CN110362068A - A kind of mechanical equipment fault method for early warning, system and readable storage medium storing program for executing based on industrial Internet of Things - Google Patents
A kind of mechanical equipment fault method for early warning, system and readable storage medium storing program for executing based on industrial Internet of Things Download PDFInfo
- Publication number
- CN110362068A CN110362068A CN201910712301.XA CN201910712301A CN110362068A CN 110362068 A CN110362068 A CN 110362068A CN 201910712301 A CN201910712301 A CN 201910712301A CN 110362068 A CN110362068 A CN 110362068A
- Authority
- CN
- China
- Prior art keywords
- mechanical equipment
- early warning
- data
- model
- industrial internet
- 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.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0243—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults model based detection method, e.g. first-principles knowledge model
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/24—Pc safety
- G05B2219/24065—Real time diagnostics
Abstract
The invention discloses a kind of mechanical equipment fault method for early warning, system and readable storage medium storing program for executing based on industrial Internet of Things, it the described method comprises the following steps: sensing node collection machinery device status data, the mechanical equipment state data are transmitted to data gateway and do anticipation processing, if Current mechanical device status data and preset standard status data absolute value of the difference are greater than preset threshold, mechanical equipment state data are uploaded to Cloud Server;The Cloud Server carries out early warning diagnosis using classification fault model to characteristic value is extracted after mechanical equipment state data prediction, by characteristic value data, obtains diagnostic result.A kind of mechanical equipment fault method for early warning, system and readable storage medium storing program for executing based on industrial Internet of Things disclosed by the invention, pass through collection machinery device status data, anticipation processing is carried out using data gateway, abnormality data are uploaded into Cloud Server, using the accurate early warning of preset classification fault model, the accuracy rate of mechanical equipment fault early warning diagnosis is improved.
Description
Technical field
The present invention relates to mechanical equipments to monitor field, more particularly to a kind of mechanical equipment based on industrial Internet of Things
Fault early warning method, system and readable storage medium storing program for executing.
Background technique
With the continuous development of modern industrial technology, plant-scale continuous increase, industrial machinery is applied to various industry
It is generally live that scene becomes industry, such as in many process industry industries, and big mechanical equipment has been widely cited entire to support
Process flow it is normal, run at high speed.Mechanical equipment once breaks down, and not only brings economic loss, is more likely to jeopardize the person
Safety, causes serious harm and influence, thus it is guaranteed that after the operating of mechanical equipment health and equipment break down, even if inspection
It surveys and repairs and be all important
As computer technology is deepened constantly what real-time monitoring and diagnostic field were applied, it is by the expert in knowledge based library
System technology is applied to diagnosis early warning field and has become important directions of diagnostic techniques, but traditional early warning diagnostic method,
Low efficiency, low precision can not provide accurately reference to operation maintenance personnel.
Summary of the invention
In order to solve at least one above-mentioned technical problem, the invention proposes a kind of mechanical equipments based on industrial Internet of Things
Fault early warning method, system and readable storage medium storing program for executing.
In order to solve the above technical problems, first aspect present invention discloses a kind of machinery based on industrial Internet of Things and sets
Standby fault early warning method, which comprises
Sensing node collection machinery device status data, by the mechanical equipment state data be transmitted to data gateway do it is pre-
Reason is sentenced, it is mechanical if Current mechanical device status data and preset standard status data absolute value of the difference are greater than preset threshold
Device status data is uploaded to Cloud Server;
The Cloud Server utilizes classification to characteristic value is extracted after mechanical equipment state data prediction, by characteristic value data
Fault model carries out early warning diagnosis, obtains diagnostic result.
In the present solution, if the mechanical equipment state value and preset standard state value absolute value of the difference of acquisition are less than default threshold
Value, then record current temporal instance t1, if after instant tl in preset period T, the mechanical equipment state value and pre-
It is marked with quasi- state value absolute value of the difference and is respectively less than preset threshold, then sampling rate adjusting is n times of current sampling frequency, continues to adopt
Sample T time section simultaneously does anticipation processing to the mechanical equipment state data of sampling.
In the present solution, the classification fault pre-alarming model includes: exception catching model, fault analysis model, fault diagnosis
Model;The exception catching model is used to catch the exception to after characteristic value data analysis to carry out status early warning;The failure
Analysis model after exception catching for carrying out failure reason analysis;The diagnostic model is for doing the result of accident analysis
It is out of order classification and last diagnostic.
In the present solution, faulty expert knowledge library is preset in the grading forewarning system model, the failure expert knowledge library base
It is obtained in historical failure data training.
