CN104281143A - Fault predicting apparatus - Google Patents
Fault predicting apparatus Download PDFInfo
- Publication number
- CN104281143A CN104281143A CN201310751451.4A CN201310751451A CN104281143A CN 104281143 A CN104281143 A CN 104281143A CN 201310751451 A CN201310751451 A CN 201310751451A CN 104281143 A CN104281143 A CN 104281143A
- Authority
- CN
- China
- Prior art keywords
- state
- behavioural information
- prediction
- failure prediction
- fault
- 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
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0259—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterized by the response to fault detection
- G05B23/0283—Predictive maintenance, e.g. involving the monitoring of a system and, based on the monitoring results, taking decisions on the maintenance schedule of the monitored system; Estimating remaining useful life [RUL]
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0243—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults model based detection method, e.g. first-principles knowledge model
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0243—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults model based detection method, e.g. first-principles knowledge model
- G05B23/0245—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults model based detection method, e.g. first-principles knowledge model based on a qualitative model, e.g. rule based; if-then decisions
- G05B23/0248—Causal models, e.g. fault tree; digraphs; qualitative physics
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/34—Director, elements to supervisory
- G05B2219/34477—Fault prediction, analyzing signal trends
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Debugging And Monitoring (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The present invention relates to a fault predicting apparatus which is able to predict the fault of a working unit in a system without imposing influence to the system. According to the embodiments of the invention, the fault predicting apparatus comprises a first acquiring unit to obtain operating information of a running system and the working unit under a running system, a generating unit to generate and build a predicting model based on the obtained operating information, a second acquiring unit to obtain operating information of the predicted system, and a fault predicting unit to generate and build a predicting model based on the obtained results of the second acquiring unit to judge whether the information is consistent with the model or not so as to predict the fault of a system.
Description
Technical field
Embodiments of the present invention relate to fault prediction device.
Background technology
Industry computing machine is applicable to the system of the continuous operation that social infrastructure system etc. will be aspired for stability.Such System's composition is prevent the fault of intrasystem machine monomer from bringing impact to whole system by the method for redundant etc.
Prevent the technology being brought impact by the fault of machine monomer to whole system, by detect machine monomer fault technology and the technology that the process that the machine broken down performs is replaced by other means is formed.
At first technical literature
Patent documentation
Patent documentation 1: JP 2008-206135 publication
Summary of the invention
But, in order to detect the fault of machine monomer, need the fault using the system of this machine to carry out detecting in the state of action this machine monomer, so can not be used in the checking of machine monomer by the test procedure etc. used.
In addition, under common installment state, after machine monomer is in malfunction, even if detect this fault, time substitute machine is needed, so be difficult to prevent the impact on system.
The present invention aim to provide a kind of can under the condition of not influential system predicted application in the fault prediction device of the fault of the machine monomer of system.
According to embodiment, fault prediction device has: the first collector unit, the behavioural information of the system components under collection system state and this state, and wherein, described system state represents the running status of each several part of failure prediction objective system; Generation unit, according to the system state of collecting and behavioural information, generates action prediction model, as the model of the behavioural information corresponding to the state of system; Second collector unit, in the operation of failure prediction objective system, the behavioural information of the system components under the state of collection system and this state; Failure prediction unit, according to the collection result of the second collector unit and the action prediction model of generation, judge that whether the behavioural information in the state of operating system is different from the behavioural information under the identical systems state in action prediction model, thus carry out the failure prediction of system.
Accompanying drawing explanation
Fig. 1 is the block diagram of the configuration example of the fault prediction device representing embodiment.
Fig. 2 represents the generation of action prediction model of the failure prediction objective system that the fault prediction device of embodiment carries out or the figure of the summary of failure prediction.
Fig. 3 is the figure of the various functions for generating action prediction model that embodiment is described.
Fig. 4 is the process flow diagram of an example of the step for generating action prediction model representing embodiment.
Fig. 5 is the figure of an example of the action prediction model representing embodiment in a tabular form.
Fig. 6 is the figure of the various functions for failure prediction illustrated about embodiment.
Fig. 7 is the process flow diagram of an example of the step for failure prediction representing embodiment.
Embodiment
Hereinafter, with reference to the accompanying drawings of embodiment.
Fig. 1 is the block diagram of the configuration example of the fault prediction device representing embodiment.
