CN105260279A - Method and device of dynamically diagnosing hard disk failure based on S.M.A.R.T (Self-Monitoring Analysis and Reporting Technology) data - Google Patents
Method and device of dynamically diagnosing hard disk failure based on S.M.A.R.T (Self-Monitoring Analysis and Reporting Technology) data Download PDFInfo
- Publication number
- CN105260279A CN105260279A CN201510738474.0A CN201510738474A CN105260279A CN 105260279 A CN105260279 A CN 105260279A CN 201510738474 A CN201510738474 A CN 201510738474A CN 105260279 A CN105260279 A CN 105260279A
- Authority
- CN
- China
- Prior art keywords
- hard disk
- data
- model
- parameter
- early warning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Debugging And Monitoring (AREA)
Abstract
The invention discloses a method and a device of dynamically diagnosing hard disk failure based on S.M.A.R.T (Self-Monitoring Analysis and Reporting Technology) data and relates to the field of data storage security diagnosis. The method comprises the following steps: 101) establishing a cloud storage server side to continuously collect three types of data; 102) establishing a hard disk failure early-warning dynamic model; 103) establishing S.M.A.R.T parameter normal fluctuation curves and ranges; 104) obtaining a health diagnosis scoring dynamic model through big data analysis. The method and the device of dynamically diagnosing hard disk failure based on S.M.A.R.T data have the following beneficial effects: 1) the cloud storage server side is established to continuously collect data related to health of hard disks; 2) the collected data are organized to establish the hard disk failure early-warning dynamic model, the S.M.A.R.T parameter normal fluctuation curves and ranges and the health diagnosis scoring dynamic model; 3) the correctness of the model is continuously improved through machine learning in hard disk failure diagnosis.
Description
Technical field
The invention belongs to data storage security diagnostic field, relate to a kind of method and apparatus based on SMART Data Dynamic diagnosis hard disk failure.
Background technology
S.M.A.R.T.: full name is " Self-MonitoringAnalysisandReportingTechnology ", i.e. " self-monitoring, analysis and reporting techniques ", it is the Technology On Data Encryption that present hard disk generally adopts, when hard disk operational, monitoring system carries out operation conditions monitoring to the state of motor, circuit, disk, magnetic head, will give a warning in time having abnormal generation.
Cloud stores (CloudStorage): be in cloud computing (CloudComputing) conceptive extension and the new concept of development out one, it is a kind of emerging Network storage technology, refer to by functions such as cluster application, network technology or distributed file systems, memory device dissimilar in a large number in network is gathered collaborative work by application software, a system of data storage and Operational Visit function is externally provided jointly.
Normalization: be also data normalization, is a kind of mode simplifying calculating, is about to the expression formula of dimension, and through conversion, turning to nondimensional expression formula, become scalar, is the element task carrying out data mining.
Machine learning (MachineLearning): " machine " mentioned here, what refer to is exactly computing machine, robot calculator, neutron computing machine, photonic computer or neuro-computer etc.Machine learning is the science of an artificial intelligence, is by data or experience in the past, uses " contrast-adjustment-contrast ", the performance of Optimal improvements programmed algorithm.Machine learning is applied in the fields such as data mining, natural language processing, search engine, medical diagnosis, voice and handwriting recognition widely.
For realizing comparatively safe data protection, eighties of last century the nineties, S.M.A.R.T. technology is arisen at the historic moment.After becoming industry standard in June, 1996, even to this day, S.M.A.R.T. technology still provides support carrying out hard disk failure prediction for us, and the tool device that numerous hard disk failure detects analysis and early warning all depends on this.But there are the following problems for the tool device of these detection analysis and early warnings:
1, only read out S.M.A.R.T. information from hard-disk system reserved area simply, represent with tabular form, numerous unprofessional user fails to understand;
2, only there is the every current value of S.M.A.R.T. information, item of information numerical value cannot be compiled and become history curve, thus more accurately diagnose;
3, cannot solve on SSD solid state hard disc, the different master controls of different HD vendor, the S.M.A.R.T. project of different model product, attribute, description are not quite similar this problem;
4, dangerous for predictable hard disk, pre-warning time is delayed, or without active forewarning;
5, the early warning of mistake cannot be revised.
Summary of the invention
The present invention is directed to the deficiencies in the prior art, provide a kind of method and apparatus based on SMART Data Dynamic diagnosis hard disk failure, effectively can solve prior art and represent with tabular form and cause unprofessional user to fail to understand; Only there is the every current value of S.M.A.R.T. information, item of information numerical value cannot be compiled and become history curve, thus more accurately diagnose; Cannot solve on SSD solid state hard disc, the different master controls of different HD vendor, the S.M.A.R.T. project of different model product, attribute, description such as to be not quite similar at the problem.
For overcoming the above problems, the technical solution used in the present invention is as follows: a kind of method based on SMART Data Dynamic diagnosis hard disk failure, comprises the following steps:
101 set up cloud stores service end, persistent collection three class data: is hard disk type data, comprises hard disk brand and model; Two is S.M.A.R.T. supplemental characteristic and parameter collection time data; Three is Hard disk error daily record datas of operating system record;
The hard disk brand of the S.M.A.R.T. supplemental characteristic collected and correspondence thereof, model data are normalized by 102, generate normalization S.M.A.R.T. data acquisition; Based on normalization S.M.A.R.T. data acquisition and the Hard disk error daily record data collected, set up hard disk failure early warning dynamic model;
The S.M.A.R.T. data collected are group with parameter by 103, in conjunction with corresponding hard disk brand, model data, form different brands, different model hard disk S.M.A.R.T. dynamic state of parameters change curve, statistics show that hard disk health runs S.M.A.R.T. parameter normal fluctuation range, sets up S.M.A.R.T. parameter normal fluctuation curve and scope;
104 by large data analysis, draws the S.M.A.R.T. parameters weighting of different brands different model hard disk; According to the setting of HD vendor to S.M.A.R.T. early-warning parameters, combined training learning data, draws the early-warning parameters that different brands different model hard disk is new and the weighing factor factor to hard disk health; Set a full marks value, according to new S.M.A.R.T. parameters weighting and the weighing factor factor to hard disk health, setting standard of deducting point, draws Gernral Check-up scoring dynamic model; Based on hard disk failure early warning dynamic model, S.M.A.R.T. parameter normal fluctuation curve and scope, Gernral Check-up scoring dynamic model, diagnostic score is carried out to hard disk health status, provides specific aim suggestion; If hard disk exists risk, automatically carry out early warning; If early warning mistake, start the machine study.