It is obtained in the present solution, the classification fault model is based on the training of convolutional neural networks training pattern, training process
Specifically:
Step 1: obtaining the corresponding mechanical equipment state data of different faults, become after carrying out noise suppression preprocessing by Fourier
It changes and generates spectrogram and be divided into training sample and test sample in preset ratio;
Step 2: establishing convolutional neural networks model and initiation parameter, determine that network parameter, the network parameter include
Have: learning rate, the number of iterations;
Step 3: training sample being input in convolutional neural networks model, output valve and expectation are acquired by propagated forward
The error of value;
Step 4: judge whether convolutional neural networks model restrains, it is no to then follow the steps 5 if convergence thens follow the steps 6;
Step 5: backpropagation and weight modification, the error acquired step 4 using stochastic gradient descent algorithm reversely by
Es-region propagations update weight, repeat step 3 and arrive step 5, until convolutional neural networks model is restrained;
Step 6: judging whether convolutional neural networks model meets the requirements according to the accuracy of test sample, such as meet and execute
Step 7, step 2 is otherwise jumped to, network parameter is modified;
Step 7: the convolutional neural networks model that output training finishes is used for fault pre-alarming.
In the present solution, the loss function that the neural network model uses is cross entropy loss function, it is specific as follows:
Wherein, 1 { yi=j } it is indicative function, it indicates that the value in bracket be true duration is 1, be fictitious time value is 0;K is sample
Sum, C be sample classification number, yiIt is the true value of the i-th sample,It is the i-th sample prediction probability of all categories for jth.
In the present solution, neural network is in the training process, propagated forward calculates error amount, and error amount backpropagation updates
The more new formula of each layer of W and e, parameter are as follows:
Wherein, the learning rate of η convolutional neural networks.
Second aspect of the present invention discloses a kind of mechanical equipment fault early warning system based on industrial Internet of Things, including storage
Device and processor include the mechanical equipment fault method for early warning program based on industrial Internet of Things in the memory, described to be based on
The mechanical equipment fault method for early warning program of industrial Internet of Things realizes following steps when being executed by the processor:
Sensing node collection machinery device status data, by the mechanical equipment state data be transmitted to data gateway do it is pre-
Reason is sentenced, it is mechanical if Current mechanical device status data and preset standard status data absolute value of the difference are greater than preset threshold
Device status data is uploaded to Cloud Server;
The Cloud Server utilizes classification to characteristic value is extracted after mechanical equipment state data prediction, by characteristic value data
Fault model carries out early warning diagnosis, obtains diagnostic result.
In the present solution, if the mechanical equipment state value and preset standard state value absolute value of the difference of acquisition are less than default threshold
Value, then record current temporal instance t1, if after instant tl in preset period T, the mechanical equipment state value and pre-
It is marked with quasi- state value absolute value of the difference and is respectively less than preset threshold, then sampling rate adjusting is n times of current sampling frequency, continues to adopt
Sample T time section simultaneously does anticipation processing to the mechanical equipment state data of sampling.
Third aspect present invention discloses a kind of computer readable storage medium, wraps in the computer readable storage medium
Include a kind of mechanical equipment fault method for early warning program based on industrial Internet of Things of machine, it is described a kind of based on industrial Internet of Things
When mechanical equipment fault method for early warning program is executed by processor, realize as described above described in any item a kind of based on industrial Internet of Things
Mechanical equipment fault method for early warning the step of.
A kind of mechanical equipment fault method for early warning, system and readable storage medium based on industrial Internet of Things disclosed by the invention
Matter carries out anticipation processing using data gateway by collection machinery device status data, and abnormality data are uploaded cloud service
Device carries out accurate early warning using preset classification fault model, improves the accuracy rate of mechanical equipment fault early warning diagnosis.
Detailed description of the invention
Fig. 1 shows a kind of mechanical equipment fault early warning flow chart based on industrial Internet of Things of the present invention;
Fig. 2 shows convolutional neural networks model training flow charts;
Fig. 3 shows a kind of block diagram of the mechanical equipment fault early warning system based on industrial Internet of Things of the present invention.
Specific implementation method
To better understand the objects, features and advantages of the present invention, with reference to the accompanying drawing and specific real
Applying mode, the present invention is further described in detail.It should be noted that in the absence of conflict, the implementation of the application
Feature in example and embodiment can be combined with each other.
In the following description, numerous specific details are set forth in order to facilitate a full understanding of the present invention, still, the present invention may be used also
To be implemented using other than the one described here other modes, therefore, protection scope of the present invention is not by described below
Specific embodiment limitation.
Method of the invention is suitable for those mechanical equipments, such as engineering mechanical device, Workshop Production equipment, including but it is unlimited
In various gear-box, various rolling bearing, motor, compressor etc., certainly, the present invention is not intended to limit the type of device, any to adopt
It is fallen in the scope of the present invention with technical solution of the present invention.
Fig. 1 shows a kind of mechanical equipment fault method for early warning flow chart based on industrial Internet of Things of the present invention.
As shown in Figure 1, first aspect present invention discloses a kind of pre- police of the mechanical equipment fault based on industrial Internet of Things
Method, comprising:
A kind of mechanical equipment fault method for early warning based on industrial Internet of Things, which comprises
Sensing node collection machinery device status data, by the mechanical equipment state data be transmitted to data gateway do it is pre-
Reason is sentenced, it is mechanical if Current mechanical device status data and preset standard status data absolute value of the difference are greater than preset threshold
Device status data is uploaded to Cloud Server;
The Cloud Server utilizes classification to characteristic value is extracted after mechanical equipment state data prediction, by characteristic value data
Fault model carries out early warning diagnosis, obtains diagnostic result.
It should be noted that the setting of sensing node can be one or more in the present invention, the corresponding biography of sensing node
The type of sensor can be to be a variety of, such as vibrating sensor, pressure sensor, temperature sensor, the status data can be
The data of single sensing node acquisition, are also possible to the multidimensional data of the composition of a variety of sensing nodes.
The mechanical equipment state data for leading to sensing node acquisition in the present invention, are handled by the anticipation of data gateway, can be with
It avoids the status data of non-unusual service condition from uploading the problems such as occupying traditional bandwidth, bringing time delay and big volume of transmitted data, furthermore counts
It can saved in the set time period according to gateway, upload data in analyzing device inoperative period or idle period.
Explanation is needed further exist for, it is comprehensive to overcome traditional single failure model for the classification fault model in the present invention
The defect of judgement can do early warning for exception catching, accident analysis, fault diagnosis respectively, so that early warning is more rationally scientific.
In the present solution, if the mechanical equipment state value and preset standard state value absolute value of the difference of acquisition are less than default threshold
Value, then record current temporal instance t1, if after instant tl in preset period T, the mechanical equipment state value and pre-
It is marked with quasi- state value absolute value of the difference and is respectively less than preset threshold, then sampling rate adjusting is n times of current sampling frequency, continues to adopt
Sample T time section simultaneously does anticipation processing to the mechanical equipment state data of sampling.
It should be noted that if after instant tl in preset period T, the state value and preset standard state value
Difference be less than preset threshold, then be n times of current sampling frequency by sampling rate adjusting, continue sampling T time section and to sampling
Data do anticipation processing, can be to avoid certain low-frequency anomaly fault conditions by adjusting a sample frequency in preset time period
Can not status data the problem of being unable to get under former sample frequency.
In the present solution, the classification fault pre-alarming model includes: exception catching model, fault analysis model, fault diagnosis
Model;The exception catching model is used to catch the exception to after characteristic value data analysis to carry out status early warning;The failure
Analysis model after exception catching for carrying out failure reason analysis;The diagnostic model is for doing the result of accident analysis
It is out of order classification and last diagnostic.
It should be noted that classification fault model overcomes traditional comprehensive descision model, the defect of inaccurate inaccuracy.
In the present solution, faulty expert knowledge library is preset in the grading forewarning system model, the failure expert knowledge library base
It is obtained in historical failure data training.
It is obtained in the present solution, the classification fault model is based on the training of convolutional neural networks training pattern, training process
Specifically:
Fig. 2 shows convolutional neural networks model training flow charts.
As shown in Fig. 2, in the present solution, the classification fault model is based on, convolutional neural networks model is trained to be obtained,
Its training process specifically:
S202: obtaining the corresponding mechanical equipment state data of different faults, is become after carrying out noise suppression preprocessing by Fourier
It changes and generates spectrogram and be divided into training sample and test sample in preset ratio;
S204: convolutional neural networks model and initiation parameter are established, determines that network parameter, the network parameter include
Have: learning rate, the number of iterations;
S206: training sample is input in convolutional neural networks model, acquires output valve and expectation by propagated forward
The error of value;
S208: judging whether convolutional neural networks model restrains, no to then follow the steps if convergence thens follow the steps S212
S210;
S210: backpropagation and weight modification, the error for being acquired step S208 using stochastic gradient descent algorithm are reversed
It successively propagates, updates weight, repeat step S206 to step S210, until convolutional neural networks model is restrained;
S212: judging whether convolutional neural networks model meets the requirements according to the accuracy of test sample, such as meets and executes
Otherwise step S214 jumps to step S204, modify network parameter;
S2014: the convolutional neural networks model that output training finishes is used for fault pre-alarming.
In the present solution, the loss function that the neural network model uses is cross entropy loss function, it is specific as follows:
Wherein, 1 { yi=j } it is indicative function, it indicates that the value in bracket be true duration is 1, be fictitious time value is 0;K is sample
Sum, C be sample classification number, yiIt is the true value of the i-th sample,It is the i-th sample prediction probability of all categories for jth.
In the present solution, neural network is in the training process, propagated forward calculates error amount, and error amount backpropagation updates
The more new formula of each layer of W and e, parameter are as follows:
Wherein, the learning rate of η convolutional neural networks.
It should be noted that classification fault model can be trained using different neural networks, obtain different
Early warning judges precision.
Fig. 3 shows a kind of mechanical equipment fault early warning system block diagram based on industrial Internet of Things.
As shown in figure 3, second aspect of the present invention discloses a kind of mechanical equipment fault early warning system based on industrial Internet of Things
It unites, including memory 31 and processor 32, includes the pre- police of mechanical equipment fault based on industrial Internet of Things in the memory
Method program is realized as follows when the mechanical equipment fault method for early warning program based on industrial Internet of Things is executed by the processor
Step:
Sensing node collection machinery device status data, by the mechanical equipment state data be transmitted to data gateway do it is pre-
Reason is sentenced, it is mechanical if Current mechanical device status data and preset standard status data absolute value of the difference are greater than preset threshold
Device status data is uploaded to Cloud Server;
The Cloud Server utilizes classification to characteristic value is extracted after mechanical equipment state data prediction, by characteristic value data
Fault model carries out early warning diagnosis, obtains diagnostic result.
In the present solution, if the mechanical equipment state value and preset standard state value absolute value of the difference of acquisition are less than default threshold
Value, then record current temporal instance t1, if after instant tl in preset period T, the mechanical equipment state value and pre-
It is marked with quasi- state value absolute value of the difference and is respectively less than preset threshold, then sampling rate adjusting is n times of current sampling frequency, continues to adopt
Sample T time section simultaneously does anticipation processing to the mechanical equipment state data of sampling.
It should be noted that if after instant tl in preset period T, the state value and preset standard state value
Difference be less than preset threshold, then be n times of current sampling frequency by sampling rate adjusting, continue sampling T time section and to sampling
Data do anticipation processing, can be to avoid certain low-frequency anomaly fault conditions by adjusting a sample frequency in preset time period
Can not status data the problem of being unable to get under former sample frequency.
In the present solution, the classification fault pre-alarming model includes: exception catching model, fault analysis model, fault diagnosis
Model;The exception catching model is used to catch the exception to after characteristic value data analysis to carry out status early warning;The failure
Analysis model after exception catching for carrying out failure reason analysis;The diagnostic model is for doing the result of accident analysis
It is out of order classification and last diagnostic.
It should be noted that classification fault model overcomes traditional comprehensive descision model, the defect of inaccurate inaccuracy.
In the present solution, faulty expert knowledge library is preset in the grading forewarning system model, the failure expert knowledge library base
It is obtained in historical failure data training.
It is obtained in the present solution, the classification fault model is based on the training of convolutional neural networks training pattern, training process
Specifically:
Fig. 2 shows convolutional neural networks model training flow charts.
As shown in Fig. 2, in the present solution, the classification fault model is based on, convolutional neural networks model is trained to be obtained,
Its training process specifically:
S202: obtaining the corresponding mechanical equipment state data of different faults, is become after carrying out noise suppression preprocessing by Fourier
It changes and generates spectrogram and be divided into training sample and test sample in preset ratio;
S204: convolutional neural networks model and initiation parameter are established, determines that network parameter, the network parameter include
Have: learning rate, the number of iterations;
S206: training sample is input in convolutional neural networks model, acquires output valve and expectation by propagated forward
The error of value;
S208: judging whether convolutional neural networks model restrains, no to then follow the steps if convergence thens follow the steps S212
S210;
S210: backpropagation and weight modification, the error for being acquired step S208 using stochastic gradient descent algorithm are reversed
It successively propagates, updates weight, repeat step S206 to step S210, until convolutional neural networks model is restrained;
S212: judging whether convolutional neural networks model meets the requirements according to the accuracy of test sample, such as meets and executes
Otherwise step S214 jumps to step S204, modify network parameter;
S2014: the convolutional neural networks model that output training finishes is used for fault pre-alarming.
In the present solution, the loss function that the neural network model uses is cross entropy loss function, it is specific as follows:
Wherein, 1 { yi=j } it is indicative function, it indicates that the value in bracket be true duration is 1, be fictitious time value is 0;K is sample
Sum, C be sample classification number, yiIt is the true value of the i-th sample,It is the i-th sample prediction probability of all categories for jth.
In the present solution, neural network is in the training process, propagated forward calculates error amount, and error amount backpropagation updates
The more new formula of each layer of W and e, parameter are as follows:
Wherein, the learning rate of η convolutional neural networks.
It should be noted that classification fault model can be trained using different neural networks, obtain different
Early warning judges precision.
Third aspect present invention discloses a kind of computer readable storage medium, wraps in the computer readable storage medium
Include a kind of mechanical equipment fault method for early warning program based on industrial Internet of Things of machine, it is described a kind of based on industrial Internet of Things
When mechanical equipment fault method for early warning program is executed by processor, realize as described above described in any item a kind of based on industrial Internet of Things
Mechanical equipment fault method for early warning the step of.
A kind of mechanical equipment fault method for early warning, system and readable storage medium based on industrial Internet of Things disclosed by the invention
Matter carries out anticipation processing using data gateway by collection machinery device status data, and abnormality data are uploaded cloud service
Device carries out accurate early warning using preset classification fault model, improves the accuracy rate of mechanical equipment fault early warning diagnosis.
In several embodiments provided herein, it should be understood that disclosed device and method can pass through it
Its mode is realized.Apparatus embodiments described above are merely indicative, for example, the division of the unit, only
A kind of logical function partition, there may be another division manner in actual implementation, such as: multiple units or components can combine, or
It is desirably integrated into another system, or some features can be ignored or not executed.In addition, shown or discussed each composition portion
Mutual coupling or direct-coupling or communication connection is divided to can be through some interfaces, the INDIRECT COUPLING of equipment or unit
Or communication connection, it can be electrical, mechanical or other forms.
Above-mentioned unit as illustrated by the separation member, which can be or may not be, to be physically separated, aobvious as unit
The component shown can be or may not be physical unit;Both it can be located in one place, and may be distributed over multiple network lists
In member;Some or all of units can be selected to achieve the purpose of the solution of this embodiment according to the actual needs.
In addition, each functional unit in various embodiments of the present invention can be fully integrated in one processing unit, it can also
To be each unit individually as a unit, can also be integrated in one unit with two or more units;It is above-mentioned
Integrated unit both can take the form of hardware realization, can also realize in the form of hardware adds SFU software functional unit.
Those of ordinary skill in the art will appreciate that: realize that all or part of the steps of above method embodiment can pass through
The relevant hardware of program instruction is completed, and program above-mentioned can store in computer-readable storage medium, which exists
When execution, step including the steps of the foregoing method embodiments is executed;And storage medium above-mentioned includes: movable storage device, read-only deposits
Reservoir (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or
The various media that can store program code such as CD.
If alternatively, the above-mentioned integrated unit of the present invention is realized in the form of software function module and as independent product
When selling or using, it also can store in a computer readable storage medium.Based on this understanding, the present invention is implemented
Substantially the part that contributes to existing technology can be embodied in the form of software products the technical solution of example in other words,
The computer software product is stored in a storage medium, including some instructions are used so that computer equipment (can be with
It is personal computer, server or network equipment etc.) execute all or part of each embodiment the method for the present invention.
And storage medium above-mentioned includes: that movable storage device, ROM, RAM, magnetic or disk etc. are various 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, protection scope of the present invention should be based on the protection scope of the described claims.
Claims (10)
1. a kind of mechanical equipment fault method for early warning based on industrial Internet of Things, which is characterized in that the described method includes:
The mechanical equipment state data are transmitted to data gateway and do pre- sentence by sensing node collection machinery device status data
Reason, if Current mechanical device status data and preset standard status data absolute value of the difference are greater than preset threshold, mechanical equipment
Status data is uploaded to Cloud Server;
The Cloud Server utilizes classification failure to characteristic value is extracted after mechanical equipment state data prediction, by characteristic value data
Model carries out early warning diagnosis, obtains diagnostic result.
2. a kind of mechanical equipment fault method for early warning based on industrial Internet of Things according to claim 1, which is characterized in that
If the mechanical equipment state value and preset standard state value absolute value of the difference of acquisition are less than preset threshold, when recording current time
T1 is carved, if after instant tl in preset period T, the mechanical equipment state value is absolute with preset standard state value difference
Value is respectively less than preset threshold, then sampling rate adjusting is n times of current sampling frequency, continues to sample T time section and to sampling
Mechanical equipment state data do anticipation processing.
3. a kind of mechanical equipment fault method for early warning based on industrial Internet of Things according to claim 1, which is characterized in that
The classification fault pre-alarming model includes: exception catching model, fault analysis model, fault diagnosis model;The exception catching
Model is used to catch the exception to after characteristic value data analysis to carry out status early warning;The fault analysis model is used in exception
Failure reason analysis is carried out after capture;The diagnostic model is used to make failure modes to the result of accident analysis and finally examine
It is disconnected.
4. a kind of mechanical equipment fault method for early warning based on industrial Internet of Things according to claim 3, which is characterized in that
Faulty expert knowledge library is preset in the grading forewarning system model, the failure expert knowledge library is based on historical failure data training
It obtains.
5. a kind of mechanical equipment fault method for early warning based on industrial Internet of Things according to claim 1, which is characterized in that
The classification fault model is based on the training of convolutional neural networks training pattern and obtains, training process specifically:
Step 1: obtaining the corresponding mechanical equipment state data of different faults, pass through Fourier transformation life after progress noise suppression preprocessing
It is divided into training sample and test sample at spectrogram and in preset ratio;
Step 2: establishing convolutional neural networks model and initiation parameter, determine network parameter, the network parameter includes: learning
Habit rate, the number of iterations;
Step 3: training sample being input in convolutional neural networks model, output valve and desired value are acquired by propagated forward
Error;
Step 4: judge whether convolutional neural networks model restrains, it is no to then follow the steps 5 if convergence thens follow the steps 6;
Step 5: backpropagation and weight modification are reversely successively passed the error that step 4 acquires using stochastic gradient descent algorithm
It broadcasts, updates weight, repeat step 3 and arrive step 5, until convolutional neural networks model is restrained;
Step 6: judging whether convolutional neural networks model meets the requirements according to the accuracy of test sample, such as meet and execute step
7, step 2 is otherwise jumped to, network parameter is modified;
Step 7: the convolutional neural networks model that output training finishes is used for fault pre-alarming.
6. a kind of mechanical equipment fault method for early warning based on industrial Internet of Things according to claim 5, which is characterized in that
The loss function that the neural network model uses is specific as follows for cross entropy loss function:
Wherein, 1 { yi=j } it is indicative function, it indicates that the value in bracket be true duration is 1, be fictitious time value is 0;K is the total of sample
Number, C are the classification number of sample, yiIt is the true value of the i-th sample,It is the i-th sample prediction probability of all categories for jth.
7. a kind of mechanical equipment fault method for early warning based on industrial Internet of Things according to claim 6, which is characterized in that
In the training process, propagated forward calculates error amount to neural network, and error amount backpropagation updates each layer of W and e, parameter
More new formula it is as follows:
Wherein, the learning rate of η convolutional neural networks.
8. a kind of mechanical equipment fault early warning system based on industrial Internet of Things, which is characterized in that including memory and processor,
It include the mechanical equipment fault method for early warning program based on industrial Internet of Things in the memory, it is described based on industrial Internet of Things
Mechanical equipment fault method for early warning program realizes following steps when being executed by the processor:
The mechanical equipment state data are transmitted to data gateway and do pre- sentence by sensing node collection machinery device status data
Reason, if Current mechanical device status data and preset standard status data absolute value of the difference are greater than preset threshold, mechanical equipment
Status data is uploaded to Cloud Server;
The Cloud Server utilizes classification failure to characteristic value is extracted after mechanical equipment state data prediction, by characteristic value data
Model carries out early warning diagnosis, obtains diagnostic result.
9. a kind of mechanical equipment fault early warning system based on industrial Internet of Things according to claim 8, which is characterized in that if
The mechanical equipment state value and preset standard state value absolute value of the difference of acquisition are less than preset threshold, then record current temporal instance
T1, if after instant tl in preset period T, the mechanical equipment state value and preset standard state value absolute value of the difference
Respectively less than preset threshold, then sampling rate adjusting is n times of current sampling frequency, continues to sample T time section and the machine to sampling
Tool device status data does anticipation processing.
10. a kind of computer readable storage medium, which is characterized in that include the one of machine in the computer readable storage medium
Mechanical equipment fault method for early warning program of the kind based on industrial Internet of Things, a kind of mechanical equipment event based on industrial Internet of Things
When barrier method for early warning program is executed by processor, realize that one kind as described in any one of claims 1 to 7 is based on industrial Internet of Things
The step of mechanical equipment fault method for early warning of net.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910712301.XA CN110362068A (en) | 2019-08-02 | 2019-08-02 | A kind of mechanical equipment fault method for early warning, system and readable storage medium storing program for executing based on industrial Internet of Things |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910712301.XA CN110362068A (en) | 2019-08-02 | 2019-08-02 | A kind of mechanical equipment fault method for early warning, system and readable storage medium storing program for executing based on industrial Internet of Things |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110362068A true CN110362068A (en) | 2019-10-22 |
Family
ID=68222095
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910712301.XA Withdrawn CN110362068A (en) | 2019-08-02 | 2019-08-02 | A kind of mechanical equipment fault method for early warning, system and readable storage medium storing program for executing based on industrial Internet of Things |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110362068A (en) |
Cited By (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110794799A (en) * | 2019-11-28 | 2020-02-14 | 桂林电子科技大学 | Big data system with fault diagnosis function applied to industrial production |
CN110794892A (en) * | 2019-11-27 | 2020-02-14 | 杭州凯达电力建设有限公司 | Abnormal temperature data diagnosis method, device and equipment |
CN111476299A (en) * | 2020-04-07 | 2020-07-31 | 国家电网有限公司华东分部 | Improved convolutional neural network and power grid intelligent alarm system based on same |
CN112199888A (en) * | 2020-09-30 | 2021-01-08 | 苏州容思恒辉智能科技有限公司 | Rotary equipment fault diagnosis method and system based on deep residual error network and readable storage medium |
CN112202897A (en) * | 2020-09-30 | 2021-01-08 | 重庆市海普软件产业有限公司 | Low-power consumption intelligent internet of things gateway |
CN112235154A (en) * | 2020-09-09 | 2021-01-15 | 广州安食通信息科技有限公司 | Data processing method, system, device and medium based on Internet of things |
CN112308130A (en) * | 2020-10-29 | 2021-02-02 | 成都千嘉科技有限公司 | Deployment method of deep learning network of Internet of things |
CN112463422A (en) * | 2020-11-04 | 2021-03-09 | 鸬鹚科技(苏州)有限公司 | Internet of things fault operation and maintenance method and device, computer equipment and storage medium |
CN112525336A (en) * | 2020-11-18 | 2021-03-19 | 西安因联信息科技有限公司 | Automatic detection method for continuous increase of vibration of mechanical equipment |
CN112749861A (en) * | 2019-10-31 | 2021-05-04 | 西安西电高压开关有限责任公司 | Ubiquitous power Internet of things edge calculation method and system |
CN113341920A (en) * | 2021-05-31 | 2021-09-03 | 三一重机有限公司 | Working machine fault early warning method and device, working machine and electronic equipment |
CN113687639A (en) * | 2021-10-25 | 2021-11-23 | 南通好心情家用纺织品有限公司 | Intelligent fault early warning method and system for textile machinery equipment |
CN113762767A (en) * | 2021-09-05 | 2021-12-07 | 西北农林科技大学 | Intelligent management method and terminal system for whole course cross-platform agricultural machinery operation of coarse cereal production |
CN113805548A (en) * | 2021-09-18 | 2021-12-17 | 深圳市玄羽科技有限公司 | Machining intelligent control system, machining intelligent control method and computer readable medium |
CN114371678A (en) * | 2022-01-11 | 2022-04-19 | 升发智联(北京)科技有限责任公司 | Equipment safety production early warning method, system, equipment and storage medium |
CN114528183A (en) * | 2022-02-17 | 2022-05-24 | 厦门四信通信科技有限公司 | Offline prediction method, device and equipment of LoRa equipment and readable storage medium |
CN115065707A (en) * | 2022-07-27 | 2022-09-16 | 北京华夏圣远能源科技有限公司 | Remote monitoring method, device and medium for micromolecule recyclable fracturing fluid sand mixing truck |
CN115096375A (en) * | 2022-08-22 | 2022-09-23 | 启东亦大通自动化设备有限公司 | Carrier roller running state monitoring method and device based on carrier roller carrying trolley detection |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105449851A (en) * | 2015-11-19 | 2016-03-30 | 国网山东曲阜市供电公司 | Rural-power-grid distribution-equipment remote on-line fault diagnosis system based on cloud server |
CN105629957A (en) * | 2016-02-04 | 2016-06-01 | 西安理工大学 | Cold-chain transport vehicle refrigerating unit fault analysis cloud service system and control method |
CN108871434A (en) * | 2018-05-30 | 2018-11-23 | 北京必创科技股份有限公司 | A kind of on-line monitoring system and method for slewing |
-
2019
- 2019-08-02 CN CN201910712301.XA patent/CN110362068A/en not_active Withdrawn
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105449851A (en) * | 2015-11-19 | 2016-03-30 | 国网山东曲阜市供电公司 | Rural-power-grid distribution-equipment remote on-line fault diagnosis system based on cloud server |
CN105629957A (en) * | 2016-02-04 | 2016-06-01 | 西安理工大学 | Cold-chain transport vehicle refrigerating unit fault analysis cloud service system and control method |
CN108871434A (en) * | 2018-05-30 | 2018-11-23 | 北京必创科技股份有限公司 | A kind of on-line monitoring system and method for slewing |
Cited By (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112749861A (en) * | 2019-10-31 | 2021-05-04 | 西安西电高压开关有限责任公司 | Ubiquitous power Internet of things edge calculation method and system |
CN110794892A (en) * | 2019-11-27 | 2020-02-14 | 杭州凯达电力建设有限公司 | Abnormal temperature data diagnosis method, device and equipment |
CN110794799A (en) * | 2019-11-28 | 2020-02-14 | 桂林电子科技大学 | Big data system with fault diagnosis function applied to industrial production |
CN111476299A (en) * | 2020-04-07 | 2020-07-31 | 国家电网有限公司华东分部 | Improved convolutional neural network and power grid intelligent alarm system based on same |
CN112235154A (en) * | 2020-09-09 | 2021-01-15 | 广州安食通信息科技有限公司 | Data processing method, system, device and medium based on Internet of things |
CN112202897B (en) * | 2020-09-30 | 2022-05-13 | 重庆市海普软件产业有限公司 | Low-power consumption intelligent internet of things gateway |
CN112199888A (en) * | 2020-09-30 | 2021-01-08 | 苏州容思恒辉智能科技有限公司 | Rotary equipment fault diagnosis method and system based on deep residual error network and readable storage medium |
CN112202897A (en) * | 2020-09-30 | 2021-01-08 | 重庆市海普软件产业有限公司 | Low-power consumption intelligent internet of things gateway |
CN112308130A (en) * | 2020-10-29 | 2021-02-02 | 成都千嘉科技有限公司 | Deployment method of deep learning network of Internet of things |
CN112308130B (en) * | 2020-10-29 | 2021-10-15 | 成都千嘉科技有限公司 | Deployment method of deep learning network of Internet of things |
CN112463422A (en) * | 2020-11-04 | 2021-03-09 | 鸬鹚科技(苏州)有限公司 | Internet of things fault operation and maintenance method and device, computer equipment and storage medium |
CN112525336A (en) * | 2020-11-18 | 2021-03-19 | 西安因联信息科技有限公司 | Automatic detection method for continuous increase of vibration of mechanical equipment |
CN113341920A (en) * | 2021-05-31 | 2021-09-03 | 三一重机有限公司 | Working machine fault early warning method and device, working machine and electronic equipment |
CN113762767A (en) * | 2021-09-05 | 2021-12-07 | 西北农林科技大学 | Intelligent management method and terminal system for whole course cross-platform agricultural machinery operation of coarse cereal production |
CN113805548A (en) * | 2021-09-18 | 2021-12-17 | 深圳市玄羽科技有限公司 | Machining intelligent control system, machining intelligent control method and computer readable medium |
CN113687639A (en) * | 2021-10-25 | 2021-11-23 | 南通好心情家用纺织品有限公司 | Intelligent fault early warning method and system for textile machinery equipment |
CN114371678A (en) * | 2022-01-11 | 2022-04-19 | 升发智联(北京)科技有限责任公司 | Equipment safety production early warning method, system, equipment and storage medium |
CN114528183A (en) * | 2022-02-17 | 2022-05-24 | 厦门四信通信科技有限公司 | Offline prediction method, device and equipment of LoRa equipment and readable storage medium |
CN115065707A (en) * | 2022-07-27 | 2022-09-16 | 北京华夏圣远能源科技有限公司 | Remote monitoring method, device and medium for micromolecule recyclable fracturing fluid sand mixing truck |
CN115065707B (en) * | 2022-07-27 | 2022-11-04 | 北京华夏圣远能源科技有限公司 | Remote monitoring method, device and medium for micromolecule recyclable fracturing fluid sand mixing truck |
CN115096375A (en) * | 2022-08-22 | 2022-09-23 | 启东亦大通自动化设备有限公司 | Carrier roller running state monitoring method and device based on carrier roller carrying trolley detection |
CN115096375B (en) * | 2022-08-22 | 2022-11-04 | 启东亦大通自动化设备有限公司 | Carrier roller running state monitoring method and device based on carrier roller carrying trolley detection |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110362068A (en) | A kind of mechanical equipment fault method for early warning, system and readable storage medium storing program for executing based on industrial Internet of Things | |
CN110414155B (en) | Fan component temperature abnormity detection and alarm method with single measuring point | |
CN106872657B (en) | A kind of multivariable water quality parameter time series data accident detection method | |
CN104573850B (en) | A kind of Power Plant Equipment state evaluating method | |
CN113077172A (en) | Equipment state trend analysis and fault diagnosis method | |
CN106528975B (en) | A kind of prognostic and health management method applied to Circuits and Systems | |
Zhang et al. | Intelligent fault diagnosis and prognosis approach for rotating machinery integrating wavelet transform, principal component analysis, and artificial neural networks | |
CN108584592A (en) | A kind of shock of elevator car abnormity early warning method based on time series predicting model | |
US20140365179A1 (en) | Method and Apparatus for Detecting and Identifying Faults in a Process | |
CN112083244B (en) | Integrated intelligent diagnosis system for faults of avionic equipment | |
CN107797537A (en) | A kind of prognostic and health management method applied to automatic production line | |
CN108027611B (en) | Decision assistance system and method for machine maintenance using expert opinion supervised decision mode learning | |
CN109308519A (en) | A kind of refrigeration equipment failure prediction method neural network based | |
EP2853972A2 (en) | Device and method for detection and/or diagnosis of faults in a process, equipment and sensors | |
CN112785091A (en) | Method for performing fault prediction and health management on oil field electric submersible pump | |
Khaleghei et al. | Model parameter estimation and residual life prediction for a partially observable failing system | |
CN111221706B (en) | CPU utilization rate prediction method, system, medium and equipment | |
EP2642362A2 (en) | System monitoring | |
AT514680A2 (en) | Process for optimizing the maintenance of technical systems | |
CN112906900A (en) | Method and system for monitoring vehicle condition and for alerting anomalies/defects | |
Qin et al. | Remaining useful life prediction for rotating machinery based on optimal degradation indicator | |
CN116670608A (en) | Hybrid ensemble method for predictive modeling of Internet of things | |
Saranya et al. | Data-driven prognostics for run-to-failure data employing machine learning models | |
CN117076258A (en) | Remote monitoring method and system based on Internet cloud | |
Burnaev | Rare failure prediction via event matching for aerospace applications |
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 | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20191022 |