As shown in Figure 1, fault prediction device 10 has the memory storage 11 of nonvolatile memory etc., communication interface 12, control device 20, input media 30 and display device 40.
Input media 30 is keyboard or mouse.Display device 40 is such as liquid crystal display.
Memory storage 11 has status information storage part 11a and action prediction model information storage part 11b.
Control device 20 has state information collection portion 21, behavioural information collection unit 22, action prediction model generation portion 23, failure prediction portion 24 and notification unit 25.
Communication interface 12 is connected with the failure prediction objective system 50 of the mode that can communicate with PC (PC) etc.
In the example depicted in figure 1, fault prediction device 10 is separated with failure prediction objective system 50, but be not limited thereto, also can be configured to: the various functions of fault prediction device 10 are such as configured to software and are applied to failure prediction objective system 50, make its action in this failure prediction objective system 50.
Fig. 2 represents the generation of action prediction model of the failure prediction objective system that the fault prediction device of embodiment carries out or the figure of the summary of failure prediction.
Fault prediction device 10 according to the behavioural information of the status information of each machine of failure prediction objective system 50 or machine monomer, can generate the action prediction model of the failure prediction model of each machine as failure prediction objective system 50.In this action prediction model, the normal behavioural information that each machine demonstrating failure prediction objective system 50 changes for various state or state.
Status information represents the various running status of failure prediction objective system 50 and the information of which kind of state change occurs.This information uses input media 30 to be transfused to by operator.
Behavioural information be represent operator failure prediction objective system 50 is operated after the information of change of each machine monomer.
Such as, temperature sensor in failure prediction objective system 50 main body, the testing result of voltage sensor, the statistical information of network packet and PCle(PCl Express(registered trademark)) and so on the packet statistics information etc. of the universal serial bus based on packet, be equivalent to the behavioural information of each several part.
The generation method needs of action prediction model are the methods of the ambiguity that can allow to a certain degree.The adaptive learning method of Bayesian filter, neural network etc. is equivalent to the method.
After action prediction model generation, described status information as teacher signal, will be have input the result feedback of described behavioural information to action prediction model, thus carries out the intensified learning of action prediction model by fault prediction device 10.
The information of all expression states of fault prediction device 10 pairs of failure prediction objective systems 50 or state change carries out the intensified learning of action prediction model, when the correct Prediction of the fault of failure prediction objective system 50 can be carried out, the generation of tenth skill forecast model.
When the failure prediction of failure prediction objective system 50, fault prediction device 10 uses the action prediction model of above-mentioned generation to carry out failure prediction.
Specifically, the status information of fault prediction device 10 input fault forecasting object system 50 when failure prediction or behavioural information.
Status information informs failure prediction mechanism by behavioural information collecting mechanism.The behavioural information of the system components after this notice is collected by behavioural information collecting mechanism and informs failure prediction mechanism.
Failure prediction mechanism contrasts combination and the action prediction model of these status informations of collecting and behavioural information.By this contrast, when the corresponding behavioural information of status information of collecting is equivalent to the corresponding behavioural information of the identical status information in action prediction model, failure prediction mechanism think system state represented by this status information or system state change in there is failure symptom.
Now, failure prediction notice is sent to processing mechanism or the operator of failure prediction objective system 50 by failure prediction mechanism.
Like this, if the sign of the fault of machine monomer can be detected, by advance the process performed in this machine being converted to replacement device, the impact that the fault of this machine monomer is brought system can be prevented in advance.
Secondly, respectively the concrete condition of action prediction model generation and failure prediction is described.
First the concrete condition of the various functions for action prediction model generation is described.
Fig. 3 is the figure of the various functions of the action prediction model generation illustrated for embodiment.The example of the fault prediction device 10 of the failure prediction of installing for carrying out the PC as failure prediction objective system 50 is represented at this.At this, be assumed to be, the function of each several part in the control device 20 shown in Fig. 1 is collected driver etc. as modelling mechanism, behavioural information collecting mechanism and behavioural information and is mounted in failure prediction objective system 50.
Fig. 4 is the process flow diagram of an example of the step of the action prediction model generation represented for embodiment.
Operator is by the operation to input media 30, and input represents the system state of failure prediction objective system 50 and the information (S1) ((1) in Fig. 3) of which kind of state change occurs.Modelling mechanism (at this, corresponding to status information obtaining section 21) obtains this input information, and is stored into the status information storage part 11a(S2 of memory storage 11).