As preferably, 102 comprise the following steps:
201 data normalizations, adopt Z-score standardized method, concrete formula is:
wherein, x is the sample data of 101 collections, and x* is the data after normalization, and μ is the average of all sample datas, and σ is the standard deviation of all sample datas;
Normalized data are classified by disk, magnetic head, head arm, motor, control circuit board, data-interface, master control and flash memory particle by 202;
203 by normalized grouped data, by HD vendor, brand, model in groups;
204 according to the threshold value of every S.M.A.R.T. parameter of each factory settings, arranges the early warning value of Classified into groups data after normalization; Build S.M.A.R.T. parameter comparison model; Combine every contrast model, early warning trigger formation hard disk failure early warning dynamic model;
205 read hard disk S.M.A.R.T. supplemental characteristic to be checked, and import comparison model, when a certain data exceed early warning value, early warning flip-flop toggle, pushes early warning information automatically, prompting user's hard disk failure place;
206 read and collect hard disk S.M.A.R.T. supplemental characteristic to be checked, after normalized, store end stored in cloud; According to hard disk S.M.A.R.T. supplemental characteristic to be checked and wrong early warning item, after the normalization that correction is corresponding, the early warning value of Classified into groups data, generates new hard disk failure early warning dynamic model; Amendment record will be correlated with at cloud storage server.
As preferably, 103 comprise the following steps:
301 call the S.M.A.R.T. parameter and parameter collection time that cloud stores service end collects, and with individual event S.M.A.R.T. supplemental characteristic for the longitudinal axis, the time is transverse axis; Generate individual event S.M.A.R.T. parametric plot; So, whole individual event S.M.A.R.T. parametric plot is generated;
302 according to individual event S.M.A.R.T. parametric plot, draws individual event S.M.A.R.T. parameter normal fluctuation range;
303 read hard disk S.M.A.R.T. supplemental characteristic to be checked, and import comparison model, when a certain data exceed normal fluctuation range suddenly, early warning flip-flop toggle, pushes early warning information automatically, prompting user's hard disk failure place;
304 read and collect hard disk early warning mistake S.M.A.R.T. supplemental characteristic to be checked, revise normal fluctuation range: reduce minimum Min or improve maximum Max early warning value, generate new individual event S.M.A.R.T. parameter normal fluctuation range; Amendment record will be correlated with at cloud storage server.
As preferably, 104 comprise the following steps:
401 according to the needs of S.M.A.R.T. parameter and hard disk Gernral Check-up, and the detecting of setting one-level hardware fault, secondary use cumulative statistics and using state monitoring two-stage weighting levels altogether, as the decision factor of Gernral Check-up;
402 based on the original setting of HD vendor, hard disk failure early warning dynamic model correction data, S.M.A.R.T. parameter normal fluctuation curve and scope correction data, in two-stage weight described in 401 and weight the weight factor setting of relevant parameters and regulation rule as follows:
(1) hardware fault detecting weight factor: 80%; Use cumulative statistics and using state monitoring: 10%;
(2), after using cumulative statistics value to exceed the highest cumulative statistics value 60% of individual event, weight factor is promoted to 20%; After exceeding 80% of the highest cumulative statistics value of individual event, weight factor is promoted to 40%; After exceeding 90% of the highest cumulative statistics value of individual event, weighting levels adjusts into highest ranking;
(3) continuous one week of the value of using state monitoring is more than S.M.A.R.T. parameter normal fluctuation curve and scope, and weight factor is promoted to 20%; Within continuous two weeks, exceed, weight factor is promoted to 40%; Continuous January exceedes, and weighting levels adjusts into highest ranking;
403 determine code of points;
404 based on the weight factor of 402 and the code of points of 403, in conjunction with each HD vendor and master control manufacturer S.M.A.R.T. setting parameter, sets up hard disk Gernral Check-up scoring algorithm model;
405 diagnosis;
406 according to feedback data, revises weight factor and the code of points of fine setting S.M.A.R.T. parameter, generates new Gernral Check-up scoring dynamic model; Amendment record will be correlated with at cloud storage server.
As preferably: hard disk type information also comprises sequence number, firmware version, interface type, disk running speed, disk size and buffer memory size data.
For overcoming the above problems, the present invention additionally uses following technical scheme: a kind of device based on SMART Data Dynamic diagnosis hard disk failure, comprises cloud stores service end unit, hard disk failure early warning dynamic model generation unit, S.M.A.R.T. parameter normal fluctuation curve and scope generation unit and Gernral Check-up scoring dynamic model generation unit;
Cloud stores service end, for persistent collection three class data: one is hard disk type data, comprises hard disk brand and model; Two is S.M.A.R.T. supplemental characteristic and parameter collection time data; Three is Hard disk error daily record datas of operating system record;
Hard disk failure early warning dynamic model generation unit, for the hard disk brand of the S.M.A.R.T. collected supplemental characteristic and correspondence thereof, model data being normalized, generates normalization S.M.A.R.T. data acquisition; Based on normalization S.M.A.R.T. data acquisition and the Hard disk error daily record data collected, set up hard disk failure early warning dynamic model;
S.M.A.R.T. parameter normal fluctuation curve and scope generation unit, be group for the S.M.A.R.T. data that will collect with parameter, in conjunction with corresponding hard disk brand, model data, form different brands, different model hard disk S.M.A.R.T. dynamic state of parameters change curve, statistics show that hard disk health runs S.M.A.R.T. parameter normal fluctuation range, sets up S.M.A.R.T. parameter normal fluctuation curve and scope;
Gernral Check-up scoring dynamic model generation unit, for by large data analysis, draws the S.M.A.R.T. parameters weighting of different brands different model hard disk; According to the setting of HD vendor to S.M.A.R.T. early-warning parameters, combined training learning data, draws the early-warning parameters that different brands different model hard disk is new and the weighing factor factor to hard disk health; Set a full marks value, according to new S.M.A.R.T. parameters weighting and the weighing factor factor to hard disk health, setting standard of deducting point, draws Gernral Check-up scoring dynamic model.
As preferably: hard disk type information also comprises sequence number, firmware version, interface type, disk running speed, disk size and buffer memory size data.
Beneficial effect of the present invention is as follows:
1. set up cloud stores service end, the healthy related data of persistent collection hard disk;
2. the data preparation of collecting is set up: hard disk failure early warning dynamic model, S.M.A.R.T. parameter ordinary wave;
3. moving curve and scope, Gernral Check-up scoring dynamic model, in hard disk failure diagnosis, constantly by machine learning, improve the correctness of model.
Accompanying drawing explanation
Fig. 1 is based on S.M.A.R.T. Data Dynamic diagnosis hard disk failure main flow;
Fig. 2 is hard disk failure early warning dynamic model main flow;
Fig. 3 is S.M.A.R.T. parameter normal fluctuation curve and scope main flow;
Fig. 4 is Gernral Check-up scoring dynamic model main flow.
Embodiment
For making object of the present invention, technical scheme and advantage clearly understand, to develop simultaneously embodiment referring to accompanying drawing, the present invention is described in further details.
