CN109614911A - Spinning machine failure prediction method, device and server - Google Patents
Spinning machine failure prediction method, device and server Download PDFInfo
- Publication number
- CN109614911A CN109614911A CN201811473882.8A CN201811473882A CN109614911A CN 109614911 A CN109614911 A CN 109614911A CN 201811473882 A CN201811473882 A CN 201811473882A CN 109614911 A CN109614911 A CN 109614911A
- Authority
- CN
- China
- Prior art keywords
- spinning machine
- image
- failure
- prediction model
- presumptive area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- D—TEXTILES; PAPER
- D01—NATURAL OR MAN-MADE THREADS OR FIBRES; SPINNING
- D01D—MECHANICAL METHODS OR APPARATUS IN THE MANUFACTURE OF ARTIFICIAL FILAMENTS, THREADS, FIBRES, BRISTLES OR RIBBONS
- D01D13/00—Complete machines for producing artificial threads
- D01D13/02—Elements of machines in combination
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/06—Recognition of objects for industrial automation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Mechanical Engineering (AREA)
- Textile Engineering (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
It includes: to establish primary fault prediction model according to the historical failure information of spinning machine that the present invention, which provides a kind of spinning machine failure prediction method, device and server, the spinning machine failure prediction method,；History image before obtaining the failure of spinning machine presumptive area, and using the history image before failure as input, corresponding failure occurs mark and is trained as output to fault prediction model, fault prediction model after being trained；When predicting spinning machine failure, by fault prediction model after the image input training of the spinning machine presumptive area before prediction, it is analyzed using image of the fault prediction model after training to the spinning machine presumptive area before prediction, predicts whether spinning machine can break down based on the analysis results.Spinning machine failure prediction method of the invention can predict the failure of spinning machine according to the history image of spinning machine presumptive area, so that spinning machine maintenance personnel be allow to carry out maintenance work in advance, safeguard the spinning machine of failure in time, reduce the loss of failure bring.
Description
Technical field
The present invention relates to industrial spinning technical field, in particular to a kind of spinning machine failure prediction method, device,
Server and computer storage medium.
Background technique
Currently, the failure of spinning machine is typically monitored by artificial mode in spinning workshop, or
Special hardware photoelectric sensor is installed in the downstream that spinning machine goes out silk thread or mechanical inductor carries out the monitoring of silk thread quality, from
And failure is monitored.
But there is no a kind of effective ways for predicting spinning machine failure, only after spinning machine breaks down, safeguard people
Member just may know that the generation of failure, therefore cannot exclude the failure of spinning machine in time, and certain loss is brought to production process.
Summary of the invention
In view of the above problems, the present invention provides a kind of spinning machine failure prediction method, device, server and computers to deposit
Storage media safeguards the spinning machine of failure so that spinning machine maintenance personnel can carry out maintenance work in advance in time, reduces failure band
The loss come.
To achieve the goals above, the present invention adopts the following technical scheme that:
A kind of spinning machine failure prediction method, comprising:
Primary fault prediction model is established according to the historical failure information of spinning machine；
History image before obtaining the failure of the spinning machine presumptive area, and using the history image before the failure as
Input, corresponding failure occur mark and are trained as output to the fault prediction model, failure predication mould after being trained
Type；
When predicting spinning machine failure, by failure after the image input training of the spinning machine presumptive area before prediction
Prediction model is analyzed using image of the fault prediction model after the training to the spinning machine presumptive area before prediction,
Whether prediction spinning machine can break down based on the analysis results.
Preferably, the spinning machine failure prediction method, further includes:
Using the history image of the spinning machine presumptive area for the random times not broken down as input, corresponding event
Mark does not occur and is trained as output to the fault prediction model for barrier.
