CN109213034A - Equipment health degree monitoring method, device, computer equipment and readable storage medium storing program for executing - Google Patents
Equipment health degree monitoring method, device, computer equipment and readable storage medium storing program for executing Download PDFInfo
- Publication number
- CN109213034A CN109213034A CN201810978149.5A CN201810978149A CN109213034A CN 109213034 A CN109213034 A CN 109213034A CN 201810978149 A CN201810978149 A CN 201810978149A CN 109213034 A CN109213034 A CN 109213034A
- Authority
- CN
- China
- Prior art keywords
- equipment
- monitored
- model
- training
- monitoring
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/04—Programme control other than numerical control, i.e. in sequence controllers or logic controllers
- G05B19/042—Programme control other than numerical control, i.e. in sequence controllers or logic controllers using digital processors
- G05B19/0428—Safety, monitoring
-
- 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
- G05B2219/20—Pc systems
- G05B2219/24—Pc safety
- G05B2219/24024—Safety, surveillance
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The present invention provides a kind of equipment health degree monitoring method, device, computer equipment and computer readable storage medium, this method comprises: obtaining production action message and yield monitoring data of the equipment to be monitored in preset duration；The production action message and the yield monitoring data are handled by health monitoring model trained in advance, obtain health degree curve of the equipment to be monitored in the preset duration.The present invention does not need excessive tune ginseng, as long as having accumulated enough data, can train health monitoring model quickly, detection process high degree of automation, a large amount of time and cost of labor have been saved, it can be with accurate quantification, so as to select most appropriate maintenance time to health degree.
Description
Technical field
The present invention relates to technical field of data processing, in particular to a kind of equipment health degree monitoring method method, dress
It sets, computer equipment and computer readable storage medium.
Background technique
In field of industrial production, need to be monitored the health degree of industrial equipment.The health degree of industrial equipment monitors
At present industry there is an urgent need to technology, be realize predictive maintenance premise.
Industry safeguards two ways after generalling use periodic maintenance and failure to the maintenance of electromechanical equipment.Wherein, the former
Institute is at high cost, and flexibility is poor, is also difficult to find to the plant issue in latency stage.The latter then be easy to cause the serious of equipment
Damage and the underproof consequence of the large quantities of products, bring huge loss to factory.
Therefore it is badly in need of a kind of plant maintenance scheme of economic and reliable, currently to accomplish neither to spend cost when there is no problem
It goes to detect, will not be handled not in time when problem occurs and causes serious consequence.
Summary of the invention
In view of this, the embodiment of the present invention is designed to provide a kind of equipment health degree monitoring method method, apparatus, meter
Machine equipment and computer readable storage medium are calculated, to accomplish to spend cost to go to detect not when there is no problem, and is occurred in problem
When can handle in time, avoid serious consequence.
In a first aspect, the embodiment of the invention provides a kind of equipment health degree monitoring methods, which comprises
Obtain production action message and yield monitoring data of the equipment to be monitored in preset duration；
By health monitoring model trained in advance to the production action message and the yield monitoring data at
Reason obtains health degree curve of the equipment to be monitored in the preset duration.
With reference to first aspect, the embodiment of the invention provides the first possible implementation of above-mentioned first aspect,
In, the yield monitoring data for obtaining equipment to be monitored in preset duration, comprising:
Obtain production audio data of the equipment to be monitored in preset duration；
Identifying processing is carried out to the production audio data by the yield monitor system pre-established, is obtained described wait supervise
Yield monitoring data of the measurement equipment in the preset duration.
With reference to first aspect, the embodiment of the invention provides second of possible implementation of above-mentioned first aspect,
In, it is described that the production action message and the yield monitoring data are handled by health monitoring model trained in advance
Before, further includes:
Obtain the corresponding training dataset of the equipment to be monitored；
According to training dataset training health monitoring model.
The possible implementation of second with reference to first aspect, the embodiment of the invention provides the of above-mentioned first aspect
Three kinds of possible implementations, wherein described to obtain the corresponding training dataset of the equipment to be monitored, comprising:
The production action message of the equipment to be monitored whithin a period of time is obtained, and by described in sound pick-up outfit admission
Production audio data of the equipment to be monitored within described a period of time；
Identifying processing is carried out to the production audio data in described a period of time by the yield monitoring model pre-established,
Obtain the corresponding yield monitoring data of the production action message；
The production action message and the corresponding yield monitoring data of the production action message are determined as described wait supervise
The corresponding training dataset of measurement equipment.