As shown in Figure 1, a kind of method based on SMART Data Dynamic diagnosis hard disk failure,
101 set up cloud stores service end, persistent collection three class data: one is hard disk brand, model, sequence number, firmware version, interface type, disk running speed, disk size, cache size data; Two is S.M.A.R.T. supplemental characteristic and parameter collection time data; Three is Hard disk error daily record datas of operating system record;
S.M.A.R.T. supplemental characteristic collects content including but not limited to 01 read error rate; 02 throughput performance; 03 cranking time; 04 startup-stopping time; 05 redistributes sector count; 06 fetch channel surplus; 07 seek error rate; 08 seek time performance; 09 conduction time; 0A runs up number of retries; 0B recalibrates number of retries; 0C starts-closes cycle index; 0D soft read error rate probe; The end-to-end mistake of B8; Cannot correcting mistakes of BB report; BC command timeout; The improper height write of BD magnetic head; BE gas flow temperature; BF acceleration induction error rate; C0 power-off magnetic head is retracted and is counted; C1 magnetic head loading system/unloading cycle count; C2 temperature; C3 hardware ECC is mis repair counting; C4 reallocation sector physical position event counting; Sector number in the current wait of C5; The sector sum that C6 cannot revise; C7UltraDMACRC error count; C8 write error rate; The soft read error rate of C9; CA data address mark mistake; CBECC error rate; The soft ECC of CC corrects; The harsh rate of CD heat; CE magnetic head flight height; CF runs up maximum current; D0 runs up, and buzzing/run up ladder; D1 off-line tracking performance; Vibration during D3 write; Vibrations during D4 write; The displacement of DC disc; DD acceleration induction error rate; DE load hourage; DF load/unload retry count; E0 loads friction; E1 load/unload cycle count; The time that E2 loads; E3 moment of torsion amplifies counting; E4 power-off magnetic head is retracted and is counted; E6 large reluctance magnetic head amplitude; E7 temperature; F0 flying magnetic head hourage; FA read error retry rate; FE freely falling body is protected;
102 set up hard disk failure early warning dynamic model.The hard disk brand of the S.M.A.R.T. supplemental characteristic collected and correspondence thereof, model data are normalized, generate normalization S.M.A.R.T. data acquisition; Based on normalization S.M.A.R.T. data acquisition and the Hard disk error daily record data collected, set up hard disk failure early warning dynamic model; (hard disk failure early warning dynamic model detailed process is shown in Fig. 2)
103 set up S.M.A.R.T. parameter normal fluctuation curve and scope.Be group by the S.M.A.R.T. data collected with parameter, in conjunction with corresponding hard disk brand, model data, form different brands, different model hard disk S.M.A.R.T. dynamic state of parameters change curve, statistics show that hard disk health runs S.M.A.R.T. parameter normal fluctuation range; (S.M.A.R.T. parameter normal fluctuation curve and scope detailed process are shown in Fig. 3)
104 set up Gernral Check-up scoring dynamic model.By large data analysis, draw the S.M.A.R.T. parameters weighting of different brands different model hard disk; According to the setting of HD vendor to S.M.A.R.T. early-warning parameters, combined training learning data, draws the early-warning parameters that different brands different model hard disk is new and the weighing factor factor to hard disk health; By full marks 100 points, according to new S.M.A.R.T. parameters weighting and the weighing factor factor to hard disk health, setting standard of deducting point, draws Gernral Check-up scoring dynamic model; (Gernral Check-up scoring dynamic model detailed process is shown in Fig. 4)
105 start Gernral Check-up;
106 determine hard disk type: be mechanical hard disk, or solid state hard disc;
107 diagnosis.Based on hard disk failure early warning dynamic model, S.M.A.R.T. parameter normal fluctuation curve and scope, Gernral Check-up scoring dynamic model, diagnostic score is carried out to hard disk health status, provides specific aim suggestion; If hard disk exists risk, automatically carry out early warning; If early warning mistake, the study that starts the machine (relevant training study detailed process is shown in Fig. 2, Fig. 3, Fig. 4);
201 data normalizations.Conventional method for normalizing has two kinds: min-max standardization (Min-MaxNormalization) and Z-score standardized method; Because of min-max method existing defects: fashionable when there being new data to add, the change of max and min may be caused, need to redefine.Therefore, this programme adopts Z-score standardized method.Concrete formula is:
wherein μ is the average of all sample datas, and σ is the standard deviation of all sample datas;
Normalized data are classified by hardware such as disk, magnetic head, head arm, motor, control circuit board (PCB), data-interface, master control, flash memory particles by 202;
203 by normalized grouped data, by HD vendor, brand, model in groups;
204 according to the threshold value of every S.M.A.R.T. parameter of each factory settings, arranges the early warning value of Classified into groups data after normalization; Build S.M.A.R.T. parameter comparison model; Combine every contrast model, early warning trigger formation hard disk failure early warning dynamic model;
205 diagnosis.Read hard disk S.M.A.R.T. supplemental characteristic to be checked, import comparison model, when a certain data exceed early warning value, early warning flip-flop toggle, pushes early warning information automatically, prompting user's hard disk failure place;
206 early warning mistakes, machine learning.Read and collect hard disk S.M.A.R.T. supplemental characteristic to be checked, after normalized, storing end stored in cloud.According to hard disk S.M.A.R.T. supplemental characteristic to be checked and wrong early warning item, after the normalization that correction is corresponding, the early warning value of Classified into groups data, generates new hard disk failure early warning dynamic model; Amendment record will be correlated with at cloud storage server.
301 formation curve figure.Call S.M.A.R.T. parameter and parameter collection time that cloud stores service end collects, with individual event S.M.A.R.T. supplemental characteristic for the longitudinal axis, the time is transverse axis; Generate individual event S.M.A.R.T. parametric plot; So, whole individual event S.M.A.R.T. parametric plot is generated;
302 according to individual event S.M.A.R.T. parametric plot, draws individual event S.M.A.R.T. parameter normal fluctuation range (Min-Max; Min is curve map the lowest point, and Max is curve map crest);
303 diagnosis.Read hard disk S.M.A.R.T. supplemental characteristic to be checked, import comparison model, when a certain data exceed suddenly normal fluctuation range (Min-Max), early warning flip-flop toggle, pushes early warning information automatically, prompting user's hard disk failure place;
304 early warning mistakes, machine learning.Read and collect hard disk early warning mistake S.M.A.R.T. supplemental characteristic to be checked, revising normal fluctuation range: reduce Min or improve Max early warning value, generating new individual event S.M.A.R.T. parameter normal fluctuation range (Min-Max); Amendment record will be correlated with at cloud storage server.
