022-06-25 | 2023-04-07 | 航科易通(北京)科技有限公司 | An equipment health management analysis method and terminal |
| CN117114420A (en) * | 2023-10-17 | 2023-11-24 | 南京启泰控股集团有限公司 | Image recognition-based industrial and trade safety accident risk management and control system and method |
| CN120470717A (en) * | 2025-07-14 | 2025-08-12 | 中交天津港湾工程研究院有限公司 | Dynamic Optimization Method for Weights of Structural Health Assessment Model of Immersed Tube Tunnel |
| CN120632644A (en) * | 2025-08-12 | 2025-09-12 | 厦门扬森数控设备有限公司 | A multi-level maintenance strategy optimization system for CNC machine tools based on multi-source data |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100023301A1 (en) * | 2008-07-22 | 2010-01-28 | Honeywell International Inc., | Electromechanical actuator and effector health management system and method |
| CN102226428A (en) * | 2011-04-29 | 2011-10-26 | 哈尔滨工程大学 | Gas Turbine Health State Prediction Method |
| CN102768115A (en) * | 2012-06-27 | 2012-11-07 | 华北电力大学 | Method for dynamically monitoring health status of wind turbine gearbox in real time |
| CN103824137A (en) * | 2014-03-20 | 2014-05-28 | 北京信息科技大学 | Multi-condition fault prediction method for complex mechanical equipment |
| CN104506609A (en) * | 2014-12-22 | 2015-04-08 | 合一网络技术(北京)有限公司 | Method and device for automatically monitoring server state and self-adaptively adjusting services |
| CN105512448A (en) * | 2014-09-22 | 2016-04-20 | 国家电网公司 | An Evaluation Method of Distribution Network Health Index |
| CN105809255A (en) * | 2016-03-07 | 2016-07-27 | 大唐淮南洛河发电厂 | IoT-based heat-engine plantrotary machine health management method and system |
| CN105974886A (en) * | 2016-06-28 | 2016-09-28 | 华中科技大学 | Health monitoring method for numerical control machine tool |
| CN106094570A (en) * | 2016-07-13 | 2016-11-09 | 北京航空航天大学 | A kind of aero-engine complete machine health evaluating method under variable working condition based on operating mode's switch and this distance of paddy |
-
2017
- 2017-03-13 CN CN201710145942.2A patent/CN106952028A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100023301A1 (en) * | 2008-07-22 | 2010-01-28 | Honeywell International Inc., | Electromechanical actuator and effector health management system and method |
| CN102226428A (en) * | 2011-04-29 | 2011-10-26 | 哈尔滨工程大学 | Gas Turbine Health State Prediction Method |
| CN102768115A (en) * | 2012-06-27 | 2012-11-07 | 华北电力大学 | Method for dynamically monitoring health status of wind turbine gearbox in real time |
| CN103824137A (en) * | 2014-03-20 | 2014-05-28 | 北京信息科技大学 | Multi-condition fault prediction method for complex mechanical equipment |
| CN105512448A (en) * | 2014-09-22 | 2016-04-20 | 国家电网公司 | An Evaluation Method of Distribution Network Health Index |
| CN104506609A (en) * | 2014-12-22 | 2015-04-08 | 合一网络技术(北京)有限公司 | Method and device for automatically monitoring server state and self-adaptively adjusting services |
| CN105809255A (en) * | 2016-03-07 | 2016-07-27 | 大唐淮南洛河发电厂 | IoT-based heat-engine plantrotary machine health management method and system |
| CN105974886A (en) * | 2016-06-28 | 2016-09-28 | 华中科技大学 | Health monitoring method for numerical control machine tool |
| CN106094570A (en) * | 2016-07-13 | 2016-11-09 | 北京航空航天大学 | A kind of aero-engine complete machine health evaluating method under variable working condition based on operating mode's switch and this distance of paddy |
Cited By (33)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107464023B (en) * | 2017-08-16 | 2020-04-17 | 新疆金风科技股份有限公司 | Online learning method and equipment of life cycle prediction model |
| CN107464023A (en) * | 2017-08-16 | 2017-12-12 | 新疆金风科技股份有限公司 | The on-line study method and apparatus of life cycle forecast model |
| CN108564236A (en) * | 2017-09-27 | 2018-09-21 | 国网安徽省电力有限公司 | A kind of dual protection equipment Risk discrimination method based on big data Distributed Calculation |