The possible implementation of second with reference to first aspect, the embodiment of the invention provides the of above-mentioned first aspect
Four kinds of possible implementations, wherein described according to training dataset training health monitoring model, comprising:
The training dataset is divided into training set and verifying collection；
Pass through training set training OneClassSVM model；
By verifying collection described in the OneClassSVM model analysis, obtains the verifying and collect corresponding health degree curve；
Collect corresponding health degree curve according to verifying collection and the verifying, adjusts in the OneClassSVM model
Negative sample scale parameter；
The OneClassSVM model adjusted is determined as the corresponding health monitoring model of the equipment to be monitored.
Second aspect, the embodiment of the invention provides a kind of equipment health degree monitoring device, described device includes:
Module is obtained, for obtaining production action message and yield monitoring data of the equipment to be monitored in preset duration；
Processing module is monitored, for the health monitoring model by training in advance to the production action message and the production
Amount monitoring data are handled, and health degree curve of the equipment to be monitored in the preset duration is obtained.
In conjunction with second aspect, the embodiment of the invention provides the first possible implementation of above-mentioned second aspect,
In, described device further include:
Model training module, for obtaining the corresponding training dataset of the equipment to be monitored；According to the training data
Collect training health monitoring model.
In conjunction with the first possible implementation of second aspect, the embodiment of the invention provides the of above-mentioned second aspect
Two kinds of possible implementations, wherein the model training module includes:
Division unit, for the training dataset to be divided into training set and verifying collection；
Training unit, for passing through training set training OneClassSVM model；
Analytical unit obtains the verifying collection and corresponds to for being collected by verifying described in the OneClassSVM model analysis
Health degree curve；
Adjustment unit, for according to verifying collection and the corresponding health degree curve of verifying collection, described in adjustment
Negative sample scale parameter in OneClassSVM model；
Determination unit, it is corresponding for the OneClassSVM model adjusted to be determined as the equipment to be monitored
Health monitoring model.
The third aspect, the embodiment of the invention provides a kind of computer equipment, described device includes processor and memory；
The memory is stored with executable instruction, and when the apparatus is operative, the processor executes in the memory
The executable instruction of storage, to realize equipment health degree monitoring method described in above-mentioned first aspect.
Fourth aspect, the embodiment of the invention provides a kind of computer readable storage medium, the computer-readable storage
Executable instruction is stored in medium, the executable instruction, which is executed by processor, realizes that equipment described in above-mentioned first aspect is strong
Kang Du monitoring method.
In embodiments of the present invention, production action message and yield monitoring number of the equipment to be monitored in preset duration are obtained
According to；The production action message and the yield monitoring data are handled by health monitoring model trained in advance, obtained
Obtain health degree curve of the equipment to be monitored in the preset duration.The present invention does not need excessive tune ginseng, as long as accumulation
Enough data, can train health monitoring model, detection process high degree of automation, when having saved a large amount of quickly
Between and cost of labor, can be with accurate quantification, so as to select most appropriate maintenance time to health degree.
To enable the above objects, features and advantages of the present invention to be clearer and more comprehensible, preferred embodiment is cited below particularly, and cooperate
Appended attached drawing, is described in detail below.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only certain embodiments of the present invention, therefore is not construed as pair
The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 shows a kind of flow diagram of preparatory trained health monitoring model provided by the embodiment of the present invention 1；
Fig. 2 shows a kind of flow charts of equipment health degree monitoring method provided by the embodiment of the present invention 1；
Fig. 3 shows the flow chart of another kind equipment health degree monitoring method provided by the embodiment of the present invention 1；
Fig. 4 shows a kind of effect picture of equipment health degree monitoring provided by the embodiment of the present invention 1；
Fig. 5 shows a kind of waveform diagram of equipment health degree exception provided by the embodiment of the present invention 1；
Fig. 6 shows a kind of structural schematic diagram of equipment health degree monitoring device provided by the embodiment of the present invention 2.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
Middle attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is only
It is a part of the embodiment of the present invention, instead of all the embodiments.The present invention being usually described and illustrated herein in the accompanying drawings is real
The component for applying example can be arranged and be designed with a variety of different configurations.Therefore, of the invention to what is provided in the accompanying drawings below
The detailed description of embodiment is not intended to limit the range of claimed invention, but is merely representative of selected reality of the invention
Apply example.Based on the embodiment of the present invention, those skilled in the art institute obtained without making creative work
There are other embodiments, shall fall within the protection scope of the present invention.
In view of safeguarding two kinds of plant maintenance modes after generalling use periodic maintenance and failure in the related technology.Wherein, fixed
Phase maintenance cost is high, and flexibility is poor, is also difficult to find to the plant issue in latency stage.It safeguards, be easy to cause after failure
The underproof consequence of the badly damaged and large quantities of products of equipment, brings huge loss to factory.Based on this, the embodiment of the present invention
A kind of equipment health degree monitoring method method, apparatus, computer equipment and computer readable storage medium are provided, below by
Embodiment is described.
Embodiment 1
The embodiment of the invention provides a kind of equipment health degree monitoring methods.Equipment to be monitored is being monitored by this method
Health degree before, need to establish for treat monitoring device carry out yield monitoring yield monitor system.Wherein, yield monitoring
System includes sound pick-up outfit and monitor terminal, and sound pick-up outfit can be microphone or recorder etc., and sound pick-up outfit is arranged wait supervise
Near measurement equipment, and sound pick-up outfit is communicated with monitor terminal by wired or wireless way.
In embodiments of the present invention, equipment to be monitored can be one or more production equipment, and equipment to be monitored produced
Cheng Zhonghui makes a sound, and is collected by the sound pick-up outfit that equipment to be monitored is nearby arranged and is generated in equipment production process to be monitored
Audio data.The audio data of admission is sent to monitor terminal by sound pick-up outfit.Monitor terminal is by audio data through Fourier point
The 2-d spectrum data of m- frequency domain when solution is converted into, marked in the 2-d spectrum data process starting point that produces every time and
2-d spectrum data after label are divided into multiple training datas according to prefixed time interval, according to multiple instructions by process terminal
Practice data training convolutional neural networks.The corresponding yield monitoring system of equipment to be monitored is set up after training convolutional neural networks
System.Monitor terminal, which passes through the convolutional neural networks trained, can treat the real-time yield monitoring of monitoring device progress.
As shown in Figure 1, after setting up the corresponding yield monitor system of equipment to be monitored through the above way, first by such as
The step of lower A1-A2, trains the corresponding health monitoring model of equipment to be monitored, specifically includes:
A1: the corresponding training dataset of equipment to be monitored is obtained.
The production action message of equipment to be monitored whithin a period of time is obtained, and to be monitored set is enrolled by sound pick-up outfit
Standby production audio data whithin a period of time；By the yield monitoring model that pre-establishes to the production audio in a period of time
Data carry out identifying processing, obtain the corresponding yield monitoring data of production action message；It will production action message and production movement
The corresponding yield monitoring data of information are determined as the corresponding training dataset of equipment to be monitored.
Above-mentioned production action message includes the information such as the operating parameter of time and equipment to be monitored.Get equipment to be monitored
After corresponding production audio data, by the convolutional neural networks in the yield monitoring model that pre-establishes to production audio data
Identifying processing is carried out, the not normalized original output of convolutional neural networks is supervised as the corresponding yield of above-mentioned production action message
Production action message and corresponding yield monitoring data are determined as corresponding training dataset with oneself to be monitored by measured data.It should
Training dataset does not need to be marked, and can save workload, improves monitoring efficiency.
A2: according to training dataset training health monitoring model.
Training dataset is divided into training set and verifying collection；Pass through training set training OneClassSVM model.Wherein,
Whether OneClassSVM model can distinguish new input similar to the sample in training set.Pass through OneClassSVM model point
Analysis verifying collection, is verified the corresponding health degree curve of collection.Collect corresponding health degree curve, adjustment according to verifying collection and verifying
Negative sample scale parameter in OneClassSVM model.OneClassSVM model adjusted is determined as equipment pair to be monitored
The health monitoring model answered.
In embodiments of the present invention, the scale of training dataset is the bigger the better, due to convolutional Neural in yield detection system
The original output of network is only an one-dimension array, the duration that data volume is produced by single and is divided into how many different
Stage determines that usually tens arrive several hundred magnitudes, therefore the complexity of OneClassSVM model training is very low, can permit
Perhaps signal as much as possible is chosen under conditions of as training dataset, it is not necessary to distinguish the signal normally with improper production.