401 setup parameter weighting levels.According to the needs of S.M.A.R.T. parameter and hard disk Gernral Check-up, setting hardware fault detecting (one-level), use cumulative statistics and using state monitoring (secondary) two-stage weighting levels altogether, as the decision factor of Gernral Check-up;
402 determine health effect weight factor.Based on the original setting of HD vendor, hard disk failure early warning dynamic model correction data, S.M.A.R.T. parameter normal fluctuation curve and scope correction data, in two-stage weight described in 401 and weight the weight factor setting of relevant parameters and regulation rule as follows:
(1) hardware fault detecting weight factor: 80%; Use cumulative statistics and using state monitoring: 10%;
(2), after using cumulative statistics value to exceed the highest cumulative statistics value 60% of individual event, weight factor is promoted to 20%; After exceeding 80% of the highest cumulative statistics value of individual event, weight factor is promoted to 40%; After exceeding 90% of the highest cumulative statistics value of individual event, weighting levels adjusts into highest ranking;
(3) continuous one week of the value of using state monitoring is more than S.M.A.R.T. parameter normal fluctuation curve and scope, and weight factor is promoted to 20%; Within continuous two weeks, exceed, weight factor is promoted to 40%; Continuous January exceedes, and weighting levels adjusts into highest ranking;
403 determine code of points.Good health state full marks 100, reduce according to health effect weight factor is accumulative item by item, are minimumly divided into 0 point, that is: alarm condition.Deduction of points rule is as follows:
(1) one-level weight: 25 points.
S.M.A.R.T. there is numerical value in parameter, detains 25 points and be multiplied by weight 80%, namely detains 20 points;
S.M.A.R.T. parameter exceedes threshold value, detains 25 points; If S.M.A.R.T. parameter has amendment record, replace genuine threshold value with modified value, then row judges;
(2) secondary weight: 10 points.
S.M.A.R.T. there is numerical value in parameter, detains 10 points and be multiplied by weight 10%, namely detains 1 point;
S.M.A.R.T. parameter exceedes threshold value, detains 10 points; If S.M.A.R.T. parameter has amendment record, replace genuine threshold value with modified value, then row judges;
When S.M.A.R.T. parameter is for use cumulative statistics parameter:
S.M.A.R.T. after parameter value exceedes the highest cumulative statistics value 60% of individual event, detain 10 points and be multiplied by weight 20%, namely detain 2 points;
S.M.A.R.T. after parameter value exceedes the highest cumulative statistics value 80% of individual event, detain 10 points and be multiplied by weight 40%, namely detain 4 points;
S.M.A.R.T. after parameter value exceedes 90% of the highest cumulative statistics value of individual event, weighting levels adjusts into highest ranking, does not exceed 20 points, threshold value button, exceedes 25 points, threshold value button;
When S.M.A.R.T. parameter is using state monitoring parameter:
S.M.A.R.T. parameter value is detained 10 points be multiplied by weight 20% more than S.M.A.R.T. parameter normal fluctuation curve and scope for continuous one week, namely detains 2 points;
S.M.A.R.T. parameter value is detained 10 points be multiplied by weight 40% more than S.M.A.R.T. parameter normal fluctuation curve and scope for continuous two weeks, namely detains 4 points;
S.M.A.R.T. weighting levels adjusts into highest ranking parameter value more than S.M.A.R.T. parameter normal fluctuation curve and scope continuous January, does not exceed 20 points, threshold value button, exceedes 25 points, threshold value button;
404 generate Gernral Check-up scoring dynamic model.Based on the weight factor of 402 and the code of points of 403, in conjunction with each HD vendor and master control manufacturer S.M.A.R.T. setting parameter, set up hard disk Gernral Check-up scoring algorithm model.
405 diagnosis.
406 adjustment Gernral Check-up scoring dynamic models.According to feedback data, revise weight factor and the code of points of fine setting S.M.A.R.T. parameter, generate new Gernral Check-up scoring dynamic model; Amendment record will be correlated with at cloud storage server.
Based on a device for SMART Data Dynamic diagnosis hard disk failure, comprise cloud stores service end unit, hard disk failure early warning dynamic model generation unit, S.M.A.R.T. parameter normal fluctuation curve and scope generation unit and Gernral Check-up scoring dynamic model generation unit;
Cloud stores service end, for persistent collection three class data: one is hard disk type data, comprises hard disk brand and model; Two is S.M.A.R.T. supplemental characteristic and parameter collection time data; Three is Hard disk error daily record datas of operating system record;
Hard disk failure early warning dynamic model generation unit, for the hard disk brand of the S.M.A.R.T. collected supplemental characteristic and correspondence thereof, model data being normalized, generates normalization S.M.A.R.T. data acquisition; Based on normalization S.M.A.R.T. data acquisition and the Hard disk error daily record data collected, set up hard disk failure early warning dynamic model;
S.M.A.R.T. parameter normal fluctuation curve and scope generation unit, be group for the S.M.A.R.T. data that will collect with parameter, in conjunction with corresponding hard disk brand, model data, form different brands, different model hard disk S.M.A.R.T. dynamic state of parameters change curve, statistics show that hard disk health runs S.M.A.R.T. parameter normal fluctuation range, sets up S.M.A.R.T. parameter normal fluctuation curve and scope;
Gernral Check-up scoring dynamic model generation unit, for by large data analysis, draws the S.M.A.R.T. parameters weighting of different brands different model hard disk; According to the setting of HD vendor to S.M.A.R.T. early-warning parameters, combined training learning data, draws the early-warning parameters that different brands different model hard disk is new and the weighing factor factor to hard disk health; Set a full marks value, according to new S.M.A.R.T. parameters weighting and the weighing factor factor to hard disk health, setting standard of deducting point, draws Gernral Check-up scoring dynamic model.
Hard disk type data also comprise sequence number, firmware version, interface type, disk running speed, disk size and buffer memory size data.
Claims (7)
1., based on a method for SMART Data Dynamic diagnosis hard disk failure, it is characterized in that: comprise the following steps:
101 set up cloud stores service end, persistent collection three class data: is hard disk type data, comprises hard disk brand and model; Two is S.M.A.R.T. supplemental characteristic and parameter collection time data; Three is Hard disk error daily record datas of operating system record;
The hard disk brand of the S.M.A.R.T. supplemental characteristic collected and correspondence thereof, model data are normalized by 102, generate normalization S.M.A.R.T. data acquisition; Based on normalization S.M.A.R.T. data acquisition and the Hard disk error daily record data collected, set up hard disk failure early warning dynamic model;
The S.M.A.R.T. data collected are group with parameter by 103, in conjunction with corresponding hard disk brand, model data, form different brands, different model hard disk S.M.A.R.T. dynamic state of parameters change curve, statistics show that hard disk health runs S.M.A.R.T. parameter normal fluctuation range, sets up S.M.A.R.T. parameter normal fluctuation curve and scope;
104 by large data analysis, draws the S.M.A.R.T. parameters weighting of different brands different model hard disk; According to the setting of HD vendor to S.M.A.R.T. early-warning parameters, combined training learning data, draws the early-warning parameters that different brands different model hard disk is new and the weighing factor factor to hard disk health; Set a full marks value, according to new S.M.A.R.T. parameters weighting and the weighing factor factor to hard disk health, setting standard of deducting point, draws Gernral Check-up scoring dynamic model; Based on hard disk failure early warning dynamic model, S.M.A.R.T. parameter normal fluctuation curve and scope, Gernral Check-up scoring dynamic model, diagnostic score is carried out to hard disk health status, provides specific aim suggestion; If hard disk exists risk, automatically carry out early warning; If early warning mistake, start the machine study.