| CN107767056A (en) * | 2017-10-25 | 2018-03-06 | 上海电气上重碾磨特装设备有限公司 | A kind of condition monitoring for power station coal pulverizer with it is health management system arranged |
| CN108062603A (en) * | 2017-12-29 | 2018-05-22 | 国网福建省电力有限公司 | Based on distribution power automation terminal life period of an equipment life-span prediction method and system |
| CN108280543A (en) * | 2018-01-17 | 2018-07-13 | 杭州安脉盛智能技术有限公司 | The adaptive equipment health degree appraisal procedure of operating mode based on classification Regression Model |
| CN108280543B (en) * | 2018-01-17 | 2020-11-17 | 杭州安脉盛智能技术有限公司 | Working condition self-adaptive equipment health degree evaluation method based on classification regression mode |
| CN108398934A (en) * | 2018-02-05 | 2018-08-14 | 常州高清信息技术有限公司 | The system that a kind of equipment fault for rail traffic monitors |
| CN108591104A (en) * | 2018-04-18 | 2018-09-28 | 广东寰球智能科技有限公司 | A kind of Research on Fan Fault Forecasting based on cloud platform and health management system arranged, method |
| CN108591104B (en) * | 2018-04-18 | 2019-11-05 | 广东寰球智能科技有限公司 | A kind of Research on Fan Fault Forecasting based on cloud platform and health management system arranged, method |
| CN109214529A (en) * | 2018-08-31 | 2019-01-15 | 深圳市紫衡技术有限公司 | A kind of Mechatronic Systems preventive maintenance method and system, equipment, storage medium |
| CN109242356A (en) * | 2018-10-25 | 2019-01-18 | 黎泽芝 | Construction of the highway safe production management system based on mobile Internet |
| CN109582657A (en) * | 2018-11-28 | 2019-04-05 | 国家电网有限公司 | Capacitor faults prediction technique based on machine learning and big data analysis |
| CN110474979A (en) * | 2019-08-13 | 2019-11-19 | 北京软通智城科技有限公司 | A kind of remote assisting system, method, platform and storage medium |
| CN110474979B (en) * | 2019-08-13 | 2022-06-21 | 北京软通绿城科技有限公司 | A remote assistance system, method, platform and storage medium |
| CN110737732A (en) * | 2019-10-25 | 2020-01-31 | 广西交通科学研究院有限公司 | electromechanical equipment fault early warning method |
| CN111105074A (en) * | 2019-11-22 | 2020-05-05 | 江南机电设计研究所 | Fault prediction method based on improved deep belief learning |
| CN115244555A (en) * | 2019-12-11 | 2022-10-25 | 品质控制有限责任公司 | Method and apparatus for assessing overall asset condition |
| CN113126571A (en) * | 2019-12-31 | 2021-07-16 | 东芝三菱电机工业系统(中国)有限公司 | Electric transmission device health diagnosis system and method and central control device |
| CN113126571B (en) * | 2019-12-31 | 2024-04-30 | 东芝三菱电机工业系统(中国)有限公司 | Electric transmission device health diagnosis system, method and central control device |
| CN111325397A (en) * | 2020-02-19 | 2020-06-23 | 国网山东省电力公司宁阳县供电公司 | Data analysis system based on power data backup state |
| CN112149791A (en) * | 2020-09-22 | 2020-12-29 | 国网河南省电力公司鹤壁供电公司 | Low-voltage risk assessment system based on neural network recognition and fuzzy analysis |
| CN112152698B (en) * | 2020-09-24 | 2023-02-28 | 中国科学院空天信息创新研究院 | A remote sensing satellite ground station health monitoring system and method |
| CN112152698A (en) * | 2020-09-24 | 2020-12-29 | 中国科学院空天信息创新研究院 | Health monitoring system and method for remote sensing satellite ground station |
| CN112308300A (en) * | 2020-10-19 | 2021-02-02 | 中国电子科技集团公司第三十八研究所 | Large-scale electronic product state prediction management system |
| CN112348209A (en) * | 2020-10-26 | 2021-02-09 | 中车工业研究院有限公司 | Train group operation and maintenance system and method, electronic device and readable storage medium |
| CN112348209B (en) * | 2020-10-26 | 2024-02-09 | 中车工业研究院有限公司 | Train set operation and maintenance system and method, electronic equipment and readable storage medium |
| CN115936294A (en) * | 2022-06-25 | 2023-04-07 | 航科易通(北京)科技有限公司 | An equipment health management analysis method and terminal |
| CN117114420A (en) * | 2023-10-17 | 2023-11-24 | 南京启泰控股集团有限公司 | Image recognition-based industrial and trade safety accident risk management and control system and method |
| CN117114420B (en) * | 2023-10-17 | 2024-01-05 | 南京启泰控股集团有限公司 | Image recognition-based industrial and trade safety accident risk management and control system and method |
| CN120470717A (en) * | 2025-07-14 | 2025-08-12 | 中交天津港湾工程研究院有限公司 | Dynamic Optimization Method for Weights of Structural Health Assessment Model of Immersed Tube Tunnel |
| CN120632644A (en) * | 2025-08-12 | 2025-09-12 | 厦门扬森数控设备有限公司 | A multi-level maintenance strategy optimization system for CNC machine tools based on multi-source data |
| CN120632644B (en) * | 2025-08-12 | 2025-10-17 | 厦门扬森数控设备有限公司 | A multi-level maintenance strategy optimization system for CNC machine tools based on multi-source data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106952028A (en) | Dynamoelectric equipment failure is examined and health control method and system in advance | |
| EP4632530A1 (en) | Refrigeration system operation method and apparatus, device, and storage medium | |
| CN112307950B (en) | Detail feature quantity extraction and intelligent analysis method for GIS vibration defect identification | |
| Saldivar et al. | Self-organizing tool for smart design with predictive customer needs and wants to realize Industry 4.0 | |
| CN118657404A (en) | A multi-modal power grid health assessment and analysis method | |
| CN118568471A (en) | Intelligent power distribution station operation fault prediction method and system | |
| Laayati et al. | Smart energy management: Energy consumption metering, monitoring and prediction for mining industry | |
| CN112085261A (en) | Diagnosis method of enterprise production status based on cloud integration and digital twin technology | |
| CN119167805B (en) | Power failure calculation prediction method and system based on digital twin | |
| CN116224137A (en) | UPS equipment fault early warning method and system | |
| CN106447107B (en) | Maintenance method based on aircraft structure health monitoring | |
| CN109886328B (en) | A method and system for fault prediction of electric vehicle charging facilities | |
| CN115174416B (en) | Network planning system, method and device and electronic equipment | |
| CN110543500A (en) | Power transmission and transformation equipment health assessment platform based on big data | |
| CN118278914A (en) | Method for realizing equipment fault rush repair based on GIS (geographic information System) | |
| CN107697107A (en) | A kind of train groups prognostic and health management ground intelligent processing system and method | |
| CN109103991A (en) | A kind of big data analysis method of intelligent distribution network | |
| CN112801815B (en) | Power communication network fault early warning method based on federal learning | |
| CN119727096A (en) | A distributed photovoltaic inverter acquisition and scheduling method and system | |
| CN119441771A (en) | Escalator health assessment method, device and terminal equipment based on deep learning | |
| CN110941558B (en) | Intelligent office remote operation and maintenance method and system | |
| CN117272042A (en) | Photovoltaic power station monitoring methods, devices, electronic equipment and storage media | |
| CN120598355A (en) | A method for identifying multi-temporal and spatial supply and demand risks in power systems based on scenario simulation | |
| CN118246695B (en) | Photovoltaic new energy operation and maintenance scheduling system | |
| CN119834732A (en) | Remote alarm device for monitoring abnormality of photovoltaic energy storage power station |
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 |
Application publication date: 20170714 |
|
| RJ01 | Rejection of invention patent application after publication |