The system application of operator to failure prediction objective system 50 operates, to be created on the system state or state change (S3) ((2) in Fig. 3) that input in S1.
System application makes system carry out action (S3) ((3) in Fig. 3) according to the operation in S2.
Secondly, the behavioural information of behavioural information collecting mechanism (corresponding to behavioural information collection unit 22) collection system each several part, and be sent to behavioural information collection driver (S4) ((4) in Fig. 3).
Such as, behavioural information collecting mechanism collects cpu bus state, memory bus state, various internal sensor information (such as temperature, voltage etc.), PCle bus data bag statistical information, the classification (memory requests, I/O request, configuring request, complete request, message (message)) of packet, the number of packet and number of retries etc.
As above collecting bus data bag statistical information is difficult because of directly preserving packet.
The behavioural information (S5) ((5) in Fig. 3) of collecting driver from behavioural information is collected by modelling mechanism (corresponding to action prediction model generation portion 23 at this).
Modelling mechanism is according to the behavioural information of collecting in the status information inputted in S1 and S5, generate action prediction model (S6), the each state of this action prediction model representation for status information and the correct behavior of state change, then, by the action prediction model information storage part 11b(S7 of the action prediction model storage of this generation to memory storage 11).
Fig. 5 is the figure of an example of the action prediction model representing embodiment in a tabular form.
Secondly, the concrete condition of the various functions for failure prediction after about action prediction model generation is described.Fig. 6 is the figure of the various functions illustrated about the action prediction model generation for embodiment.The installation example of the fault prediction device 10 of the failure prediction for carrying out the PC as failure prediction objective system 50 is represented at this.In this hypothesis, the function of each several part in the control device 20 shown in Fig. 1 is collected driver etc. as failure prediction mechanism, behavioural information collecting mechanism and behavioural information and is mounted in failure prediction objective system 50.
Fig. 7 is the process flow diagram of an example of the step of the failure prediction represented for embodiment.Operator, by the operation to input media 30, carries out operating the system application action (S11) ((7) in Fig. 6) making failure prediction objective system 50.
The state information notification of the expression system state that the operation by S11 occurs by system application or state change is to failure prediction mechanism (corresponding to failure prediction portion 24 at this) (S12) ((8) in Fig. 6).
System application makes system acting (S13) ((9) in Fig. 6) according to the operation in S11.
The behavioural information of behavioural information collecting mechanism (corresponding to behavioural information collection unit 22) collection system each several part, and be sent to behavioural information collection driver (S14) ((10) in Fig. 6).The kind of collected information is identical with during action prediction model generation.
The behavioural information (S15) ((11) in Fig. 6) of collecting driver from behavioural information is collected by failure prediction mechanism (corresponding to failure prediction portion 24 at this).
Failure prediction mechanism (corresponding to failure prediction portion 24 at this) reads the action prediction model be stored in action prediction model information storage part 11b.This failure prediction mechanism, according to this action prediction model, status information notified in S12 and the behavioural information of collecting in S15, carries out the failure prediction (S17) ((12) in Fig. 6) of failure prediction objective system 50.
When finding the sign of fault in failure prediction objective system 50, that is, when for status information notified in S12, status information notified in S15 is inconsistent with the corresponding behavioural information of the equal state information represented in action prediction model, failure prediction mechanism (corresponding to notification unit 25 at this) represents the failure prediction result (S18) ((13) in Fig. 6) of the failure symptom involved by this status information to system application or operator notification.
As above, the fault prediction device of embodiment by the behavioural information modelling of each several part in the state of failure prediction objective system action, and by the behavioural information in the action of comparing this model and system, can carry out failure prediction.
Therefore, be in the state in system cloud gray model at failure prediction objective system under, the impact on this system can be prevented, and can the fault of machine monomer in prognoses system.
In addition, the information of the various internal sensor of described collection or the function of collection cpu bus, memory bus and packet statistics information are the functions being generally equipped on computing machine, so the hardware for collecting the behavioural information being used in action prediction model generation need not be rolled up, so can with low cost to the existing system additional fault forecast function possessing failure prediction objective system.
Thus, form the system requiring continuous print to run and become easy, and system stability can be made to improve.
Describe several embodiments of invention, these embodiments exemplarily propose, and the protection domain of non-limiting invention.These new embodiments can be implemented with other various ways, in the scope not departing from invention aim, can carry out various omission, replacement, change.These embodiments or its distortion, in the protection domain being contained in invention or aim, be also contained in the invention and equivalent protection domain recorded in claims.
Claims (3)
1. a fault prediction device, is characterized in that, possesses:
First collector unit, the behavioural information of the system components under collection system state and this state, wherein, described system state represents the running status of each several part of failure prediction objective system;
Generation unit, according to the described system state of collecting and behavioural information, generates action prediction model, as the model of the behavioural information corresponding to the state of system;
Second collector unit, in the operation of failure prediction objective system, the behavioural information of the system components under the state of collection system and this state;
Failure prediction unit, according to the collection result of described second collector unit and the action prediction model of described generation, judge that whether the behavioural information in the state of described operating system is different from the behavioural information under the identical systems state in described action prediction model, thus carry out the failure prediction of described system.
2. fault prediction device according to claim 1, is characterized in that,
Described first collector unit collect each several part of failure prediction objective system from the first state to the behavioural information of the system components the change of the state of the second state and this state;
Described generation unit, according to the described state change of collecting and behavioural information, generates action prediction model, changes the model of corresponding behavioural information as to the state of system;
The behavioural information of the system components under the state change of described second collector unit collection system in the operation of failure prediction objective system and this state change;
The collection result of described failure prediction unit according to described second collector unit and the action prediction model of described generation, behavioural information under whether the behavioural information judging in the state change of described operating system changes from the equal state in described action prediction model is different, thus carries out the failure prediction of described system.
3. fault prediction device according to claim 1 and 2, is characterized in that,
Described behavioural information comprises at least one in the detected state of the cpu bus state of described system, memory bus state and various sensor.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2013-146804 | 2013-07-12 | ||
JP2013146804A JP2015018505A (en) | 2013-07-12 | 2013-07-12 | Failure prediction apparatus |
Publications (1)
Publication Number | Publication Date |
---|---|
CN104281143A true CN104281143A (en) | 2015-01-14 |
Family
ID=52256127
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310751451.4A Pending CN104281143A (en) | 2013-07-12 | 2013-12-31 | Fault predicting apparatus |
Country Status (3)
Country | Link |
---|---|
JP (1) | JP2015018505A (en) |
KR (1) | KR20150007913A (en) |
CN (1) | CN104281143A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107024917A (en) * | 2016-01-29 | 2017-08-08 | 发那科株式会社 | It was found that the unit control apparatus the reason for exception of manufacture machinery |
CN107636617A (en) * | 2016-04-29 | 2018-01-26 | 慧与发展有限责任合伙企业 | Storage device failure strategy |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11436911B2 (en) | 2015-09-30 | 2022-09-06 | Johnson Controls Tyco IP Holdings LLP | Sensor based system and method for premises safety and operational profiling based on drift analysis |
US11151654B2 (en) * | 2015-09-30 | 2021-10-19 | Johnson Controls Tyco IP Holdings LLP | System and method for determining risk profile, adjusting insurance premiums and automatically collecting premiums based on sensor data |
CN110795260B (en) * | 2019-09-10 | 2023-08-08 | 武汉攀升鼎承科技有限公司 | Smart customer care system |
JP7334554B2 (en) * | 2019-09-18 | 2023-08-29 | 富士電機株式会社 | Equipment management system and equipment management method |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1393177A1 (en) * | 2001-04-10 | 2004-03-03 | Smartsignal Corporation | Diagnostic systems and methods for predictive condition monitoring |