2. a kind of method based on SMART Data Dynamic diagnosis hard disk failure according to claim 1, is characterized in that: 102 comprise the following steps:
201 data normalizations, adopt Z-score standardized method, concrete formula is:
wherein, x is the sample data of 101 collections, and x* is the data after normalization, and μ is the average of all sample datas, and σ is the standard deviation of all sample datas;
Normalized data are classified by disk, magnetic head, head arm, motor, control circuit board, data-interface, master control and flash memory particle by 202;
203 by normalized grouped data, by HD vendor, brand, model in groups;
204 according to the threshold value of every S.M.A.R.T. parameter of each factory settings, arranges the early warning value of Classified into groups data after normalization; Build S.M.A.R.T. parameter comparison model; Combine every contrast model, early warning trigger formation hard disk failure early warning dynamic model;
205 read hard disk S.M.A.R.T. supplemental characteristic to be checked, and import comparison model, when a certain data exceed early warning value, early warning flip-flop toggle, pushes early warning information automatically, prompting user's hard disk failure place;
206 read and collect hard disk S.M.A.R.T. supplemental characteristic to be checked, after normalized, store end stored in cloud; According to hard disk S.M.A.R.T. supplemental characteristic to be checked and wrong early warning item, after the normalization that correction is corresponding, the early warning value of Classified into groups data, generates new hard disk failure early warning dynamic model; Amendment record will be correlated with at cloud storage server.
3. a kind of method based on SMART Data Dynamic diagnosis hard disk failure according to claim 1 and 2, is characterized in that: 103 comprise the following steps:
301 call the S.M.A.R.T. parameter and parameter collection time that cloud stores service end collects, and with individual event S.M.A.R.T. supplemental characteristic for the longitudinal axis, the time is transverse axis; Generate individual event S.M.A.R.T. parametric plot; So, whole individual event S.M.A.R.T. parametric plot is generated;
302 according to individual event S.M.A.R.T. parametric plot, draws individual event S.M.A.R.T. parameter normal fluctuation range;
303 read hard disk S.M.A.R.T. supplemental characteristic to be checked, and import comparison model, when a certain data exceed normal fluctuation range suddenly, early warning flip-flop toggle, pushes early warning information automatically, prompting user's hard disk failure place;
304 read and collect hard disk early warning mistake S.M.A.R.T. supplemental characteristic to be checked, revise normal fluctuation range: reduce minimum Min or improve maximum Max early warning value, generate new individual event S.M.A.R.T. parameter normal fluctuation range; Amendment record will be correlated with at cloud storage server.
4. a kind of method based on SMART Data Dynamic diagnosis hard disk failure according to claim 3, is characterized in that: 104 comprise the following steps:
401 according to the needs of S.M.A.R.T. parameter and hard disk Gernral Check-up, and the detecting of setting one-level hardware fault, secondary use cumulative statistics and using state monitoring two-stage weighting levels altogether, as the decision factor of Gernral Check-up;
402 based on the original setting of HD vendor, hard disk failure early warning dynamic model correction data, S.M.A.R.T. parameter normal fluctuation curve and scope correction data, in two-stage weight described in 401 and weight the weight factor setting of relevant parameters and regulation rule as follows:
(1) hardware fault detecting weight factor: 80%; Use cumulative statistics and using state monitoring: 10%;
(2), after using cumulative statistics value to exceed the highest cumulative statistics value 60% of individual event, weight factor is promoted to 20%; After exceeding 80% of the highest cumulative statistics value of individual event, weight factor is promoted to 40%; After exceeding 90% of the highest cumulative statistics value of individual event, weighting levels adjusts into highest ranking;
(3) continuous one week of the value of using state monitoring is more than S.M.A.R.T. parameter normal fluctuation curve and scope, and weight factor is promoted to 20%; Within continuous two weeks, exceed, weight factor is promoted to 40%; Continuous January exceedes, and weighting levels adjusts into highest ranking;
403 determine code of points;
404 based on the weight factor of 402 and the code of points of 403, in conjunction with each HD vendor and master control manufacturer S.M.A.R.T. setting parameter, sets up hard disk Gernral Check-up scoring algorithm model;
405 diagnosis;
406 according to feedback data, revises weight factor and the code of points of fine setting S.M.A.R.T. parameter, generates new Gernral Check-up scoring dynamic model; Amendment record will be correlated with at cloud storage server.
5. a kind of method based on SMART Data Dynamic diagnosis hard disk failure according to claim 1, is characterized in that: hard disk type information also comprises sequence number, firmware version, interface type, disk running speed, disk size and buffer memory size data.
6. a kind of device based on SMART Data Dynamic diagnosis hard disk failure according to claim 1, is characterized in that: comprise cloud stores service end unit, hard disk failure early warning dynamic model generation unit, S.M.A.R.T. parameter normal fluctuation curve and scope generation unit and Gernral Check-up scoring dynamic model generation unit;
Cloud stores service end, for persistent collection three class data: one is hard disk type data, comprises hard disk brand and model; Two is S.M.A.R.T. supplemental characteristic and parameter collection time data; Three is Hard disk error daily record datas of operating system record;
Hard disk failure early warning dynamic model generation unit, for the hard disk brand of the S.M.A.R.T. collected supplemental characteristic and correspondence thereof, model data being normalized, generates normalization S.M.A.R.T. data acquisition; Based on normalization S.M.A.R.T. data acquisition and the Hard disk error daily record data collected, set up hard disk failure early warning dynamic model;
S.M.A.R.T. parameter normal fluctuation curve and scope generation unit, be group for the S.M.A.R.T. data that will collect with parameter, in conjunction with corresponding hard disk brand, model data, form different brands, different model hard disk S.M.A.R.T. dynamic state of parameters change curve, statistics show that hard disk health runs S.M.A.R.T. parameter normal fluctuation range, sets up S.M.A.R.T. parameter normal fluctuation curve and scope;
Gernral Check-up scoring dynamic model generation unit, for by large data analysis, draws the S.M.A.R.T. parameters weighting of different brands different model hard disk; According to the setting of HD vendor to S.M.A.R.T. early-warning parameters, combined training learning data, draws the early-warning parameters that different brands different model hard disk is new and the weighing factor factor to hard disk health; Set a full marks value, according to new S.M.A.R.T. parameters weighting and the weighing factor factor to hard disk health, setting standard of deducting point, draws Gernral Check-up scoring dynamic model.