Preferably, described " image of the spinning machine presumptive area before prediction to be inputted into failure predication mould after the training
Type is analyzed using image of the fault prediction model after the training to the spinning machine presumptive area before prediction, according to point
Whether analysis prediction of result spinning machine can break down " include:
The image for obtaining the spinning machine presumptive area before the prediction, to the spinning machine presumptive area before the prediction
Image pre-processed, generate pretreatment image；
By fault prediction model after the pretreatment image input training, fault prediction model after the training is utilized
The pretreatment image is analyzed, obtains the output of respective identification based on the analysis results.
Preferably, described " image of the spinning machine presumptive area before the prediction to be obtained, to the spinning before the prediction
The image of silk machine presumptive area is pre-processed, and pretreatment image is generated " include:
Obtain the image of the spinning machine presumptive area before the prediction；
According to preset frame number interval and/or time interval, to the image of the spinning machine presumptive area before the prediction
Frame sampling is carried out, at least one frame sampling image is obtained；
At least one described frame sampling image is spliced according to preset rules, generates the pretreatment image.
Preferably, the fault prediction model includes convolutional neural networks and deep learning model.
The present invention also provides a kind of spinning machine fault prediction devices, comprising:
Prediction model establishes module, for establishing primary fault prediction model according to the historical failure information of spinning machine；
Prediction model training module, the history image before failure for obtaining the spinning machine presumptive area, and by institute
As input, corresponding failure occurs mark and instructs as output to the fault prediction model history image before stating failure
Practice, fault prediction model after being trained；
Failure predication module is used for when predicting spinning machine failure, by the image of the spinning machine presumptive area before prediction
Fault prediction model after the training is inputted, using fault prediction model after the training to the spinning machine fate before prediction
The image in domain is analyzed, and predicts whether spinning machine can break down based on the analysis results.
Preferably, the spinning machine fault prediction device, further includes:
Non- failure training module, the history for the spinning machine presumptive area using the random times not broken down
As input, mark does not occur and is trained as output to the fault prediction model image for corresponding failure.
Preferably, the failure predication module includes:
Image pre-processing unit, for obtaining the image of the spinning machine presumptive area before the prediction, to the prediction
The image of spinning machine presumptive area before is pre-processed, and pretreatment image is generated；
Failure predication unit, for the pretreatment image to be inputted fault prediction model after the training, using described
Fault prediction model analyzes the pretreatment image after training, obtains the output of respective identification based on the analysis results.
The present invention also provides a kind of server, including memory and processor, the memory is for storing computer
Program, the processor runs the computer program so that the server executes the spinning machine failure prediction method.
The present invention also provides a kind of computer storage medium, it is stored with computer journey used in the server
Sequence.
The present invention provides a kind of spinning machine failure prediction method, which includes: according to spinning machine
Historical failure information establish primary fault prediction model；History image before obtaining the failure of the spinning machine presumptive area,
And using the history image before the failure as input, corresponding failure occur mark as output to the fault prediction model into
Row training, fault prediction model after being trained；When predicting spinning machine failure, by the spinning machine presumptive area before prediction
Image inputs fault prediction model after the training, pre- to the spinning machine before prediction using fault prediction model after the training
The image for determining region is analyzed, and predicts whether spinning machine can break down based on the analysis results.Spinning machine failure of the invention
Prediction technique can predict the failure of spinning machine according to the history image of spinning machine presumptive area, so that spinning machine be made to safeguard people
Member can carry out maintenance work in advance, safeguard the spinning machine of failure in time, reduce the loss of failure bring.
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 the scope of the invention.
Fig. 1 is a kind of flow chart for spinning machine failure prediction method that the embodiment of the present invention 1 provides；
Fig. 2 is a kind of flow chart for spinning machine failure prediction method that the embodiment of the present invention 2 provides；
Fig. 3 is a kind of prediction failure flow chart for spinning machine failure prediction method that the embodiment of the present invention 3 provides；
Fig. 4 is a kind of image preprocessing flow chart for spinning machine failure prediction method that the embodiment of the present invention 3 provides；
Fig. 5 is a kind of structural schematic diagram for spinning machine fault prediction device that the embodiment of the present invention 4 provides；
Fig. 6 is the structural schematic diagram for another spinning machine fault prediction device that the embodiment of the present invention 4 provides；
Fig. 7 is that a kind of structure of the failure predication module for spinning machine fault prediction device that the embodiment of the present invention 4 provides is shown
It is intended to.
Specific embodiment
Below in conjunction with attached drawing in the embodiment of the present invention, technical solution in the embodiment of the present invention carries out clear, complete
Ground description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.Usually exist
The component of the embodiment of the present invention described and illustrated in attached drawing can be arranged and be designed with a variety of different configurations herein.Cause
This, is not intended to limit claimed invention to the detailed description of the embodiment of the present invention provided in the accompanying drawings below
Range, but it is merely representative of selected embodiment of the invention.Based on the embodiment of the present invention, those skilled in the art are not doing
Every other embodiment obtained under the premise of creative work out, shall fall within the protection scope of the present invention.
Embodiment 1
Fig. 1 is a kind of flow chart for spinning machine failure prediction method that the embodiment of the present invention 1 provides, and this method includes as follows
Step:
Step S11: primary fault prediction model is established according to the historical failure information of spinning machine.
In the embodiment of the present invention, it is pre- initial failure can be established according to the historical failure information of spinning machine in the server
Survey model.Wherein, which can be uploaded in server by staff, which includes to spin
The parameter etc. that spinning machine exports after the image of predeterminable area and failure when silk machine failure.The server also can connect the spinning
Silk machine receives the parameter of spinning machine output, and the sensor that connection is arranged on spinning machine, benefit when spinning machine breaks down
Information etc. when with sensor acquisition spinning machine failure.
In the embodiment of the present invention, which includes convolutional neural networks and deep learning model.That is, the event
Barrier prediction model can be made of convolutional neural networks and deep learning model, and the input terminal of the prediction model connects convolution mind
Through network, convolutional neural networks obtain image by input terminal and carry out process of convolution, extract the feature of image, and the image is special
The deep learning model that sign is transmitted to connection is trained and analyzes, and finally exports result from output end.
Step S12: obtain spinning machine presumptive area failure before history image, and using the history image before failure as
Input, corresponding failure occur mark and are trained as output to fault prediction model, fault prediction model after being trained.
In the embodiment of the present invention, which is also connected with camera, which is arranged in spinning machine presumptive area,
The image of spinning machine presumptive area is obtained in real time, and image is stored in the server.After server fail, work
Personnel can obtain the fault history image of failure for the previous period from the image that server saves, and the image is inputted event
It is trained in barrier prediction model.Wherein, the process of the acquisition historical failure image can also be realized by application program, example
It can such as be provided with application program in the server, when spinning machine breaks down, failure can be obtained by the application program
One section of image of the preset time of preceding predeterminable area, and the image is input to fault prediction model and is trained.
In the embodiment of the present invention, it is input in fault prediction model is trained using historical failure image in the server
When, correspondingly the output of the fault prediction model should be spinning machine and break down, therefore be trained to fault prediction model
During, it is also necessary to mark is occurred into for failure as the output of the fault prediction model and is trained.
Step S13: when predicting spinning machine failure, after the image input training of the spinning machine presumptive area before prediction
Fault prediction model is analyzed using image of the fault prediction model after training to the spinning machine presumptive area before prediction,
Whether prediction spinning machine can break down based on the analysis results.
In the embodiment of the present invention, when predicting the failure of spinning machine, which can use camera and obtains prediction
The image of preceding spinning machine presumptive area is input in the fault prediction model after the training.Wherein, the image of the presumptive area can
To be the image of a period of time, to obtain the failure predication result of the presumptive area after a period of time.It is also possible to be continuous
The image of time is input in the fault prediction model and carries out continuous failure predication.
Embodiment 2
Fig. 2 is a kind of flow chart for spinning machine failure prediction method that the embodiment of the present invention 2 provides, and this method includes as follows
Step:
Step S21: primary fault prediction model is established according to the historical failure information of spinning machine.
This step is consistent with above-mentioned steps S11, and details are not described herein.
Step S22: obtain spinning machine presumptive area failure before history image, and using the history image before failure as
Input, corresponding failure occur mark and are trained as output to fault prediction model, fault prediction model after being trained.
This step is consistent with above-mentioned steps S12, and details are not described herein.
Step S23: using the history image of the spinning machine presumptive area for the random times not broken down as input, phase
It answers failure that mark does not occur to be trained fault prediction model as output.
In the embodiment of the present invention, during fault prediction model is trained, which can also utilize and not send out
The spinning machine presumptive area history image of the random times of raw failure is trained the fault prediction model as input.?
When inputting input of the history image not broken down as prediction model training, failure can also to that mark do not occur simultaneously and made
Fault prediction model is trained for output.It is instruction that mark, which does not occur, for the above-mentioned history image not broken down and failure
Multiple and different negative samples can be used before fault prediction model formally is used to carry out failure predication in the negative sample for practicing model
It is trained, to improve the accuracy of prediction failure.
Step S24: when predicting spinning machine failure, after the image input training of the spinning machine presumptive area before prediction
Fault prediction model is analyzed using image of the fault prediction model after training to the spinning machine presumptive area before prediction,
Whether prediction spinning machine can break down based on the analysis results.
This step is consistent with above-mentioned steps S13, and details are not described herein.
Embodiment 3
Fig. 3 is a kind of prediction failure flow chart for spinning machine failure prediction method that the embodiment of the present invention 3 provides, including such as
Lower step:
Step S31: the image of the spinning machine presumptive area before prediction is obtained, to the spinning machine presumptive area before prediction
Image pre-processed, generate pretreatment image.
It, can be to this after which obtains the image of the spinning machine presumptive area before prediction in the embodiment of the present invention
Image is pre-processed, and pretreatment image is generated, and carries out failure predication so that fault prediction model can preferably extract feature.
Wherein, which can be realized with used application program or algorithm, such as can be provided with pretreatment in the server
Program can use the preprocessor and carry out to the image after the image of the spinning machine presumptive area before obtaining prediction
Pretreatment.
Step S32: by fault prediction model after pretreatment image input training, using fault prediction model after training to pre-
Processing image is analyzed, and obtains the output of respective identification based on the analysis results.
In the embodiment of the present invention, the pretreatment image obtained after being pre-processed can be directly inputted into the failure after training
In prediction model, the final output for obtaining respective identification, wherein the mark of output can be respectively that mark and failure occur for failure
It does not identify, respectively indicates and predict that the spinning machine can break down, and predict that the spinning machine will not break down.
Fig. 4 is a kind of image preprocessing flow chart for spinning machine failure prediction method that the embodiment of the present invention 3 provides, including
Following steps:
Step S41: the image of the spinning machine presumptive area before prediction is obtained.
Step S42: according to preset frame number interval and/or time interval, to the spinning machine presumptive area before prediction
Image carries out frame sampling, obtains at least one frame sampling image.
In the embodiment of the present invention, in the preprocessing process of image, frame sampling processing can be carried out to the image, it can be pre-
If time interval abstract image preset quantity picture frame, such as can be every in the image of the spinning machine predeterminable area of acquisition
Every 2 picture frames of extraction in 20 seconds.It is also possible in the picture frame of preset frame number interval abstract image preset quantity, such as
2 picture frames can be extracted every 100 frames in the image of the spinning machine predeterminable area of acquisition.
In the embodiment of the present invention, the process of above-mentioned frame sampling can use algorithm or application program to realize, such as can be with
It is provided with application program in the server, the image for the spinning machine predeterminable area that will acquire carries out frame using the sampling application program
Sampling.Wherein, the algorithm of the carry out frame sampling or application program can also be arranged in camera, and camera acquires realtime graphic
Real-time frame sampling is carried out using the algorithm or application program afterwards.
Step S43: at least one frame sampling image is spliced according to preset rules, generates pretreatment image.
It, can also be according to default rule after carrying out frame sampling and obtaining at least one frame sampling image in the embodiment of the present invention
Splicing then is carried out at least one frame sampling image using algorithm or application program, generates pretreatment image.Wherein, this is pre-
If rule is image mosaic rule, with multiple images are spliced into an image according to certain rules, such as can be
16 images are spliced into an image according to level matrix distribution.Above-mentioned stitching algorithm or application program, which can be set, to image
In machine or server, here without limitation.Finally, less pre- place can be generated after carrying out splicing in multiple frame sampling images
Manage image.
In the embodiment of the present invention, by above-mentioned frame sampling and the image pre-processing method of image mosaic, can effectively it subtract
Few image carries out the time of convolution by convolutional neural networks model, to improve the efficiency of prediction.
Embodiment 4
Fig. 5 is a kind of structural schematic diagram for spinning machine fault prediction device that the embodiment of the present invention 4 provides.
The spinning machine fault prediction device 500 includes:
Prediction model establishes module 510, for establishing primary fault prediction model according to the historical failure information of spinning machine.
Prediction model training module 520, the history image before failure for obtaining the spinning machine presumptive area, and will
As input, corresponding failure occurs mark and instructs as output to the fault prediction model history image before the failure
Practice, fault prediction model after being trained.
Failure predication module 530 is used for when predicting spinning machine failure, by the figure of the spinning machine presumptive area before prediction
It is predetermined to the spinning machine before prediction using fault prediction model after the training as fault prediction model after the input training
The image in region is analyzed, and predicts whether spinning machine can break down based on the analysis results.
As shown in fig. 6, the spinning machine fault prediction device 500 further include:
Non- failure training module 540, for the spinning machine presumptive area using the random times not broken down
As input, mark does not occur and is trained as output to the fault prediction model history image for corresponding failure.
As shown in fig. 7, the failure predication module 530 includes:
Image pre-processing unit 531, for obtaining the image of the spinning machine presumptive area before the prediction, to described pre-
The image of spinning machine presumptive area before survey is pre-processed, and pretreatment image is generated.
Failure predication unit 532, for utilizing institute for fault prediction model after the pretreatment image input training
Fault prediction model analyzes the pretreatment image after stating training, obtains the output of respective identification based on the analysis results.
In the embodiment of the present invention, above-mentioned modules and the more detailed function description of each unit can refer to aforementioned reality
The content of corresponding portion in example is applied, details are not described herein.
In addition, the server includes memory and processor the present invention also provides a kind of server, memory can be used for
Computer program is stored, processor is by running the computer program, so that server be made to execute the above method or above-mentioned
The function of modules in spinning machine fault prediction device.
Memory may include storing program area and storage data area, wherein storing program area can storage program area, at least
Application program needed for one function (such as sound-playing function, image player function etc.) etc.；Storage data area can store root
Created data (such as audio data, phone directory etc.) etc. are used according to server.In addition, memory may include high speed with
Machine access memory, can also include nonvolatile memory, a for example, at least disk memory, flush memory device or its
His volatile solid-state part.
The present embodiment additionally provides a kind of computer storage medium, for storing computer journey used in above-mentioned server
Sequence.
In several embodiments provided herein, it should be understood that disclosed device and method can also pass through
Other modes are realized.The apparatus embodiments described above are merely exemplary, for example, flow chart and structure in attached drawing
Figure shows the system frame in the cards of the device of multiple embodiments according to the present invention, method and computer program product
Structure, function and operation.In this regard, each box in flowchart or block diagram can represent a module, section or code
A part, a part of the module, section or code includes one or more for implementing the specified logical function
Executable instruction.It should also be noted that function marked in the box can also be to be different from the implementation as replacement
The sequence marked in attached drawing occurs.For example, two continuous boxes can actually be basically executed in parallel, they are sometimes
It can execute in the opposite order, this depends on the function involved.It is also noted that in structure chart and/or flow chart
The combination of each box and the box in structure chart and/or flow chart, can function or movement as defined in executing it is dedicated
Hardware based system realize, or can realize using a combination of dedicated hardware and computer instructions.
In addition, each functional module or unit in each embodiment of the present invention can integrate one independence of formation together
Part, be also possible to modules individualism, an independent part can also be integrated to form with two or more modules.
It, can be with if the function is realized and when sold or used as an independent product in the form of software function module
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 intelligence
Can mobile phone, personal computer, server or network equipment etc.) execute each embodiment the method for the present invention whole or
Part steps.And storage medium above-mentioned include: USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory),
Random access memory (RAM, Random Access Memory), magnetic or disk etc. be various to can store program code
Medium.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can easily think of the change or the replacement, and should all contain
Lid is within protection scope of the present invention.Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. a kind of spinning machine failure prediction method characterized by comprising
Primary fault prediction model is established according to the historical failure information of spinning machine；
History image before obtaining the failure of the spinning machine presumptive area, and using the history image before the failure as defeated
Enter, corresponding failure occurs mark and is trained as output to the fault prediction model, fault prediction model after being trained；
When predicting spinning machine failure, by failure predication after the image input training of the spinning machine presumptive area before prediction
Model is analyzed using image of the fault prediction model after the training to the spinning machine presumptive area before prediction, according to
Whether analysis prediction of result spinning machine can break down.
2. spinning machine failure prediction method according to claim 1, which is characterized in that further include:
Using the history image of the spinning machine presumptive area for the random times not broken down as input, corresponding failure is not
Mark occurs to be trained the fault prediction model as output.
3. spinning machine failure prediction method according to claim 1, which is characterized in that described " by the spinning before prediction
The image of machine presumptive area inputs fault prediction model after the training, using fault prediction model after the training to prediction
The image of preceding spinning machine presumptive area is analyzed, and predicts whether spinning machine can break down based on the analysis results " include:
The image for obtaining the spinning machine presumptive area before the prediction, to the figure of the spinning machine presumptive area before the prediction
As being pre-processed, pretreatment image is generated；
By fault prediction model after the pretreatment image input training, using fault prediction model after the training to institute
It states pretreatment image to be analyzed, obtains the output of respective identification based on the analysis results.
4. spinning machine failure prediction method according to claim 3, which is characterized in that described " before obtaining the prediction
Spinning machine presumptive area image, the image of the spinning machine presumptive area before the prediction is pre-processed, is generated pre-
Handle image " include:
Obtain the image of the spinning machine presumptive area before the prediction；
According to preset frame number interval and/or time interval, the image of the spinning machine presumptive area before the prediction is carried out
Frame sampling obtains at least one frame sampling image；
At least one described frame sampling image is spliced according to preset rules, generates the pretreatment image.
5. spinning machine failure prediction method according to claim 1, which is characterized in that the fault prediction model includes volume
Product neural network and deep learning model.
6. a kind of spinning machine fault prediction device characterized by comprising
Prediction model establishes module, for establishing primary fault prediction model according to the historical failure information of spinning machine；
Prediction model training module, the history image before failure for obtaining the spinning machine presumptive area, and will the event
As input, corresponding failure occurs mark and is trained as output to the fault prediction model history image before barrier, obtains
Fault prediction model after must training；
Failure predication module, for when predicting spinning machine failure, the image of the spinning machine presumptive area before prediction to be inputted
Fault prediction model after the training, using fault prediction model after the training to the spinning machine presumptive area before prediction
Image is analyzed, and predicts whether spinning machine can break down based on the analysis results.
7. spinning machine fault prediction device according to claim 6, which is characterized in that further include:
Non- failure training module, the history image for the spinning machine presumptive area using the random times not broken down
As input, mark does not occur and is trained as output to the fault prediction model for corresponding failure.
8. spinning machine fault prediction device according to claim 6, which is characterized in that the failure predication module includes:
Image pre-processing unit, for obtaining the image of the spinning machine presumptive area before the prediction, before the prediction
The image of spinning machine presumptive area pre-processed, generate pretreatment image；
Failure predication unit, for utilizing the training for fault prediction model after the pretreatment image input training
Fault prediction model analyzes the pretreatment image afterwards, obtains the output of respective identification based on the analysis results.
9. a kind of server, which is characterized in that including memory and processor, the memory is for storing computer journey
Sequence, the processor runs the computer program so that the server executes according to claim 1 to described in any one of 5
Spinning machine failure prediction method.
10. a kind of computer storage medium, which is characterized in that it is stored with used in server as claimed in claim 9
Computer program.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811473882.8A CN109614911A (en) | 2018-12-04 | 2018-12-04 | Spinning machine failure prediction method, device and server |
| CN201910602467.6A CN110175659B (en) | 2018-12-04 | 2019-07-05 | Spinning machine fault monitoring method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811473882.8A CN109614911A (en) | 2018-12-04 | 2018-12-04 | Spinning machine failure prediction method, device and server |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109614911A true CN109614911A (en) | 2019-04-12 |
Family
ID=66005905
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811473882.8A Pending CN109614911A (en) | 2018-12-04 | 2018-12-04 | Spinning machine failure prediction method, device and server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109614911A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115130702A (en) * | 2022-09-02 | 2022-09-30 | 山东汇泓纺织科技有限公司 | Textile machine fault prediction system based on big data analysis |
-
2018
- 2018-12-04 CN CN201811473882.8A patent/CN109614911A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115130702A (en) * | 2022-09-02 | 2022-09-30 | 山东汇泓纺织科技有限公司 | Textile machine fault prediction system based on big data analysis |
| CN115130702B (en) * | 2022-09-02 | 2022-12-02 | 山东汇泓纺织科技有限公司 | Textile machine fault prediction system based on big data analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108229321B (en) | Face recognition model, and training method, device, apparatus, program, and medium therefor | |
| CN111368089B (en) | Business processing method and device based on knowledge graph | |
| CN110622176A (en) | Video partitioning | |
| CN110059761A (en) | A kind of human body behavior prediction method and device | |
| CN107688795A (en) | A kind of monitoring method and terminal of power system video image | |
| US20200082199A1 (en) | Method and apparatus for inspecting burrs of electrode slice | |
| CN109580004A (en) | A kind of temperature checking method and device | |
| CN109544549A (en) | Spinning machine fault monitoring method, device and server | |
| CN116055690B (en) | Method and equipment for processing machine room monitoring video | |
| CN109803112A (en) | Video analysis management method based on big data, apparatus and system, storage medium | |
| CN113691733A (en) | Video jitter detection method and device, electronic equipment and storage medium | |
| CN114998830A (en) | Wearing detection method and system for safety helmet of transformer substation personnel | |
| CN109614911A (en) | Spinning machine failure prediction method, device and server | |
| CN114238402A (en) | Alarm data processing method and device, storage medium and electronic equipment | |
| CN112633100B (en) | Behavior recognition method, behavior recognition device, electronic equipment and storage medium | |
| CN116823233B (en) | User data processing method and system based on full-period operation and maintenance | |
| CN109615000A (en) | Fault recognition method, device and server | |
| CN116189063B (en) | Key frame optimization method and device for intelligent video monitoring | |
| CN107844777B (en) | Method and apparatus for generating information | |
| CN117056728A (en) | Time sequence generation method, device, equipment and storage medium | |
| CN112153076A (en) | Computer network safety intrusion detection system | |
| CN109063854A (en) | Intelligent O&M cloud platform system and its control method | |
| CN116248346A (en) | Smart city-oriented CPS network security situation awareness establishing method and system | |
| CN115424253A (en) | License plate recognition method and device, electronic equipment and storage medium | |
| CN111061815B (en) | Session data classification method |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190412 |