CN102829967A (en) * | 2012-08-27 | 2012-12-19 | 中国舰船研究设计中心 | Time-domain fault identifying method based on coefficient variation of regression model |
CN102880115A (en) * | 2012-09-29 | 2013-01-16 | 佛山喜讯电子科技有限公司 | Remote collaborative diagnosis system of numerical-control machine tool on basis of internet of things |
CN102893000A (en) * | 2010-04-08 | 2013-01-23 | 德尔福技术控股有限公司 | Diagnosis devise and method using an in- cylinder pressure sensor in internal combustion engine |
CN103149476A (en) * | 2013-02-06 | 2013-06-12 | 浙江大学 | Electric-vibration model-based power transformer failure diagnosis method |
-
2013
- 2013-07-12 JP JP2013146804A patent/JP2015018505A/en active Pending
- 2013-11-25 KR KR1020130143573A patent/KR20150007913A/en not_active Application Discontinuation
- 2013-12-31 CN CN201310751451.4A patent/CN104281143A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1393177A1 (en) * | 2001-04-10 | 2004-03-03 | Smartsignal Corporation | Diagnostic systems and methods for predictive condition monitoring |
CN102893000A (en) * | 2010-04-08 | 2013-01-23 | 德尔福技术控股有限公司 | Diagnosis devise and method using an in- cylinder pressure sensor in internal combustion engine |
CN102829967A (en) * | 2012-08-27 | 2012-12-19 | 中国舰船研究设计中心 | Time-domain fault identifying method based on coefficient variation of regression model |
CN102880115A (en) * | 2012-09-29 | 2013-01-16 | 佛山喜讯电子科技有限公司 | Remote collaborative diagnosis system of numerical-control machine tool on basis of internet of things |
CN103149476A (en) * | 2013-02-06 | 2013-06-12 | 浙江大学 | Electric-vibration model-based power transformer failure diagnosis method |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107024917A (en) * | 2016-01-29 | 2017-08-08 | 发那科株式会社 | It was found that the unit control apparatus the reason for exception of manufacture machinery |
CN107024917B (en) * | 2016-01-29 | 2018-08-03 | 发那科株式会社 | It was found that the unit control apparatus of the abnormal reason of manufacture machinery |
US10203666B2 (en) | 2016-01-29 | 2019-02-12 | Fanuc Corporation | Cell controller for finding cause of abnormality in manufacturing machine |
CN107636617A (en) * | 2016-04-29 | 2018-01-26 | 慧与发展有限责任合伙企业 | Storage device failure strategy |
CN107636617B (en) * | 2016-04-29 | 2021-06-22 | 慧与发展有限责任合伙企业 | Storage system, method for learning failure policy by storage system, and medium |
US11468359B2 (en) | 2016-04-29 | 2022-10-11 | Hewlett Packard Enterprise Development Lp | Storage device failure policies |
Also Published As
Publication number | Publication date |
---|---|
JP2015018505A (en) | 2015-01-29 |
KR20150007913A (en) | 2015-01-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104281143A (en) | Fault predicting apparatus | |
JP7017861B2 (en) | Anomaly detection system and anomaly detection method | |
US10147048B2 (en) | Storage device lifetime monitoring system and storage device lifetime monitoring method thereof | |
CN112436968B (en) | Network traffic monitoring method, device, equipment and storage medium | |
JP6875179B2 (en) | System analyzer and system analysis method | |
US9915925B2 (en) | Initiated test health management system and method | |
CN110806743A (en) | Equipment fault detection and early warning system and method based on artificial intelligence | |
JP6003689B2 (en) | Diagnostic equipment | |
EP2277778A2 (en) | Vehicle health management systems and methods with predicted diagnostic indicators | |
KR20180108446A (en) | System and method for management of ict infra | |
CN103617110A (en) | Server device condition maintenance system | |
CN110888412B (en) | Semiconductor device and analysis system | |
KR102343752B1 (en) | Computer-implemented method and system for automatically monitoring and determining the status of entire process segments in a process unit | |
US20160379144A1 (en) | Information processing system and failure prediction model adoption determining method | |
JP2017097712A (en) | Instrument diagnosis device and system as well as method | |
CN104777762A (en) | Vehicle-mounted system monitoring method and terminal thereof | |
CN101308387A (en) | Apparatus and method for monitoring device condition and computer readable medium | |
US20150046757A1 (en) | Performance Metrics of a Computer System | |
JP7031743B2 (en) | Anomaly detection device | |
CN111459692A (en) | Method, apparatus and computer program product for predicting drive failure | |
CN113168172A (en) | Model generation device, model generation method, and program | |
JP2021092971A (en) | Control method, control unit, machine plant, control program, and recording medium | |
KR101995026B1 (en) | System and Method for State Diagnosis and Cause Analysis | |
KR20160072812A (en) | Case management linkage of updates, evidence, and triggers | |
EP4127849A1 (en) | Hvac health monitoring system combining rules and anomaly detection |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150114 |