7. a kind of device based on SMART Data Dynamic diagnosis hard disk failure according to claim 6, is characterized in that: hard disk type information also comprises sequence number, firmware version, interface type, disk running speed, disk size and buffer memory size data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510738474.0A CN105260279B (en) | 2015-11-04 | 2015-11-04 | Method and apparatus based on SMART data dynamic diagnosis hard disk failure |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510738474.0A CN105260279B (en) | 2015-11-04 | 2015-11-04 | Method and apparatus based on SMART data dynamic diagnosis hard disk failure |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105260279A true CN105260279A (en) | 2016-01-20 |
| CN105260279B CN105260279B (en) | 2019-01-01 |
Family
ID=55099979
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510738474.0A Active CN105260279B (en) | 2015-11-04 | 2015-11-04 | Method and apparatus based on SMART data dynamic diagnosis hard disk failure |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105260279B (en) |
Cited By (36)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107025154A (en) * | 2016-01-29 | 2017-08-08 | 阿里巴巴集团控股有限公司 | The failure prediction method and device of disk |
| CN107172128A (en) * | 2017-04-24 | 2017-09-15 | 华南理工大学 | A kind of manufacturing equipment big data acquisition method of cloud auxiliary |
| WO2017184157A1 (en) | 2016-04-22 | 2017-10-26 | Hewlett-Packard Development Company, L.P. | Determining the health of a storage drive |
| CN107391325A (en) * | 2017-06-30 | 2017-11-24 | 郑州云海信息技术有限公司 | A kind of method of testing of hard disk, device and terminal |
| CN107479836A (en) * | 2017-08-29 | 2017-12-15 | 郑州云海信息技术有限公司 | Disk failure monitoring method, device and storage system |
| CN108073486A (en) * | 2017-12-28 | 2018-05-25 | 新华三大数据技术有限公司 | The Forecasting Methodology and device of a kind of hard disk failure |
| CN108446734A (en) * | 2018-03-20 | 2018-08-24 | 中科边缘智慧信息科技（苏州）有限公司 | Disk failure automatic prediction method based on artificial intelligence |
| CN108681496A (en) * | 2018-05-09 | 2018-10-19 | 北京奇艺世纪科技有限公司 | Prediction technique, device and the electronic equipment of disk failure |
| CN108763023A (en) * | 2018-05-29 | 2018-11-06 | 郑州云海信息技术有限公司 | A kind of stage division of disk, device, equipment and readable storage medium storing program for executing |
| CN108846833A (en) * | 2018-05-30 | 2018-11-20 | 郑州云海信息技术有限公司 | A method of hard disk failure is diagnosed based on TensorFlow image recognition |
| CN108959006A (en) * | 2018-06-29 | 2018-12-07 | 郑州云海信息技术有限公司 | A kind of hardware detection method and its tool |
| CN109032891A (en) * | 2018-07-23 | 2018-12-18 | 郑州云海信息技术有限公司 | A kind of cloud computing server hard disk failure prediction technique and device |
| CN109144833A (en) * | 2017-06-27 | 2019-01-04 | 中兴通讯股份有限公司 | A kind of hard disk analysis method and device |
| CN109144835A (en) * | 2018-08-02 | 2019-01-04 | 广东浪潮大数据研究有限公司 | A kind of automatic prediction method, device, equipment and the medium of application service failure |
| CN109144798A (en) * | 2018-08-13 | 2019-01-04 | 清华大学 | Intelligent management system with machine learning function |
| CN109828869A (en) * | 2018-12-05 | 2019-05-31 | 中兴通讯股份有限公司 | Predict the method, apparatus and storage medium of hard disk failure time of origin |
| CN109918246A (en) * | 2019-02-28 | 2019-06-21 | 苏州浪潮智能科技有限公司 | A kind of disk state detection method, system, terminal and storage medium |
| CN109945968A (en) * | 2019-03-19 | 2019-06-28 | 苏州浪潮智能科技有限公司 | A kind of detection hard disk multiple location is impacted device, the method and system of size by noise |
| CN110119344A (en) * | 2019-04-10 | 2019-08-13 | 河南文正电子数据处理有限公司 | Hard disk health status analysis method based on S.M.A.R.T parameter |
| CN110427311A (en) * | 2019-06-26 | 2019-11-08 | 华中科技大学 | Disk failure prediction technique and system based on temporal aspect processing and model optimization |
| CN110888763A (en) * | 2018-09-11 | 2020-03-17 | 北京奇虎科技有限公司 | Disk fault diagnosis method and device, terminal equipment and computer storage medium |
| CN110929305A (en) * | 2019-08-08 | 2020-03-27 | 北京盛赞科技有限公司 | Hard disk protection method, device, equipment and computer readable storage medium |
| CN111382029A (en) * | 2020-03-05 | 2020-07-07 | 清华大学 | Mainboard abnormity diagnosis method and device based on PCA and multidimensional monitoring data |
| CN111581072A (en) * | 2020-05-12 | 2020-08-25 | 国网安徽省电力有限公司信息通信分公司 | Disk failure prediction method based on SMART and performance log |
| CN111656446A (en) * | 2018-01-31 | 2020-09-11 | 惠普发展公司，有限责任合伙企业 | Hard disk drive life prediction |
| CN111835593A (en) * | 2020-07-14 | 2020-10-27 | 杭州海康威视数字技术股份有限公司 | Detection method based on nonvolatile storage medium, storage medium and electronic equipment |
| CN111966569A (en) * | 2019-05-20 | 2020-11-20 | 中国电信股份有限公司 | Hard disk health degree evaluation method and device and computer readable storage medium |
| WO2020263336A1 (en) * | 2019-06-26 | 2020-12-30 | Western Digital Technologies, Inc. | Use of recovery behavior for prognosticating and in-situ repair of data storage devices |
| CN112231141A (en) * | 2020-09-18 | 2021-01-15 | 苏州浪潮智能科技有限公司 | Method and device for improving Raid data backup efficiency |
| CN112416670A (en) * | 2020-11-12 | 2021-02-26 | 宁畅信息产业(北京)有限公司 | Hard disk test method, device, server and storage medium |
| CN112486787A (en) * | 2020-11-13 | 2021-03-12 | 苏州浪潮智能科技有限公司 | Method and device for evaluating warning state of hard disk for distributed storage |
| CN112631848A (en) * | 2021-01-13 | 2021-04-09 | 公安部物证鉴定中心 | Intelligent diagnosis method and system for mechanical hard disk faults |
| CN113886128A (en) * | 2021-10-20 | 2022-01-04 | 深圳市东方聚成科技有限公司 | SSD (solid State disk) fault diagnosis and data recovery method and system |
| CN117472629A (en) * | 2023-11-02 | 2024-01-30 | 兰州航空职业技术学院 | Multi-fault diagnosis method and system for electronic information system |
| CN117520104A (en) * | 2024-01-08 | 2024-02-06 | 中国民航大学 | System for predicting abnormal state of hard disk |