The training of OneClassSVM model needs to adjust negative sample proportion, and algorithm can will be instructed according to this ratio
Most of data that white silk data integrated distribution is concentrated the most are as positive sample, and remaining outlier is as negative sample, to be divided
Interface.Therefore the ratio that the ratio of negative sample should be shared close to practical improper production movement as far as possible, can wait for according to the past
The frequency that monitoring device breaks down is estimated.If not passing by the frequency that equipment to be monitored breaks down, can also lead to
The mode continuously attempted to as follows is crossed to determine:
The sample for preparing twice is respectively used to training set and checksum set, provides the negative sample ratio of an attempt first
Example, such as 10%, with training set one OneClassSVM model of training, verification is calculated by trained OneClassSVM model
Collect corresponding health degree, analyzes the health degree lower time, see the problem of whether corresponding to equipment to be monitored.If equipment to be monitored does not have
It is problematic, but health degree it is lower situation it is very much, then can reduce negative sample ratio.If each health degree is lower all corresponded to
The problem of monitoring device, it tries increase negative sample ratio, the plant issue for seeing if there is omission does not detect.Repeatedly
It attempts, obtains a suitable negative sample ratio.
After determining negative sample ratio through the above way, the negative sample scale parameter in OneClassSVM model is adjusted.
OneClassSVM model adjusted is the corresponding health monitoring model of equipment to be monitored.
As shown in Fig. 2, the operation training of A1-A2 goes out the corresponding health monitoring model of equipment to be monitored through the above steps
Afterwards, health degree monitoring is carried out by the way that health monitoring model is treated monitoring device, specifically included:
Step 101: obtaining production action message and yield monitoring data of the equipment to be monitored in preset duration.
Above-mentioned preset duration can be 1 hour, 12 hours, one day or one week etc..Equipment to be monitored is obtained in preset duration
Interior production action message, and the sound pick-up outfit being nearby arranged by equipment to be monitored obtain equipment to be monitored in preset duration
Interior production audio data.Production audio data is carried out by the convolutional neural networks in the yield monitor system that pre-establishes
Identifying processing obtains yield monitoring data of the equipment to be monitored in preset duration.
Step 102: by health monitoring model trained in advance to production action message and yield monitoring data at
Reason, obtains health degree curve of the equipment to be monitored in preset duration.
By the health monitoring model OneClassSVM model of above-mentioned training to production action message and yield monitoring data
Classification processing is carried out, determines and belongs to normal production movement, improper production movement is still fallen within, will normally be produced in a period of time
Movement accounts for index of the ratio of total production number as weighing device health degree, can draw out equipment to be monitored when default
Health degree curve in length.
The health degree monitoring scheme provided to facilitate the understanding of the present invention, is made a concrete analysis of with reference to the accompanying drawing.Such as Fig. 3
It is shown, the corresponding training set waveform of equipment to be monitored, verifying collection waveform and waveform to be identified are obtained, yield monitor system point is passed through
It is other that identifying processing is carried out to training set waveform, verifying collection waveform and waveform to be identified, obtain training set CNN (convolutional neural networks)
Original output, the original output of verifying collection CNN and the original output of CNN to be identified.It is carried out using the original output of training set CNN
OneClassSVM model training carries out tune ginseng to the OneClassSVM model trained according to the original output of verifying collection CNN.It adjusts
After ginseng in the actual application of OneClassSVM model, judge that CNN to be identified is original defeated by OneClassSVM model
It is whether normal out, obtain the equipment health degree of equipment to be monitored.
In embodiments of the present invention, a certain or a few equipment are directed in application every time, by being arranged in beside it
Microphone records audio builds yield detection system for these equipment.Next the production action message of a period of time is obtained
And production acts the output of convolutional neural networks in corresponding yield detection system every time, and data are temporally divided into two sections, point
It Yong Zuo not training set and verifying collection.Using training set training OneClassSVM model, and verified with the model analysis trained
Collection, obtain health degree curve, according to health degree curve it is reasonable whether adjust in OneClassSVM model indicate negative sample ratio
Parameter.After adjusting ginseng, that is, OneClassSVM model can be used to carry out health degree analysis to new data.
The equipment health degree method provided through the embodiment of the present invention is illustrated in figure 4 to paste SMT (surface mounting technology)
The result that the equipment health degree of piece machine is analyzed.The curve of Fig. 4, which shares, there is being decreased obviously for health degree at three, except the
It one, is that manufacturer carries out except decline caused by equipment debugging at three liang, decline corresponds to the exception of production movement at centre one, this
It is kind abnormal from the waveform of microphone records also, it is apparent that as shown in figure 5, in the Wave anomaly stage, production movement pair
The tail portion for the waveform answered has lacked several peaks, may correspond to the imperfect of production movement.And after this occurs extremely, manufacturer is connecing
It just reacts after nearly 10 hours and has modified this as a result, if using health degree monitoring scheme provided by the invention, different
1-2 hours after often, being decreased obviously for health degree curve can be seen.The problem of monitoring device can be treated much sooner, makes
Reaction.
In embodiments of the present invention, production action message and yield monitoring number of the equipment to be monitored in preset duration are obtained
According to；The production action message and the yield monitoring data are handled by health monitoring model trained in advance, obtained
Obtain health degree curve of the equipment to be monitored in the preset duration.The present invention does not need excessive tune ginseng, as long as accumulation
Enough data, can train health monitoring model, detection process high degree of automation, when having saved a large amount of quickly
Between and cost of labor, can be with accurate quantification, so as to select most appropriate maintenance time to health degree.
Embodiment 2
As shown in fig. 6, the device is above-mentioned for executing the embodiment of the invention provides a kind of equipment health degree monitoring device
Method provided by embodiment 1.The device includes:
Module 20 is obtained, for obtaining production action message and yield monitoring number of the equipment to be monitored in preset duration
According to；
Processing module 21 is monitored, for the health monitoring model by training in advance to production action message and yield monitoring
Data are handled, and health degree curve of the equipment to be monitored in preset duration is obtained.
Above-mentioned acquisition module 20, for obtaining production audio data of the equipment to be monitored in preset duration；By preparatory
The yield monitor system of foundation carries out identifying processing to the production audio data, obtains the equipment to be monitored described default
Yield monitoring data in duration.
The device further include: model training module, for obtaining the corresponding training dataset of equipment to be monitored；According to training
Data set trains health monitoring model.
Above-mentioned model training module, for obtaining the production action message of the equipment to be monitored whithin a period of time, with
And production audio data of the equipment to be monitored within described a period of time is enrolled by sound pick-up outfit；Pass through what is pre-established
Yield monitoring model carries out identifying processing to the production audio data in described a period of time, obtains the production action message pair
The yield monitoring data answered；The production action message and the corresponding yield monitoring data of the production action message are determined as
The corresponding training dataset of the equipment to be monitored.
Model training module includes:
Division unit, for training dataset to be divided into training set and verifying collection；
Training unit, for passing through training set training OneClassSVM model；
Analytical unit, for being verified the corresponding health of collection and writing music by OneClassSVM model analysis verifying collection
Line；
Adjustment unit collects corresponding health degree curve for collecting according to verifying and verifying, adjusts in OneClassSVM model
Negative sample scale parameter；
Determination unit, for OneClassSVM model adjusted to be determined as the corresponding health monitoring of equipment to be monitored
Model.
In embodiments of the present invention, production action message and yield monitoring number of the equipment to be monitored in preset duration are obtained
According to；The production action message and the yield monitoring data are handled by health monitoring model trained in advance, obtained
Obtain health degree curve of the equipment to be monitored in the preset duration.The present invention does not need excessive tune ginseng, as long as accumulation
Enough data, can train health monitoring model, detection process high degree of automation, when having saved a large amount of quickly
Between and cost of labor, can be with accurate quantification, so as to select most appropriate maintenance time to health degree.
Embodiment 3
The embodiment of the invention provides a kind of computer equipment, which includes processor and memory；
Memory is stored with executable instruction, when the apparatus is operative, stores in processor execution memory executable
Instruction, to realize the equipment health degree monitoring method of the offer of above-described embodiment 1.
The computer equipment is executed instruction by processor, obtains production movement letter of the equipment to be monitored in preset duration
Breath and yield monitoring data；By health monitoring model trained in advance to the production action message and the yield monitoring number
According to being handled, health degree curve of the equipment to be monitored in the preset duration is obtained.Excessive tune ginseng is not needed, only
Enough data are had accumulated, health monitoring model can be trained quickly, detection process high degree of automation has been saved big
The time of amount and cost of labor, can be with accurate quantification, so as to select most appropriate maintenance time to health degree.
Embodiment 4
The embodiment of the invention provides a kind of computer readable storage medium, it is stored in the computer readable storage medium
Executable instruction, executable instruction are computer-executed the equipment health degree monitoring method for realizing that above-described embodiment 1 provides.
After the computer executable instructions of computer storage medium storage are performed, equipment to be monitored is obtained when default
Production action message and yield monitoring data in length；By health monitoring model trained in advance to the production action message
And the yield monitoring data are handled, and health degree curve of the equipment to be monitored in the preset duration is obtained.No
It needs excessive tune to join, as long as having accumulated enough data, health monitoring model can be trained quickly, detection process is automatic
Change degree is high, has saved a large amount of time and cost of labor, can be most appropriate so as to select with accurate quantification to health degree
Maintenance time.
Equipment health degree monitoring device provided by the embodiment of the present invention can be the specific hardware or installation in equipment
In software or firmware etc. in equipment.The technical effect of device provided by the embodiment of the present invention, realization principle and generation and
Preceding method embodiment is identical, and to briefly describe, Installation practice part does not refer to place, can refer in preceding method embodiment
Corresponding contents.It is apparent to those skilled in the art that for convenience and simplicity of description, foregoing description is
The specific work process of system, device and unit, the corresponding process during reference can be made to the above method embodiment, it is no longer superfluous herein
It states.
In embodiment provided by the present invention, it should be understood that disclosed device and method, it can be by others side
Formula is realized.The apparatus embodiments described above are merely exemplary, for example, the division of the unit, only one kind are patrolled
Function division is collected, there may be another division manner in actual implementation, in another example, multiple units or components can combine or can
To be integrated into another system, or some features can be ignored or not executed.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
In addition, each functional unit in embodiment provided by the invention can integrate in one processing unit, it can also
To be that each unit physically exists alone, can also be integrated in one unit with two or more units.
It, can be with if the function is realized in the form of SFU software functional unit and when sold or used as an independent product
It is stored in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, server or network equipment etc.) it performs all or part of the steps of the method described in the various embodiments of the present invention.
And storage medium above-mentioned includes: that USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
The various media that can store program code such as reservoir (RAM, Random Access Memory), magnetic or disk.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, does not then need that it is further defined and explained in subsequent attached drawing, in addition, term " the
One ", " second ", " third " etc. are only used for distinguishing description, are not understood to indicate or imply relative importance.
Finally, it should be noted that embodiment described above, only a specific embodiment of the invention, to illustrate the present invention
Technical solution, rather than its limitations, scope of protection of the present invention is not limited thereto, although with reference to the foregoing embodiments to this hair
It is bright to be described in detail, those skilled in the art should understand that: anyone skilled in the art
In the technical scope disclosed by the present invention, it can still modify to technical solution documented by previous embodiment or can be light
It is readily conceivable that variation or equivalent replacement of some of the technical features；And these modifications, variation or replacement, do not make
The essence of corresponding technical solution is detached from the spirit and scope of technical solution of the embodiment of the present invention.Should all it cover in protection of the invention
Within the scope of.Therefore, protection scope of the present invention should be based on the protection scope of the described claims.
Claims (10)
1. a kind of equipment health degree monitoring method, which is characterized in that the described method includes:
Obtain production action message and yield monitoring data of the equipment to be monitored in preset duration；
The production action message and the yield monitoring data are handled by health monitoring model trained in advance, obtained
Obtain health degree curve of the equipment to be monitored in the preset duration.
2. the method according to claim 1, wherein the yield for obtaining equipment to be monitored in preset duration
Monitoring data, comprising:
Obtain production audio data of the equipment to be monitored in preset duration；
Identifying processing is carried out to the production audio data by the yield monitor system that pre-establishes, obtains described to be monitored set
The standby yield monitoring data in the preset duration.
3. the method according to claim 1, wherein it is described by health monitoring model trained in advance to described
Before production action message and the yield monitoring data are handled, further includes:
Obtain the corresponding training dataset of the equipment to be monitored；
According to training dataset training health monitoring model.
4. according to the method described in claim 3, it is characterized in that, described obtain the corresponding training data of the equipment to be monitored
Collection, comprising:
The production action message of the equipment to be monitored whithin a period of time is obtained, and described wait supervise by sound pick-up outfit admission
Production audio data of the measurement equipment within described a period of time；
Identifying processing is carried out to the production audio data in described a period of time by the yield monitoring model pre-established, is obtained
The corresponding yield monitoring data of the production action message；
The production action message and the corresponding yield monitoring data of the production action message are determined as described to be monitored set
Standby corresponding training dataset.
5. according to the method described in claim 3, it is characterized in that, described according to training dataset training health monitoring mould
Type, comprising:
The training dataset is divided into training set and verifying collection；
Pass through training set training OneClassSVM model；
By verifying collection described in the OneClassSVM model analysis, obtains the verifying and collect corresponding health degree curve；
Collect corresponding health degree curve according to verifying collection and the verifying, adjusts negative in the OneClassSVM model
Sample proportion parameter；
The OneClassSVM model adjusted is determined as the corresponding health monitoring model of the equipment to be monitored.
6. a kind of equipment health degree monitoring device, which is characterized in that described device includes:
Module is obtained, for obtaining production action message and yield monitoring data of the equipment to be monitored in preset duration；
Processing module is monitored, for supervising by health monitoring model trained in advance to the production action message and the yield
Measured data is handled, and health degree curve of the equipment to be monitored in the preset duration is obtained.
7. device according to claim 6, which is characterized in that described device further include:
Model training module, for obtaining the corresponding training dataset of the equipment to be monitored；It is assembled for training according to the training data
Practice health monitoring model.
8. device according to claim 7, which is characterized in that the model training module includes:
Division unit, for the training dataset to be divided into training set and verifying collection；
Training unit, for passing through training set training OneClassSVM model；
It is corresponding strong to obtain the verifying collection for collecting by verifying described in the OneClassSVM model analysis for analytical unit
Kang Du curve；
Adjustment unit, for according to verifying collection and the corresponding health degree curve of verifying collection, described in adjustment
Negative sample scale parameter in OneClassSVM model；
Determination unit, for the OneClassSVM model adjusted to be determined as the corresponding health of the equipment to be monitored
Monitoring model.
9. a kind of computer equipment, which is characterized in that described device includes processor and memory；
The memory is stored with executable instruction, and when the apparatus is operative, the processor executes to be stored in the memory
Executable instruction, to realize the described in any item equipment health degree monitoring methods of the claim 1-5.
10. a kind of computer readable storage medium, which is characterized in that be stored in the computer readable storage medium executable
Instruction, the executable instruction, which is executed by processor, realizes the described in any item equipment health degree monitoring of the claim 1-5
Method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810978149.5A CN109213034B (en) | 2018-08-27 | 2018-08-27 | Equipment health degree monitoring method and device, computer equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810978149.5A CN109213034B (en) | 2018-08-27 | 2018-08-27 | Equipment health degree monitoring method and device, computer equipment and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109213034A true CN109213034A (en) | 2019-01-15 |
| CN109213034B CN109213034B (en) | 2020-04-21 |
Family
ID=64989668
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810978149.5A Active CN109213034B (en) | 2018-08-27 | 2018-08-27 | Equipment health degree monitoring method and device, computer equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109213034B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110262950A (en) * | 2019-05-21 | 2019-09-20 | 阿里巴巴集团控股有限公司 | Abnormal movement detection method and device based on many index |
| CN111310697A (en) * | 2020-02-17 | 2020-06-19 | 硕橙（厦门）科技有限公司 | Equipment operation period detection and health degree analysis method and device and storage medium |
| CN113008494A (en) * | 2021-02-01 | 2021-06-22 | 上海盛磊信息科技有限公司 | Radome structure health degree monitoring equipment and monitoring method based on deep learning |
| CN115270993A (en) * | 2022-08-23 | 2022-11-01 | 南通思诺船舶科技有限公司 | Diesel engine unit state detection method and system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2002054654A2 (en) * | 2001-01-08 | 2002-07-11 | Vextec Corporation | Method and apparatus for predicting failure in a system |
| US7020593B2 (en) * | 2002-12-04 | 2006-03-28 | International Business Machines Corporation | Method for ensemble predictive modeling by multiplicative adjustment of class probability: APM (adjusted probability model) |
| CN103262069A (en) * | 2010-12-21 | 2013-08-21 | 国际商业机器公司 | Method and system for predictive modeling |
| CN103439933A (en) * | 2013-08-13 | 2013-12-11 | 清华大学 | System and method for production process self-adaption monitoring using OCSVM |
| US20170360377A1 (en) * | 2016-05-31 | 2017-12-21 | Stmicroelectronics S.R.L. | Method for the detecting electrocardiogram anomalies and corresponding system |
| CN107705183A (en) * | 2017-09-30 | 2018-02-16 | 深圳乐信软件技术有限公司 | Recommendation method, apparatus, storage medium and the server of a kind of commodity |
| CN107797537A (en) * | 2017-11-10 | 2018-03-13 | 上海第二工业大学 | A kind of prognostic and health management method applied to automatic production line |
| CN108241343A (en) * | 2016-12-24 | 2018-07-03 | 青岛海尔模具有限公司 | A kind of intelligent plant management platform system |
-
2018
- 2018-08-27 CN CN201810978149.5A patent/CN109213034B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2002054654A2 (en) * | 2001-01-08 | 2002-07-11 | Vextec Corporation | Method and apparatus for predicting failure in a system |
| US7020593B2 (en) * | 2002-12-04 | 2006-03-28 | International Business Machines Corporation | Method for ensemble predictive modeling by multiplicative adjustment of class probability: APM (adjusted probability model) |
| CN103262069A (en) * | 2010-12-21 | 2013-08-21 | 国际商业机器公司 | Method and system for predictive modeling |
| CN103439933A (en) * | 2013-08-13 | 2013-12-11 | 清华大学 | System and method for production process self-adaption monitoring using OCSVM |
| US20170360377A1 (en) * | 2016-05-31 | 2017-12-21 | Stmicroelectronics S.R.L. | Method for the detecting electrocardiogram anomalies and corresponding system |
| CN108241343A (en) * | 2016-12-24 | 2018-07-03 | 青岛海尔模具有限公司 | A kind of intelligent plant management platform system |
| CN107705183A (en) * | 2017-09-30 | 2018-02-16 | 深圳乐信软件技术有限公司 | Recommendation method, apparatus, storage medium and the server of a kind of commodity |
| CN107797537A (en) * | 2017-11-10 | 2018-03-13 | 上海第二工业大学 | A kind of prognostic and health management method applied to automatic production line |
Non-Patent Citations (1)
| Title |
|---|
| 李城梁: "基于One-Class AVM的机载塔康测距信息异常监测方法研究", 《现代导航》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110262950A (en) * | 2019-05-21 | 2019-09-20 | 阿里巴巴集团控股有限公司 | Abnormal movement detection method and device based on many index |
| CN111310697A (en) * | 2020-02-17 | 2020-06-19 | 硕橙（厦门）科技有限公司 | Equipment operation period detection and health degree analysis method and device and storage medium |
| CN111310697B (en) * | 2020-02-17 | 2023-03-24 | 硕橙（厦门）科技有限公司 | Equipment operation period detection and health degree analysis method and device and storage medium |
| CN113008494A (en) * | 2021-02-01 | 2021-06-22 | 上海盛磊信息科技有限公司 | Radome structure health degree monitoring equipment and monitoring method based on deep learning |
| CN115270993A (en) * | 2022-08-23 | 2022-11-01 | 南通思诺船舶科技有限公司 | Diesel engine unit state detection method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109213034B (en) | 2020-04-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109213034A (en) | Equipment health degree monitoring method, device, computer equipment and readable storage medium storing program for executing | |
| CN103412542B (en) | A kind of integrated circuit technology unit exception early warning technology method of data-driven | |
| EP3665462B1 (en) | Identification of air leaks in a compressed air system using a plurality of current measurement sensors | |
| CN111898443B (en) | Flow monitoring method for wire feeding mechanism of FDM type 3D printer | |
| CN111174370A (en) | Fault detection method and device, storage medium and electronic device | |
| CN103750552A (en) | Intelligent sampling method and application of method in cigarette quality control | |
| CN116842348B (en) | Bridge health monitoring system based on artificial intelligence | |
| CN110347569A (en) | A kind of performance data of server acquisition method and device | |
| CN111580411A (en) | Control parameter optimization method, device and system | |
| CN112362304B (en) | Method for identifying target optical cable in multiple optical cables and corresponding system | |
| CN109598309B (en) | Detection system and monitoring method of metal packaging punching machine | |
| CN113343361A (en) | Intelligent monitoring method, device and equipment for vehicle body size and storage medium | |
| CN106844170A (en) | A kind of troubleshooting, the influence face method and apparatus of analysis failure | |
| CN116578486A (en) | Intelligent manufacturing industrial software debugging system based on cloud computing | |
| CN115562163A (en) | Parameter data real-time monitoring system based on numerical control machine tool | |
| CN111198979A (en) | Method and system for cleaning big data for power transmission and transformation reliability evaluation | |
| CN109460863A (en) | Equipment state prediction method based on deep learning | |
| CN116723138B (en) | Abnormal flow monitoring method and system based on flow probe dyeing | |
| CN116975938A (en) | Sensor data processing method in product manufacturing process | |
| CN116910117A (en) | Multi-dimensional high-calculation-force microclimate sensor data analysis system and method | |
| US20220309061A1 (en) | Mining machine management method and system | |
| CN112084093B (en) | Energy consumption control device, method and equipment of server | |
| CN113285847A (en) | Communication network anomaly detection method and system of intelligent converter station monitoring system | |
| CN114626758A (en) | Effect evaluation system for medical equipment maintenance | |
| CN114037010A (en) | Method and device for identifying abnormal electric quantity data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Yang Zongtou Inventor after: Tian Wenjing Inventor after: Tan Yi Inventor after: Zhuang Yan Inventor after: Chen Rui Inventor after: Huang Zhaoxian Inventor after: Wang Yougan Inventor after: Li Bohan Inventor before: Yang Zongtou Inventor before: Tian Wenjing Inventor before: Tan Yi Inventor before: Zhuang Yan Inventor before: Chen Rui Inventor before: Huang Zhaoxian Inventor before: Wang Yougan |