CN112446389A - Fault judgment method and device - Google Patents
Fault judgment method and device Download PDFInfo
- Publication number
- CN112446389A CN112446389A CN201910754270.4A CN201910754270A CN112446389A CN 112446389 A CN112446389 A CN 112446389A CN 201910754270 A CN201910754270 A CN 201910754270A CN 112446389 A CN112446389 A CN 112446389A
- Authority
- CN
- China
- Prior art keywords
- preset
- fault
- frequency spectrum
- vibration signal
- characteristic value
- 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
- 238000000034 method Methods 0.000 title claims abstract description 62
- 238000001228 spectrum Methods 0.000 claims abstract description 112
- 238000012545 processing Methods 0.000 claims abstract description 41
- 238000010801 machine learning Methods 0.000 claims abstract description 27
- 238000012549 training Methods 0.000 claims description 44
- 238000000605 extraction Methods 0.000 claims description 21
- 238000004590 computer program Methods 0.000 claims description 13
- 238000003860 storage Methods 0.000 claims description 13
- 238000012850 discrimination method Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 abstract description 27
- 238000013527 convolutional neural network Methods 0.000 description 42
- 238000012360 testing method Methods 0.000 description 24
- 230000006870 function Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 238000003745 diagnosis Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000009826 distribution Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000003595 spectral effect Effects 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H1/00—Measuring characteristics of vibrations in solids by using direct conduction to the detector
- G01H1/12—Measuring characteristics of vibrations in solids by using direct conduction to the detector of longitudinal or not specified vibrations
- G01H1/14—Frequency
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H1/00—Measuring characteristics of vibrations in solids by using direct conduction to the detector
- G01H1/12—Measuring characteristics of vibrations in solids by using direct conduction to the detector of longitudinal or not specified vibrations
- G01H1/16—Amplitude
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Abstract
The embodiment of the invention provides a fault judgment method and device. The method comprises the following steps: acquiring a vibration signal frequency spectrum of target mobile equipment; extracting a characteristic value in the vibration signal frequency spectrum according to a preset signal processing rule; the characteristic value is an amplitude of a preset characteristic frequency in the vibration signal frequency spectrum; inputting the characteristic value into a preset fault discrimination model to obtain a fault discrimination result of the target mobile equipment; the fault discrimination model is obtained by machine learning of sample data. The embodiment of the invention solves the problem that the fault judgment process of the oil field power equipment depends on manual judgment in the prior art.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a fault judgment method and device.
Background
In the production activity of oil fields, oil field power equipment plays an important role. The oil field power equipment generally refers to rotating equipment driven by a driving machine, and if a fault occurs in the working process of the power equipment, the production activity of the oil field is usually required to be interrupted, so that the fault treatment is performed in a longer time, and the performance of the oil field production activity is influenced to a great extent. Therefore, fault detection of mobile equipment is particularly important in the production process of oil fields.
At present, the fault diagnosis process of most oilfield dynamic equipment is generally based on the manual judgment of the running condition of the equipment; however, the manual judgment is greatly influenced by the experience of the judgment personnel, the judgment result is not objective enough, the unified judgment standard is difficult to achieve, and the conditions such as judgment errors are easily caused.
Disclosure of Invention
The embodiment of the invention provides a fault judgment method and a fault judgment device, which aim to solve the problem that in the prior art, the fault judgment process of oil field power equipment depends on manual judgment.
In one aspect, an embodiment of the present invention provides a fault determination method, where the method includes:
acquiring a vibration signal frequency spectrum of target mobile equipment;
extracting a characteristic value in the vibration signal frequency spectrum according to a preset signal processing rule; the characteristic value is an amplitude of a preset characteristic frequency in the vibration signal frequency spectrum;
inputting the characteristic value into a preset fault discrimination model to obtain a fault discrimination result of the target mobile equipment; the fault discrimination model is obtained by machine learning of sample data.
Optionally, the step of extracting the feature value in the frequency spectrum of the vibration signal according to a preset signal processing rule includes:
according to a preset denoising rule, denoising the vibration signal frequency spectrum to obtain a processed frequency spectrum;
and extracting the characteristic value in the processed frequency spectrum according to a preset characteristic extraction rule.
Optionally, the preset characteristic frequency is a frequency between 1 and 10 multiples of a preset reference frequency;
the preset reference frequency is the reference frequency of the target mobile device.
Optionally, the method further comprises:
receiving model training operation aiming at a preset sample library; wherein the preset sample library comprises a first preset number group of the sample data; each group of the sample data comprises a characteristic value in a vibration signal frequency spectrum of the mobile equipment and the probability and/or fault type of the fault of the mobile equipment corresponding to the sample data;
and responding to the model training operation, and training a fault discrimination model according to the sample data and a preset rule.
Optionally, after the step of obtaining the fault determination result of the target mobile device, the method further includes:
and storing the fault judgment result and the characteristic value of the vibration signal frequency spectrum of the target mobile equipment into the preset sample library as a group of sample data.
On the other hand, an embodiment of the present invention further provides a fault determination apparatus, where the apparatus includes:
the frequency spectrum acquisition module is used for acquiring a vibration signal frequency spectrum of the target mobile device;
the characteristic extraction module is used for extracting a characteristic value in the vibration signal frequency spectrum according to a preset signal processing rule; the characteristic value is an amplitude of a preset characteristic frequency in the vibration signal frequency spectrum;
the fault discrimination module is used for inputting the characteristic value into a preset fault discrimination model to obtain a fault discrimination result of the target mobile equipment; the fault discrimination model is obtained by machine learning of sample data.
Optionally, the feature extraction module includes:
the noise processing submodule is used for carrying out denoising processing on the vibration signal frequency spectrum according to a preset denoising rule to obtain a processed frequency spectrum;
and the extraction submodule is used for extracting the characteristic value in the processed frequency spectrum according to a preset characteristic extraction rule.
Optionally, the preset characteristic frequency is a frequency between 1 and 10 multiples of a preset reference frequency;
the preset reference frequency is the reference frequency of the target mobile device.
Optionally, the apparatus further comprises:
the operation receiving module is used for receiving model training operation aiming at a preset sample library; wherein the preset sample library comprises a first preset number group of the sample data; each group of the sample data comprises a characteristic value in a vibration signal frequency spectrum of the mobile equipment and the probability and/or fault type of the fault of the mobile equipment corresponding to the sample data;
and the model training module is used for responding to the model training operation and training the fault discrimination model according to the sample data and the preset rule.
Optionally, the apparatus further comprises:
and the data storage module is used for storing the fault judgment result and the characteristic value of the vibration signal frequency spectrum of the target mobile equipment as a group of sample data into the preset sample library.
In still another aspect, an embodiment of the present invention further provides an electronic device, where the electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps in the fault determination method as described above when executing the computer program.
In still another aspect, an embodiment of the present invention further provides a storage medium, where the storage medium has a computer program stored thereon, and the computer program, when executed by a processor, implements the steps in the fault determination method described above.
In the embodiment of the invention, the vibration signal frequency spectrum of the target mobile equipment is obtained; then extracting a characteristic value in the vibration signal frequency spectrum according to a preset signal processing rule, wherein the characteristic value is an amplitude of a preset characteristic frequency in the vibration signal frequency spectrum; finally, inputting the characteristic value into a preset fault judgment model to obtain a fault judgment result of the target mobile equipment; the fault discrimination model is obtained by machine learning of sample data, and the fault discrimination model obtained by the machine learning has higher accuracy and forms the same standard of fault discrimination; the embodiment of the invention realizes intelligent processing of fault judgment, outputs objective judgment results through the fault judgment model, avoids the judgment process from being influenced by subjective factors of workers, and saves labor cost compared with manual judgment.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments of the present invention will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive labor.
FIG. 1 is a flowchart illustrating steps of a method for determining a fault according to an embodiment of the present invention;
FIG. 2 is a second flowchart illustrating steps of a fault determination method according to an embodiment of the present invention;
fig. 3 is a block diagram of a fault determination apparatus according to an embodiment of the present invention;
fig. 4 is a block diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be appreciated that reference throughout this specification to "one embodiment" or "an embodiment" means that a particular feature, structure or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention. Thus, the appearances of the phrases "in one embodiment" or "in an embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
In various embodiments of the present invention, it should be understood that the sequence numbers of the following processes do not mean the execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
Referring to fig. 1, an embodiment of the present invention provides a fault determination method, which may be applied to an apparatus such as an upper computer or a server that performs fault determination and diagnosis;
the method comprises the following steps:
Wherein, the target mobile equipment can be oilfield mobile equipment; the frequency spectrum, i.e. the frequency spectral density, the distribution curve of the frequency, usually reflects the vibration condition through the frequency spectrum; optionally, a sensor may be disposed at the target mobile device side for acquiring a vibration signal of the target mobile device to obtain a vibration signal spectrum of the target mobile device.
Optionally, an acquisition period may be set for each target mobile device, and the vibration signal spectrum acquired in each acquisition period is used for fault discrimination of the next mobile device.
102, extracting a characteristic value in the frequency spectrum of the vibration signal according to a preset signal processing rule; and the characteristic value is the amplitude of a preset characteristic frequency in the vibration signal frequency spectrum.
The method comprises the steps of carrying out signal processing on a vibration signal frequency spectrum according to a preset signal processing rule to obtain a characteristic value, wherein the characteristic value is an amplitude of a preset characteristic frequency in the vibration signal frequency spectrum, and the amplitude is vibration amplitude.
The preset characteristic frequency is preset and can reflect the frequency value of the vibration characteristic, namely the frequency value with data significance, such as the frequency value at the integral multiple position of the reference frequency, and can usually reflect the vibration characteristic; and analyzing the vibration condition of the mobile equipment by extracting the characteristic value.
103, inputting the characteristic value into a preset fault judgment model to obtain a fault judgment result of the target mobile equipment; the fault discrimination model is obtained by machine learning of sample data.
Inputting the characteristic value into a preset fault discrimination model, and obtaining a fault discrimination result of the target mobile equipment by the fault discrimination model; optionally, the fault discrimination result may include a probability of occurrence of a fault and/or a fault type of the target mobile device.
The fault discrimination model is obtained by performing machine learning on sample data, the model of the machine learning can be a Convolutional Neural Network (CNN), specifically, in the process of the machine learning, a supervised learning mode is adopted, a large amount of sample data are divided into a training data set and a test data set, the training data set is used for training an initial CNN to obtain the fault discrimination model, and the test data set is used for testing the accuracy of the fault discrimination model; in the training process, circularly inputting data in a training data set to an initial CNN, comparing an output result of the initial CNN with a known result, wherein the output result comprises the probability and/or fault type of fault of the mobile equipment corresponding to the group of test data after fault judgment is carried out on multiple test data; the known result is the probability and/or fault type of the failure of the mobile equipment corresponding to the set of test data which is measured in advance; and reversely optimizing the CNN according to the difference between the test result and the known result in the comparison result, so that the loss function in the CNN tends to be the minimum value, and finally obtaining the CNN meeting the accuracy requirement, wherein the CNN at the moment is the fault discrimination model.
It is understood that the machine-learned model may also be a random forest model or a support vector machine model, which is not described herein.
Therefore, the target movable equipment is judged based on the fault judgment model, the accuracy is high, manual judgment can be replaced, an independent fault judgment model can be trained for the movable equipment of the same model, a uniform fault judgment standard is formed, and the influence of subjective factors of workers during fault judgment is avoided.
In the above embodiment of the present invention, a frequency spectrum of a vibration signal of a target mobile device is obtained; then extracting a characteristic value in the vibration signal frequency spectrum according to a preset signal processing rule, wherein the characteristic value is an amplitude of a preset characteristic frequency in the vibration signal frequency spectrum; finally, inputting the characteristic value into a preset fault judgment model to obtain a fault judgment result of the target mobile equipment; the fault discrimination model is obtained by machine learning of sample data, and the fault discrimination model obtained by the machine learning has higher accuracy and forms the same standard of fault discrimination; the embodiment of the invention realizes intelligent processing of fault judgment, outputs objective judgment results through the fault judgment model, avoids the judgment process from being influenced by subjective factors of workers, and saves labor cost compared with manual judgment. The embodiment of the invention solves the problem that the fault judgment process of the oil field power equipment depends on manual judgment in the prior art.
Optionally, in the embodiment of the present invention, the step of extracting a feature value in the frequency spectrum of the vibration signal according to a preset signal processing rule includes:
according to a preset denoising rule, denoising the vibration signal frequency spectrum to obtain a processed frequency spectrum;
and extracting the characteristic value in the processed frequency spectrum according to a preset characteristic extraction rule.
The denoising processing is mainly realized based on filters, and the filters comprise a low-pass filter, a high-pass filter, a band-pass filter and the like; noise signals in the vibration signal frequency spectrum are removed through the filter according to a preset denoising rule, and the influence of the noise signals on fault judgment is avoided.
Filtering noise signals to obtain a processed frequency spectrum, and extracting characteristic values in the frequency; specifically, in the process of extracting the characteristic value, according to a preset characteristic extraction rule, extracting the amplitude of a preset characteristic frequency in the processed frequency spectrum; the preset characteristic frequency is preset and can reflect the frequency value of the vibration characteristic, namely the frequency value with data significance, such as the frequency value at the integral multiple position of the reference frequency, and can usually reflect the vibration characteristic; and analyzing the vibration condition of the mobile equipment by extracting the characteristic value.
Further, in the embodiment of the present invention, the preset characteristic frequency is a frequency between 1 frequency doubling and 10 frequency doubling of the preset reference frequency;
the preset reference frequency is the reference frequency of the target mobile device.
Wherein, 1 frequency doubling is 1X reference frequency, and 10 frequency doubling is 10X reference frequency. The frequency multiplication, i.e. the generation of an output signal frequency, is an integer multiple of the input signal frequency. For example, if the input signal frequency is n, the first frequency multiplication is 2n, and accordingly 3n, 4n, … …, etc. are all called frequency multiplication. For the mobile equipment, a part of vibration comes from 1 frequency doubling, and the vibration signal abnormality between 1 frequency doubling and 10 frequency doubling indicates that the mobile equipment is possible to have a fault, so that the frequency characteristic value between 1 frequency doubling and 10 frequency doubling is collected as the basis of fault analysis during fault analysis.
Referring to fig. 2, another embodiment of the present invention provides a fault determination method, including:
The model training operation is to train the fault discrimination model in a machine learning manner, the preset sample library comprises a first preset number group of sample data, and the first preset number can be set to be a larger value so as to improve the accuracy of the trained model.
Each group of the sample data comprises a characteristic value in a vibration signal frequency spectrum of the mobile equipment and also comprises a known judgment result of the sample data, namely the probability and/or the fault type of the mobile equipment corresponding to the sample data.
In addition, if the trained fault discrimination model is a model for a type of mobile equipment, the sample data should be data in a vibration signal spectrum of the type of mobile equipment.
Optionally, each set of sample data may be data in a preset acquisition period of each mobile device, and a vibration signal spectrum of the mobile device is acquired in each acquisition period as a set of sample data.
And 202, responding to the model training operation, and training a fault discrimination model according to sample data and a preset rule.
In the machine learning process, a supervised learning mode is adopted, sample data in a preset sample library are divided into a training data set and a testing data set, the training data set is used for training an initial CNN to obtain a fault discrimination model, and the testing data set is used for testing the accuracy of the fault discrimination model.
In the training process, circularly inputting sample data in a training data set to the initial CNN; specifically, firstly, inputting a characteristic value in a first group of sample data into an initial CNN to obtain an output result of the initial CNN; then comparing the output result of the initial CNN with a known result in the first group of sample data, wherein the known result is the pre-determined probability and/or fault type of the mobile equipment corresponding to the group of test data; reversely optimizing the CNN according to the difference between the test result and the known result in the comparison result, and adjusting the internal structure and/or parameters of the CNN to obtain the optimized CNN; and iterating the characteristic values of the second group of sample data to the converted CNN … …, and iterating and optimizing until the loss function in the CNN tends to the preset loss function minimum value to finally obtain the CNN meeting the accuracy requirement, wherein the CNN at the moment is the fault discrimination model.
The target mobile equipment can be oilfield mobile equipment, and is preferably equipment with the same model as the source equipment of sample data in a preset sample library; the frequency spectrum, i.e. the frequency spectral density, the distribution curve of the frequency, usually reflects the vibration condition through the frequency spectrum; optionally, a sensor may be disposed at the target mobile device side for acquiring a vibration signal of the target mobile device to obtain a vibration signal spectrum of the target mobile device.
Optionally, an acquisition period may be set for each target mobile device, and the vibration signal spectrum acquired in each acquisition period is used for fault discrimination of the next mobile device.
The method comprises the steps of carrying out signal processing on a vibration signal frequency spectrum according to a preset signal processing rule to obtain a characteristic value, wherein the characteristic value is an amplitude of a preset characteristic frequency in the vibration signal frequency spectrum, and the amplitude is vibration amplitude.
The preset characteristic frequency is preset and can reflect the frequency value of the vibration characteristic, namely the frequency value with data significance, such as the frequency value at the integral multiple position of the reference frequency, and can usually reflect the vibration characteristic; and analyzing the vibration condition of the mobile equipment by extracting the characteristic value.
Inputting the characteristic value into a preset fault discrimination model, and obtaining a fault discrimination result of the target mobile equipment by the fault discrimination model; optionally, the fault discrimination result may include a probability of occurrence of a fault and/or a fault type of the target mobile device.
The target movable equipment is judged based on the fault judgment model, the accuracy is high, manual judgment can be replaced, an independent fault judgment model can be trained for the movable equipment of the same model, a unified fault judgment standard is formed, and the influence of subjective factors of workers during fault judgment is avoided.
Further, in the embodiment of the present invention, after the step of obtaining the fault determination result of the target mobile device, the method further includes:
and storing the fault judgment result and the characteristic value of the vibration signal frequency spectrum of the target mobile equipment into the preset sample library as a group of sample data.
And after fault discrimination is carried out each time or fault maintenance is further carried out, storing the fault discrimination result and the characteristic value of the vibration signal frequency spectrum of the target mobile equipment as a group of sample data into the preset sample library for subsequent training and optimizing upgrading of the model, and further improving the accuracy of the fault discrimination model.
Based on the fault discrimination method provided by the embodiment of the invention, a set of communication link from a sensor, a Remote Terminal Unit (RTU), a Programmable Logic Controller (PLC), a Distributed Control System (DCS) to a fault diagnosis System can be established, the sensor collects data, the RTU, the PLC and the DCS perform data processing and transmission, and finally the fault discrimination is performed by the fault diagnosis System.
In the above embodiment of the present invention, a frequency spectrum of a vibration signal of a target mobile device is obtained; then extracting a characteristic value in the vibration signal frequency spectrum according to a preset signal processing rule, wherein the characteristic value is an amplitude of a preset characteristic frequency in the vibration signal frequency spectrum; finally, inputting the characteristic value into a preset fault judgment model to obtain a fault judgment result of the target mobile equipment; the fault discrimination model is obtained by machine learning of sample data, and the fault discrimination model obtained by the machine learning has higher accuracy and forms the same standard of fault discrimination; the embodiment of the invention realizes intelligent processing of fault judgment, outputs objective judgment results through the fault judgment model, avoids the judgment process from being influenced by subjective factors of workers, and saves labor cost compared with manual judgment. The embodiment of the invention solves the problem that the fault judgment process of the oil field power equipment depends on manual judgment in the prior art.
The fault determination method provided by the embodiment of the present invention is described above, and a fault determination device provided by the embodiment of the present invention will be described below with reference to the accompanying drawings.
Referring to fig. 3, an embodiment of the present invention further provides a fault determination device, where the fault determination device may be applied to an apparatus such as an upper computer or a server that performs fault determination and diagnosis; the device comprises:
the frequency spectrum acquiring module 301 is configured to acquire a frequency spectrum of a vibration signal of a target mobile device.
Wherein, the target mobile equipment can be oilfield mobile equipment; the frequency spectrum, i.e. the frequency spectral density, the distribution curve of the frequency, usually reflects the vibration condition through the frequency spectrum; optionally, a sensor may be disposed at the target mobile device side for acquiring a vibration signal of the target mobile device to obtain a vibration signal spectrum of the target mobile device.
Optionally, an acquisition period may be set for each target mobile device, and the vibration signal spectrum acquired in each acquisition period is used for fault discrimination of the next mobile device.
A feature extraction module 302, configured to extract a feature value in the frequency spectrum of the vibration signal according to a preset signal processing rule; and the characteristic value is the amplitude of a preset characteristic frequency in the vibration signal frequency spectrum.
The method comprises the steps of carrying out signal processing on a vibration signal frequency spectrum according to a preset signal processing rule to obtain a characteristic value, wherein the characteristic value is an amplitude of a preset characteristic frequency in the vibration signal frequency spectrum, and the amplitude is vibration amplitude.
The preset characteristic frequency is preset and can reflect the frequency value of the vibration characteristic, namely the frequency value with data significance, such as the frequency value at the integral multiple position of the reference frequency, and can usually reflect the vibration characteristic; and analyzing the vibration condition of the mobile equipment by extracting the characteristic value.
A fault discrimination module 303, configured to input the feature value to a preset fault discrimination model to obtain a fault discrimination result of the target mobile device; the fault discrimination model is obtained by machine learning of sample data.
Inputting the characteristic value into a preset fault discrimination model, and obtaining a fault discrimination result of the target mobile equipment by the fault discrimination model; optionally, the fault discrimination result may include a probability of occurrence of a fault and/or a fault type of the target mobile device.
The fault discrimination model is obtained by performing machine learning on sample data, the model of the machine learning can be a Convolutional Neural Network (CNN), specifically, in the process of the machine learning, a supervised learning mode is adopted, a large amount of sample data are divided into a training data set and a test data set, the training data set is used for training an initial CNN to obtain the fault discrimination model, and the test data set is used for testing the accuracy of the fault discrimination model; in the training process, circularly inputting data in a training data set to an initial CNN, comparing an output result of the initial CNN with a known result, wherein the output result comprises the probability and/or fault type of fault of the mobile equipment corresponding to the group of test data after fault judgment is carried out on multiple test data; the known result is the probability and/or fault type of the failure of the mobile equipment corresponding to the set of test data which is measured in advance; and reversely optimizing the CNN according to the difference between the test result and the known result in the comparison result, so that the loss function in the CNN tends to be the minimum value, and finally obtaining the CNN meeting the accuracy requirement, wherein the CNN at the moment is the fault discrimination model.
Therefore, the target movable equipment is judged based on the fault judgment model, the accuracy is high, manual judgment can be replaced, an independent fault judgment model can be trained for the movable equipment of the same model, a uniform fault judgment standard is formed, and the influence of subjective factors of workers during fault judgment is avoided.
Optionally, in this embodiment of the present invention, the feature extraction module 302 includes:
the noise processing submodule is used for carrying out denoising processing on the vibration signal frequency spectrum according to a preset denoising rule to obtain a processed frequency spectrum;
and the extraction submodule is used for extracting the characteristic value in the processed frequency spectrum according to a preset characteristic extraction rule.
The denoising processing is mainly realized based on filters, and the filters comprise a low-pass filter, a high-pass filter, a band-pass filter and the like; noise signals in the vibration signal frequency spectrum are removed through the filter according to a preset denoising rule, and the influence of the noise signals on fault judgment is avoided.
Filtering noise signals to obtain a processed frequency spectrum, and extracting characteristic values in the frequency; specifically, in the process of extracting the characteristic value, according to a preset characteristic extraction rule, extracting the amplitude of a preset characteristic frequency in the processed frequency spectrum; the preset characteristic frequency is preset and can reflect the frequency value of the vibration characteristic, namely the frequency value with data significance, such as the frequency value at the integral multiple position of the reference frequency, and can usually reflect the vibration characteristic; and analyzing the vibration condition of the mobile equipment by extracting the characteristic value.
Optionally, in an embodiment of the present invention, the preset characteristic frequency is a frequency between 1 frequency doubling and 10 frequency doubling of a preset reference frequency;
the preset reference frequency is the reference frequency of the target mobile device.
Wherein, 1 frequency doubling is 1X reference frequency, and 10 frequency doubling is 10X reference frequency. The frequency multiplication, i.e. the generation of an output signal frequency, is an integer multiple of the input signal frequency. For example, if the input signal frequency is n, the first frequency multiplication is 2n, and accordingly 3n, 4n, … …, etc. are all called frequency multiplication. For the mobile equipment, a part of vibration comes from 1 frequency doubling, and the vibration signal abnormality between 1 frequency doubling and 10 frequency doubling indicates that the mobile equipment is possible to have a fault, so that the frequency characteristic value between 1 frequency doubling and 10 frequency doubling is collected as the basis of fault analysis during fault analysis.
Optionally, in an embodiment of the present invention, the apparatus further includes:
the operation receiving module is used for receiving model training operation aiming at a preset sample library; wherein the preset sample library comprises a first preset number group of the sample data; each group of the sample data comprises a characteristic value in a vibration signal frequency spectrum of the mobile equipment and the probability and/or fault type of the fault of the mobile equipment corresponding to the sample data;
and the model training module is used for responding to the model training operation and training the fault discrimination model according to the sample data and the preset rule.
The model training operation is to train the fault discrimination model in a machine learning manner, the preset sample library comprises a first preset number group of sample data, and the first preset number can be set to be a larger value so as to improve the accuracy of the trained model.
Each group of the sample data comprises a characteristic value in a vibration signal frequency spectrum of the mobile equipment and also comprises a known judgment result of the sample data, namely the probability and/or the fault type of the mobile equipment corresponding to the sample data.
In addition, if the trained fault discrimination model is a model for a type of mobile equipment, the sample data should be data in a vibration signal spectrum of the type of mobile equipment.
Optionally, each set of sample data may be data in a preset acquisition period of each mobile device, and a vibration signal spectrum of the mobile device is acquired in each acquisition period as a set of sample data.
In the machine learning process, a supervised learning mode is adopted, sample data in a preset sample library are divided into a training data set and a testing data set, the training data set is used for training an initial CNN to obtain a fault discrimination model, and the testing data set is used for testing the accuracy of the fault discrimination model.
In the training process, circularly inputting sample data in a training data set to the initial CNN; specifically, firstly, inputting a characteristic value in a first group of sample data into an initial CNN to obtain an output result of the initial CNN; then comparing the output result of the initial CNN with a known result in the first group of sample data, wherein the known result is the pre-determined probability and/or fault type of the mobile equipment corresponding to the group of test data; reversely optimizing the CNN according to the difference between the test result and the known result in the comparison result, and adjusting the internal structure and/or parameters of the CNN to obtain the optimized CNN; and iterating the characteristic values of the second group of sample data to the converted CNN … …, and iterating and optimizing until the loss function in the CNN tends to the preset loss function minimum value to finally obtain the CNN meeting the accuracy requirement, wherein the CNN at the moment is the fault discrimination model.
Optionally, in an embodiment of the present invention, the apparatus further includes:
and the data storage module is used for storing the fault judgment result and the characteristic value of the vibration signal frequency spectrum of the target mobile equipment as a group of sample data into the preset sample library.
And after fault discrimination is carried out each time or fault maintenance is further carried out, storing the fault discrimination result and the characteristic value of the vibration signal frequency spectrum of the target mobile equipment as a group of sample data into the preset sample library for subsequent training and optimizing upgrading of the model, and further improving the accuracy of the fault discrimination model.
The fault determination device provided by the embodiment of the present invention can implement each process implemented by the fault determination device in the method embodiments of fig. 1 to fig. 2, and is not described herein again in order to avoid repetition.
In the embodiment of the present invention, the frequency spectrum obtaining module 301 obtains a frequency spectrum of a vibration signal of a target mobile device; the feature extraction module 302 extracts a feature value in the vibration signal frequency spectrum according to a preset signal processing rule, wherein the feature value is an amplitude of a preset feature frequency in the vibration signal frequency spectrum; the fault discrimination module 303 inputs the characteristic value into a preset fault discrimination model to obtain a fault discrimination result of the target mobile device; the fault discrimination model is obtained by machine learning of sample data, and the fault discrimination model obtained by the machine learning has higher accuracy and forms the same standard of fault discrimination; the embodiment of the invention realizes intelligent processing of fault judgment, outputs objective judgment results through the fault judgment model, avoids the judgment process from being influenced by subjective factors of workers, and saves labor cost compared with manual judgment.
On the other hand, the fault discrimination device comprises a processor and a memory, the spectrum acquisition module, the feature extraction module, the fault discrimination module, the noise processing submodule and the extraction submodule are all stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.
The processor comprises a kernel, and the kernel calls the corresponding program unit from the memory. One or more than one kernel can be set, and intelligent processing of fault judgment is realized by adjusting kernel parameters.
An embodiment of the present invention provides a storage medium on which a program is stored, the program implementing the fault discrimination method when executed by a processor.
The embodiment of the invention provides a processor, which is used for running a program, wherein the fault judgment method is executed when the program runs.
Referring to fig. 4, an electronic device 400 according to an embodiment of the present invention includes at least one processor 401, and at least one memory 402 and a bus connected to the processor 401; the processor 401 and the memory 402 complete communication with each other through the bus 403; the processor 401 is used to call program instructions in the memory 402 to execute the above-mentioned fault determination method. The device 400 herein may be a server, a PC, a PAD, a handset, etc.
The present application further provides a computer program product adapted to perform a program for initializing the following method steps when executed on a data processing device:
acquiring a vibration signal frequency spectrum of target mobile equipment;
extracting a characteristic value in the vibration signal frequency spectrum according to a preset signal processing rule; the characteristic value is an amplitude of a preset characteristic frequency in the vibration signal frequency spectrum;
inputting the characteristic value into a preset fault discrimination model to obtain a fault discrimination result of the target mobile equipment; the fault discrimination model is obtained by machine learning of sample data.
And
according to a preset denoising rule, denoising the vibration signal frequency spectrum to obtain a processed frequency spectrum;
and extracting the characteristic value in the processed frequency spectrum according to a preset characteristic extraction rule.
The preset characteristic frequency is a frequency between 1 frequency multiplication and 10 frequency multiplication of a preset reference frequency;
the preset reference frequency is the reference frequency of the target mobile device.
And
receiving model training operation aiming at a preset sample library; wherein the preset sample library comprises a first preset number group of the sample data; each group of the sample data comprises a characteristic value in a vibration signal frequency spectrum of the mobile equipment and the probability and/or fault type of the fault of the mobile equipment corresponding to the sample data;
and responding to the model training operation, and training a fault discrimination model according to the sample data and a preset rule.
And
and storing the fault judgment result and the characteristic value of the vibration signal frequency spectrum of the target mobile equipment into the preset sample library as a group of sample data.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a device includes one or more processors (CPUs), memory, and a bus. The device may also include input/output interfaces, network interfaces, and the like.
The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip. The memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (10)
1. A fault discrimination method, comprising:
acquiring a vibration signal frequency spectrum of target mobile equipment;
extracting a characteristic value in the vibration signal frequency spectrum according to a preset signal processing rule; the characteristic value is an amplitude of a preset characteristic frequency in the vibration signal frequency spectrum;
inputting the characteristic value into a preset fault discrimination model to obtain a fault discrimination result of the target mobile equipment; the fault discrimination model is obtained by machine learning of sample data.
2. The method according to claim 1, wherein the step of extracting the characteristic value in the spectrum of the vibration signal according to a preset signal processing rule comprises:
according to a preset denoising rule, denoising the vibration signal frequency spectrum to obtain a processed frequency spectrum;
and extracting the characteristic value in the processed frequency spectrum according to a preset characteristic extraction rule.
3. The fault discrimination method according to claim 1, wherein the preset characteristic frequency is a frequency between 1 and 10 multiples of a preset reference frequency;
the preset reference frequency is the reference frequency of the target mobile device.
4. The fault discrimination method according to claim 1, further comprising:
receiving model training operation aiming at a preset sample library; wherein the preset sample library comprises a first preset number group of the sample data; each group of the sample data comprises a characteristic value in a vibration signal frequency spectrum of the mobile equipment and the probability and/or fault type of the fault of the mobile equipment corresponding to the sample data;
and responding to the model training operation, and training a fault discrimination model according to the sample data and a preset rule.
5. The method according to claim 4, wherein the step of obtaining the fault determination result of the target mobile device is followed by the method further comprising:
and storing the fault judgment result and the characteristic value of the vibration signal frequency spectrum of the target mobile equipment into the preset sample library as a group of sample data.
6. A fault discrimination apparatus comprising:
the frequency spectrum acquisition module is used for acquiring a vibration signal frequency spectrum of the target mobile device;
the characteristic extraction module is used for extracting a characteristic value in the vibration signal frequency spectrum according to a preset signal processing rule; the characteristic value is an amplitude of a preset characteristic frequency in the vibration signal frequency spectrum;
the fault discrimination module is used for inputting the characteristic value into a preset fault discrimination model to obtain a fault discrimination result of the target mobile equipment; the fault discrimination model is obtained by machine learning of sample data.
7. The fault discrimination apparatus according to claim 6, wherein the feature extraction module includes:
the noise processing submodule is used for carrying out denoising processing on the vibration signal frequency spectrum according to a preset denoising rule to obtain a processed frequency spectrum;
and the extraction submodule is used for extracting the characteristic value in the processed frequency spectrum according to a preset characteristic extraction rule.
8. The apparatus according to claim 6, wherein the predetermined characteristic frequency is a frequency between 1 and 10 multiples of a predetermined reference frequency;
the preset reference frequency is the reference frequency of the target mobile device.
9. An electronic device comprising a processor, a memory and a computer program stored on the memory and executable on the processor, characterized in that the computer program, when executed by the processor, implements the steps of the fault discrimination method as claimed in any one of claims 1 to 5.
10. A storage medium, characterized in that the storage medium has stored thereon a computer program which, when being executed by a processor, carries out the steps of the fault discrimination method according to one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910754270.4A CN112446389A (en) | 2019-08-15 | 2019-08-15 | Fault judgment method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910754270.4A CN112446389A (en) | 2019-08-15 | 2019-08-15 | Fault judgment method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112446389A true CN112446389A (en) | 2021-03-05 |
Family
ID=74740913
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910754270.4A Pending CN112446389A (en) | 2019-08-15 | 2019-08-15 | Fault judgment method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112446389A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114046970A (en) * | 2021-10-26 | 2022-02-15 | 山东浪潮通软信息科技有限公司 | Method and device for detecting misalignment of rotating shaft of mining axial-flow fan |
| CN114543982A (en) * | 2022-03-11 | 2022-05-27 | 珠海格力电器股份有限公司 | Method and device for detecting vibration of equipment, vibration detection equipment and storage medium |
| CN117054872A (en) * | 2023-09-15 | 2023-11-14 | 合肥融讯电子科技有限公司 | Motor fault prediction detection system based on data model |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108757426A (en) * | 2018-07-04 | 2018-11-06 | 温州大学 | Oilfield water filling plunger pump trouble diagnostic method |
| US20190204818A1 (en) * | 2016-11-30 | 2019-07-04 | Hitachi, Ltd. | Data collection system, abnormality detection method, and gateway device |
| CN110108486A (en) * | 2018-01-31 | 2019-08-09 | 阿里巴巴集团控股有限公司 | Bearing fault prediction technique, equipment and system |
-
2019
- 2019-08-15 CN CN201910754270.4A patent/CN112446389A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190204818A1 (en) * | 2016-11-30 | 2019-07-04 | Hitachi, Ltd. | Data collection system, abnormality detection method, and gateway device |
| CN110108486A (en) * | 2018-01-31 | 2019-08-09 | 阿里巴巴集团控股有限公司 | Bearing fault prediction technique, equipment and system |
| CN108757426A (en) * | 2018-07-04 | 2018-11-06 | 温州大学 | Oilfield water filling plunger pump trouble diagnostic method |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114046970A (en) * | 2021-10-26 | 2022-02-15 | 山东浪潮通软信息科技有限公司 | Method and device for detecting misalignment of rotating shaft of mining axial-flow fan |
| CN114543982A (en) * | 2022-03-11 | 2022-05-27 | 珠海格力电器股份有限公司 | Method and device for detecting vibration of equipment, vibration detection equipment and storage medium |
| CN114543982B (en) * | 2022-03-11 | 2023-09-08 | 珠海格力电器股份有限公司 | Vibration detection method and device for equipment, vibration detection equipment and storage medium |
| CN117054872A (en) * | 2023-09-15 | 2023-11-14 | 合肥融讯电子科技有限公司 | Motor fault prediction detection system based on data model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108731923B (en) | Fault detection method and device for rotary mechanical equipment | |
| CN112446389A (en) | Fault judgment method and device | |
| CN112346941A (en) | Fault diagnosis method and device | |
| CN109765055B (en) | Rolling bearing fault detection method and system based on EWT, spectrum effective value and KNN | |
| CN110133500B (en) | Motor online monitoring and fault precursor diagnosis system and method based on multi-layer architecture | |
| US9396061B1 (en) | Automated repair of storage system components via data analytics | |
| CN111309539A (en) | Abnormity monitoring method and device and electronic equipment | |
| CN112131907A (en) | Method and device for training classification model | |
| CN112557069A (en) | Equipment vibration fault detection method, device and system and storage medium | |
| CN109213034B (en) | Equipment health degree monitoring method and device, computer equipment and readable storage medium | |
| CN110119787B (en) | Working condition detection method and equipment for rotary mechanical equipment | |
| CN110909826A (en) | Diagnosis monitoring method and device for energy equipment and electronic equipment | |
| CN108009063B (en) | Method for detecting fault threshold of electronic equipment | |
| CN111291918B (en) | Rotating machine degradation trend prediction method based on stationary subspace exogenous vector autoregression | |
| CN116304909A (en) | Abnormality detection model training method, fault scene positioning method and device | |
| CN114021448A (en) | Semiconductor device detection method, processor and semiconductor device | |
| CN113239970A (en) | Model training method, equipment vibration abnormity detection method and device | |
| EP3712728A1 (en) | Apparatus for predicting equipment damage | |
| CN114138601A (en) | Service alarm method, device, equipment and storage medium | |
| CN112577664A (en) | Sensor fault detection method and device and related product | |
| CN107977626B (en) | Grouping method for electronic equipment working data | |
| CN116415126A (en) | Method, device and computing equipment for anomaly detection of doctor blades of paper machine | |
| CN108009582B (en) | Method for setting standard working index of electronic equipment | |
| CN113123955B (en) | Plunger pump abnormity detection method and device, storage medium and electronic equipment | |
| CN114639391A (en) | Mechanical failure prompting method and device, electronic equipment and storage medium |
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 |