| TWI845597B (en) * | 2019-01-31 | 2024-06-21 | 新加坡商馬維爾亞洲私人有限公司 | Health management for magnetic storage media |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8094015B2 (en) * | 2009-01-22 | 2012-01-10 | International Business Machines Corporation | Wavelet based hard disk analysis |
| CN103578568A (en) * | 2012-07-24 | 2014-02-12 | 苏州捷泰科信息技术有限公司 | Method and apparatus for testing performances of solid state disks |
| CN103646114A (en) * | 2013-12-26 | 2014-03-19 | 北京百度网讯科技有限公司 | Method and device for extracting feature data from SMART data of hard disk |
| CN104503874A (en) * | 2014-12-29 | 2015-04-08 | 南京大学 | Hard disk failure prediction method for cloud computing platform |
-
2015
- 2015-11-04 CN CN201510738474.0A patent/CN105260279B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8094015B2 (en) * | 2009-01-22 | 2012-01-10 | International Business Machines Corporation | Wavelet based hard disk analysis |
| CN103578568A (en) * | 2012-07-24 | 2014-02-12 | 苏州捷泰科信息技术有限公司 | Method and apparatus for testing performances of solid state disks |
| CN103646114A (en) * | 2013-12-26 | 2014-03-19 | 北京百度网讯科技有限公司 | Method and device for extracting feature data from SMART data of hard disk |
| CN104503874A (en) * | 2014-12-29 | 2015-04-08 | 南京大学 | Hard disk failure prediction method for cloud computing platform |
Non-Patent Citations (3)
| Title |
|---|
| JOSEPH F.MURRAY ET AL.: "Machine Learning Methods for Predicting Failures in Hard Drives:A Multiple-Instance Application", 《JOURNAL OF MACHINE LEARNING RESEARCH》 * |
| YUKIHIRO WATANABE ET AL.: "Online Failure Prediction in Cloud Datacenters by Real-time Message Pattern Learning", 《2012 IEEE 4TH INTERNATIONAL CONFERENCE ON CLOUD COMPUTING TECHNOLOGY AND SCIENCE》 * |
| 宋云华 等: "基于COG-OS框架利用SMART预测云计算平台的硬盘故障", 《计算机应用》 * |
Cited By (56)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107025154B (en) * | 2016-01-29 | 2020-12-01 | 阿里巴巴集团控股有限公司 | Disk failure prediction method and device |
| CN107025154A (en) * | 2016-01-29 | 2017-08-08 | 阿里巴巴集团控股有限公司 | The failure prediction method and device of disk |
| CN109074302A (en) * | 2016-04-22 | 2018-12-21 | 惠普发展公司，有限责任合伙企业 | Determine the health of memory driver |
| WO2017184157A1 (en) | 2016-04-22 | 2017-10-26 | Hewlett-Packard Development Company, L.P. | Determining the health of a storage drive |
| US10963325B2 (en) | 2016-04-22 | 2021-03-30 | Hewlett-Packard Development Company, L.P. | Determining the health of a storage drive |
| CN109074302B (en) * | 2016-04-22 | 2022-04-05 | 惠普发展公司，有限责任合伙企业 | Method and system for determining health of storage drive |
| EP3446220A4 (en) * | 2016-04-22 | 2020-03-25 | Hewlett-Packard Development Company, L.P. | Determining the health of a storage drive |
| CN107172128A (en) * | 2017-04-24 | 2017-09-15 | 华南理工大学 | A kind of manufacturing equipment big data acquisition method of cloud auxiliary |
| CN109144833A (en) * | 2017-06-27 | 2019-01-04 | 中兴通讯股份有限公司 | A kind of hard disk analysis method and device |
| CN107391325A (en) * | 2017-06-30 | 2017-11-24 | 郑州云海信息技术有限公司 | A kind of method of testing of hard disk, device and terminal |
| CN107479836A (en) * | 2017-08-29 | 2017-12-15 | 郑州云海信息技术有限公司 | Disk failure monitoring method, device and storage system |
| CN108073486B (en) * | 2017-12-28 | 2022-05-10 | 新华三大数据技术有限公司 | Hard disk fault prediction method and device |
| CN108073486A (en) * | 2017-12-28 | 2018-05-25 | 新华三大数据技术有限公司 | The Forecasting Methodology and device of a kind of hard disk failure |
| CN111656446A (en) * | 2018-01-31 | 2020-09-11 | 惠普发展公司，有限责任合伙企业 | Hard disk drive life prediction |
| CN108446734A (en) * | 2018-03-20 | 2018-08-24 | 中科边缘智慧信息科技（苏州）有限公司 | Disk failure automatic prediction method based on artificial intelligence |
| CN108681496A (en) * | 2018-05-09 | 2018-10-19 | 北京奇艺世纪科技有限公司 | Prediction technique, device and the electronic equipment of disk failure |
| CN108763023A (en) * | 2018-05-29 | 2018-11-06 | 郑州云海信息技术有限公司 | A kind of stage division of disk, device, equipment and readable storage medium storing program for executing |
| CN108846833A (en) * | 2018-05-30 | 2018-11-20 | 郑州云海信息技术有限公司 | A method of hard disk failure is diagnosed based on TensorFlow image recognition |
| CN108959006A (en) * | 2018-06-29 | 2018-12-07 | 郑州云海信息技术有限公司 | A kind of hardware detection method and its tool |
| CN109032891A (en) * | 2018-07-23 | 2018-12-18 | 郑州云海信息技术有限公司 | A kind of cloud computing server hard disk failure prediction technique and device |
| CN109144835A (en) * | 2018-08-02 | 2019-01-04 | 广东浪潮大数据研究有限公司 | A kind of automatic prediction method, device, equipment and the medium of application service failure |
| CN109144798A (en) * | 2018-08-13 | 2019-01-04 | 清华大学 | Intelligent management system with machine learning function |
| CN109144798B (en) * | 2018-08-13 | 2020-11-10 | 清华大学 | Intelligent management system with machine learning function |
| CN110888763A (en) * | 2018-09-11 | 2020-03-17 | 北京奇虎科技有限公司 | Disk fault diagnosis method and device, terminal equipment and computer storage medium |
| CN109828869A (en) * | 2018-12-05 | 2019-05-31 | 中兴通讯股份有限公司 | Predict the method, apparatus and storage medium of hard disk failure time of origin |
| CN109828869B (en) * | 2018-12-05 | 2020-12-04 | 南京中兴软件有限责任公司 | Method, device and storage medium for predicting hard disk fault occurrence time |
| TWI845597B (en) * | 2019-01-31 | 2024-06-21 | 新加坡商馬維爾亞洲私人有限公司 | Health management for magnetic storage media |
| CN109918246A (en) * | 2019-02-28 | 2019-06-21 | 苏州浪潮智能科技有限公司 | A kind of disk state detection method, system, terminal and storage medium |
| CN109945968A (en) * | 2019-03-19 | 2019-06-28 | 苏州浪潮智能科技有限公司 | A kind of detection hard disk multiple location is impacted device, the method and system of size by noise |
| CN110119344B (en) * | 2019-04-10 | 2023-09-01 | 深圳市科新精密电子有限公司 | Hard disk health state analysis method based on S.M.A.R.T. parameters |
| CN110119344A (en) * | 2019-04-10 | 2019-08-13 | 河南文正电子数据处理有限公司 | Hard disk health status analysis method based on S.M.A.R.T parameter |
| CN111966569B (en) * | 2019-05-20 | 2024-10-18 | 中国电信股份有限公司 | Hard disk health evaluation method and device and computer readable storage medium |
| CN111966569A (en) * | 2019-05-20 | 2020-11-20 | 中国电信股份有限公司 | Hard disk health degree evaluation method and device and computer readable storage medium |
| US10969969B2 (en) | 2019-06-26 | 2021-04-06 | Western Digital Technologies, Inc. | Use of recovery behavior for prognosticating and in-situ repair of data storage devices |
| CN110427311A (en) * | 2019-06-26 | 2019-11-08 | 华中科技大学 | Disk failure prediction technique and system based on temporal aspect processing and model optimization |
| WO2020263336A1 (en) * | 2019-06-26 | 2020-12-30 | Western Digital Technologies, Inc. | Use of recovery behavior for prognosticating and in-situ repair of data storage devices |
| CN113179657A (en) * | 2019-06-26 | 2021-07-27 | 西部数据技术公司 | Use of recovery behavior for prognosis and in situ repair of data storage devices |
| CN110929305A (en) * | 2019-08-08 | 2020-03-27 | 北京盛赞科技有限公司 | Hard disk protection method, device, equipment and computer readable storage medium |
| CN111382029A (en) * | 2020-03-05 | 2020-07-07 | 清华大学 | Mainboard abnormity diagnosis method and device based on PCA and multidimensional monitoring data |
| CN111382029B (en) * | 2020-03-05 | 2021-09-03 | 清华大学 | Mainboard abnormity diagnosis method and device based on PCA and multidimensional monitoring data |
| CN111581072A (en) * | 2020-05-12 | 2020-08-25 | 国网安徽省电力有限公司信息通信分公司 | Disk failure prediction method based on SMART and performance log |
| CN111581072B (en) * | 2020-05-12 | 2023-08-15 | 国网安徽省电力有限公司信息通信分公司 | Disk fault prediction method based on SMART and performance log |
| CN111835593B (en) * | 2020-07-14 | 2022-06-03 | 杭州海康威视数字技术股份有限公司 | Detection method based on nonvolatile storage medium, storage medium and electronic equipment |
| CN111835593A (en) * | 2020-07-14 | 2020-10-27 | 杭州海康威视数字技术股份有限公司 | Detection method based on nonvolatile storage medium, storage medium and electronic equipment |
| CN112231141A (en) * | 2020-09-18 | 2021-01-15 | 苏州浪潮智能科技有限公司 | Method and device for improving Raid data backup efficiency |
| CN112231141B (en) * | 2020-09-18 | 2022-07-29 | 苏州浪潮智能科技有限公司 | Method and device for improving Raid data backup efficiency |
| CN112416670A (en) * | 2020-11-12 | 2021-02-26 | 宁畅信息产业(北京)有限公司 | Hard disk test method, device, server and storage medium |
| CN112416670B (en) * | 2020-11-12 | 2024-02-09 | 宁畅信息产业(北京)有限公司 | Hard disk testing method, device, server and storage medium |
| CN112486787A (en) * | 2020-11-13 | 2021-03-12 | 苏州浪潮智能科技有限公司 | Method and device for evaluating warning state of hard disk for distributed storage |
| CN112631848A (en) * | 2021-01-13 | 2021-04-09 | 公安部物证鉴定中心 | Intelligent diagnosis method and system for mechanical hard disk faults |
| CN113886128B (en) * | 2021-10-20 | 2022-09-09 | 深圳市东方聚成科技有限公司 | SSD (solid State disk) fault diagnosis and data recovery method and system |
| CN113886128A (en) * | 2021-10-20 | 2022-01-04 | 深圳市东方聚成科技有限公司 | SSD (solid State disk) fault diagnosis and data recovery method and system |
| CN117472629A (en) * | 2023-11-02 | 2024-01-30 | 兰州航空职业技术学院 | Multi-fault diagnosis method and system for electronic information system |
| CN117472629B (en) * | 2023-11-02 | 2024-05-28 | 兰州航空职业技术学院 | Multi-fault diagnosis method and system for electronic information system |
| CN117520104B (en) * | 2024-01-08 | 2024-03-29 | 中国民航大学 | System for predicting abnormal state of hard disk |
| CN117520104A (en) * | 2024-01-08 | 2024-02-06 | 中国民航大学 | System for predicting abnormal state of hard disk |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105260279B (en) | 2019-01-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105260279A (en) | Method and device of dynamically diagnosing hard disk failure based on S.M.A.R.T (Self-Monitoring Analysis and Reporting Technology) data | |
| US11093519B2 (en) | Artificial intelligence (AI) based automatic data remediation | |
| US20210041862A1 (en) | Malfunction early-warning method for production logistics delivery equipment | |
| CN109905269B (en) | Method and device for determining network fault | |
| CN108959564A (en) | Data warehouse metadata management method, readable storage medium storing program for executing and computer equipment | |
| CN105095747B (en) | A kind of Java application health degree appraisal procedure and system | |
| US20160203036A1 (en) | Machine learning-based fault detection system | |
| CN111242323B (en) | Active automatic system and method for repairing suboptimal operation of a machine | |
| EP3776115A1 (en) | Predicting failures in electrical submersible pumps using pattern recognition | |
| CN110119344B (en) | Hard disk health state analysis method based on S.M.A.R.T. parameters | |
| US20160171037A1 (en) | Model change boundary on time series data | |
| CN104956373A (en) | Determining suspected root causes of anomalous network behavior | |
| CN109815533A (en) | It is a kind of difference operating condition under hydroelectric machine group parts Operational Data Analysis method and system | |
| JP7180985B2 (en) | Diagnostic device and diagnostic method | |
| CN108255620A (en) | A kind of business logic processing method, apparatus, service server and system | |
| GB2608772A (en) | Machine learning based data monitoring | |
| US20170236071A1 (en) | Alarm management system | |
| CN109783509A (en) | SQL scenario generation method and device | |
| CN117913830B (en) | Resource scheduling method and system for pumped storage power station | |
| WO2017127260A1 (en) | System and method for allocating machine behavioral models | |
| JP7167992B2 (en) | label correction device | |
| WO2018154558A1 (en) | Methods and systems for problem-alert aggregation | |
| JP2016532221A (en) | Apparatus and method for model fitting | |
| US11520831B2 (en) | Accuracy metric for regular expression | |
| KR102236802B1 (en) | Device and method for feature extraction of data for diagnostic models |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |