CN114742108A - Method and system for detecting fault of bearing of numerical control machine tool - Google Patents
Method and system for detecting fault of bearing of numerical control machine tool Download PDFInfo
- Publication number
- CN114742108A CN114742108A CN202210415151.8A CN202210415151A CN114742108A CN 114742108 A CN114742108 A CN 114742108A CN 202210415151 A CN202210415151 A CN 202210415151A CN 114742108 A CN114742108 A CN 114742108A
- Authority
- CN
- China
- Prior art keywords
- bearing
- data
- sub
- band
- operation data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/251—Fusion techniques of input or preprocessed data
-
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- 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
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computational Linguistics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Software Systems (AREA)
- Signal Processing (AREA)
- Numerical Control (AREA)
Abstract
The invention discloses a method and a system for detecting faults of a bearing of a numerical control machine tool, wherein the method comprises the following steps: acquiring operation data of a bearing to be detected of a numerical control machine tool and environment correction data corresponding to the bearing to be detected; correcting the operation data according to the environment correction data to obtain corrected operation data corresponding to the bearing to be detected; performing wavelet transformation on the corrected operation data to obtain a plurality of sub-band operation data corresponding to the bearing to be detected; performing data fusion on each sub-band operation data to obtain sub-band fusion data corresponding to each sub-band operation data; and inputting the sub-band fusion data into a pre-trained fault detection model, and acquiring a fault detection result of the bearing to be detected according to the fault detection model. Compared with the prior art, the scheme of the invention is beneficial to eliminating the influence of complex environmental information on the bearing fault detection process and improving the accuracy of bearing fault detection.
Description
Technical Field
The invention relates to the technical field of fault detection, in particular to a fault detection method and system for a bearing of a numerical control machine tool.
Background
With the development of science and technology, the application of the bearing is more and more extensive. The bearing is an important part in mechanical equipment, and the main function of the bearing is to support a mechanical rotator, reduce the friction coefficient in the movement process of the mechanical rotator and ensure the rotation precision of the mechanical rotator. The bearings are an important part of the mechanical equipment, for example, a plurality of bearings may be provided at different positions of the numerical control machine tool for maintaining the proper operation of the numerical control machine tool. However, at the same time, the bearing is also one of the components of the mechanical equipment which are prone to faults, and the fault of the bearing will affect the operation of the mechanical equipment, so that the fault state of the bearing needs to be monitored and detected.
In the prior art, a sensor is usually arranged near a bearing, and the fault detection is performed on the bearing directly through data acquired by the sensor. The problem of the prior art is that when the fault detection is directly performed on the bearing through the data acquired by the sensor, the influence of complex environmental information on the data acquired by the sensor is ignored, and the accuracy of the fault detection of the bearing is not improved.
Thus, there is still a need for improvement and development of the prior art.
Disclosure of Invention
The invention mainly aims to provide a method and a system for detecting faults of a bearing of a numerical control machine tool, and aims to solve the problems that when the fault detection is carried out on the bearing by directly using data acquired by a sensor in the prior art, the influence of complex environmental information on the data acquired by the sensor is ignored, and the accuracy of the fault detection of the bearing is not improved.
In order to achieve the above object, a first aspect of the present invention provides a method for detecting a bearing fault of a numerical control machine tool, wherein the method for detecting a bearing fault of a numerical control machine tool comprises:
acquiring operation data of a bearing to be detected of a numerical control machine tool and environment correction data corresponding to the bearing to be detected, wherein the operation data comprises a vibration signal, a current signal and a temperature signal when the bearing to be detected operates, and the environment correction data comprises an environment vibration signal, an environment current signal and an environment temperature signal corresponding to when the bearing to be detected stops operating;
correcting the operation data according to the environment correction data to obtain corrected operation data corresponding to the bearing to be detected;
performing wavelet transformation on the corrected operation data to obtain a plurality of sub-band operation data corresponding to the bearing to be detected;
performing data fusion on each sub-band operation data to obtain sub-band fusion data corresponding to each sub-band operation data;
and inputting the sub-band fusion data into a pre-trained fault detection model, and acquiring a fault detection result of the bearing to be detected according to the fault detection model.
Optionally, the acquiring operation data of one bearing to be detected of the numerical control machine tool and the environment correction data corresponding to the bearing to be detected includes:
acquiring vibration signals, current signals and temperature signals of the bearing to be detected during operation in real time through a plurality of preset sensors, and taking the vibration signals, the current signals and the temperature signals as the operation data;
and acquiring an environmental vibration signal, an environmental current signal and an environmental temperature signal which are obtained by measuring through the sensor when the bearing to be detected stops running and other bearings of the numerical control machine tool run in advance, and taking the environmental vibration signal, the environmental current signal and the environmental temperature signal as the environmental correction data.
Optionally, the correcting the operation data according to the environment correction data to obtain corrected operation data corresponding to the bearing to be detected includes:
acquiring the running time length corresponding to the running data and the measuring time length corresponding to the environment correction data;
adjusting the environment correction data according to the running time length and the measuring time length to obtain target correction data, wherein the time length corresponding to the target correction data is the same as the running time length;
and subtracting a corresponding signal in the target correction data from a signal in the operation data to obtain the corrected operation data, wherein the corrected operation data comprises a corrected vibration signal, a corrected current signal and a corrected temperature signal.
Optionally, the adjusting the environmental correction data according to the running time length and the measuring time length and obtaining target correction data includes:
acquiring a segment time length and a preset segment number, wherein the segment time length is an absolute value of a difference between the running time length and the measuring time length;
when the running time length is less than the measuring time length, randomly selecting a plurality of segments to be deleted from the environment correction data and deleting the segments to obtain the target correction data, wherein the sum of the time lengths of the segments to be deleted is equal to the segment time length;
and when the running time length is greater than the measuring time length, randomly selecting a segment number of segments to be added from the environmental correction data and adding the segments to the environmental correction data to obtain the target correction data, wherein the sum of the time lengths of the segments to be added is equal to the segment time length.
Optionally, the performing wavelet transform on the corrected operation data to obtain multiple sub-band operation data corresponding to the bearing to be detected includes:
and performing discrete wavelet transformation on the corrected operation data, dividing the corrected operation data into a plurality of sub-bands and obtaining a plurality of sub-band operation data corresponding to the bearing to be detected, wherein each sub-band operation data comprises a sub-band corrected vibration signal, a sub-band corrected current signal and a sub-band corrected temperature signal.
Optionally, the performing data fusion on each sub-band operating data to obtain sub-band fusion data corresponding to each sub-band operating data respectively includes:
and respectively carrying out adaptive weighted fusion on the sub-band correction vibration signal, the sub-band correction current signal and the sub-band correction temperature signal in each sub-band operation data to obtain each sub-band fusion data.
Optionally, the fault detection model is a gated cyclic unit neural network model, and the gated cyclic unit neural network model is trained in advance through the following steps:
acquiring a training data set, wherein the training data set comprises a plurality of fault operation data, training environment correction data corresponding to the fault operation data and fault category labels corresponding to the fault operation data, each fault operation data comprises a training vibration signal, a training current signal and a training temperature signal when a training bearing operates, and the training environment correction data comprises a training environment vibration signal, a training environment current signal and a training environment temperature signal corresponding to the training bearing when the training bearing stops operating;
correcting the fault operation data according to the training environment correction data to obtain training correction fault data corresponding to the training bearing;
performing wavelet transformation on the training corrected fault data to obtain a plurality of sub-band training data corresponding to the training bearings;
respectively carrying out data fusion on each sub-band training data to obtain sub-band training fusion data corresponding to each sub-band training data and obtain sub-band fault class labels corresponding to each sub-band training fusion data;
and performing iterative training on the gate control cycle unit neural network model according to the subband training fusion data and the subband fault class label, and taking the trained gate control cycle unit neural network model as the fault detection model.
Optionally, the iteratively training the gate control cycle unit neural network model according to the subband training fusion data and the subband fault class label includes:
inputting the sub-band training fusion data and the sub-band fault class labels into an ith updated gating cycle unit neural network model, and respectively performing feature extraction on each sub-band training fusion data through the ith updated gating cycle unit neural network model to obtain sub-band features, wherein i is any integer greater than or equal to 0, and the 0 th updated gating cycle unit neural network model is a preset initial gating unit neural network model;
fault identification is carried out on the sub-band characteristics through a preset normalization index function, corresponding identification faults are obtained, and loss values between the identification faults and corresponding sub-band fault category labels are calculated according to a preset cross entropy loss function;
when the loss value is larger than a preset loss threshold value, updating the parameters of the gate control cycle unit neural network model after the ith updating by a minimum gradient descent method, and obtaining the gate control cycle unit neural network model after the (i + 1) th updating;
and when the loss value is not greater than the loss threshold value, taking the gating cycle unit neural network model updated for the ith time as the gating cycle unit neural network model after training is completed.
Optionally, after the sub-band fusion data is input into a pre-trained fault detection model and a fault detection result of the bearing to be detected is obtained according to the fault detection model, the method further includes:
and acquiring a fault processing scheme corresponding to the fault detection result according to a preset fault processing scheme list and executing the fault processing scheme.
The second aspect of the present invention provides a system for detecting a bearing fault of a numerical control machine tool, wherein the system for detecting a bearing fault of a numerical control machine tool comprises:
the data acquisition module is used for acquiring operation data of a bearing to be detected of the numerical control machine tool and environment correction data corresponding to the bearing to be detected, wherein the operation data comprises a vibration signal, a current signal and a temperature signal when the bearing to be detected operates, and the environment correction data comprises an environment vibration signal, an environment current signal and an environment temperature signal corresponding to the condition that the bearing to be detected stops operating;
the data correction module is used for correcting the operation data according to the environment correction data to obtain corrected operation data corresponding to the bearing to be detected;
the data transformation module is used for performing wavelet transformation on the corrected operation data to obtain a plurality of sub-band operation data corresponding to the bearing to be detected;
a data fusion module, configured to perform data fusion on each subband operating data to obtain subband fusion data corresponding to each subband operating data;
and the fault detection module is used for inputting the sub-band fusion data into a pre-trained fault detection model and acquiring a fault detection result of the bearing to be detected according to the fault detection model.
As can be seen from the above, in the scheme of the present invention, operation data of a bearing to be detected of a numerical control machine tool and environment correction data corresponding to the bearing to be detected are obtained, wherein the operation data includes a vibration signal, a current signal and a temperature signal when the bearing to be detected operates, and the environment correction data includes an environment vibration signal, an environment current signal and an environment temperature signal corresponding to when the bearing to be detected stops operating; correcting the operation data according to the environment correction data to obtain corrected operation data corresponding to the bearing to be detected; performing wavelet transformation on the corrected operation data to obtain a plurality of sub-band operation data corresponding to the bearing to be detected; performing data fusion on each sub-band operation data to obtain sub-band fusion data corresponding to each sub-band operation data; and inputting the sub-band fusion data into a pre-trained fault detection model, and acquiring a fault detection result of the bearing to be detected according to the fault detection model. Compared with the scheme of directly detecting the fault of the bearing through the data acquired by the sensor in the prior art, the method and the device for detecting the fault of the bearing further acquire the corresponding environment correction data, correct the operation data of the bearing to be detected according to the environment correction data, and detect the fault of the bearing according to the corrected operation data, so that the method and the device are beneficial to eliminating the influence of complex environment information on the fault detection process of the bearing and improving the accuracy of the fault detection of the bearing.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required to be used in the embodiments or the prior art description will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without inventive labor.
Fig. 1 is a schematic flow chart of a method for detecting a bearing fault of a numerically-controlled machine tool according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating the step S100 in FIG. 1 according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating the step S200 in FIG. 1 according to an embodiment of the present invention;
FIG. 4 is a flowchart illustrating the step S202 in FIG. 3 according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a system for detecting a bearing fault of a numerical control machine tool according to an embodiment of the present invention.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.
It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
As used in this specification and the appended claims, the term "if" may be interpreted contextually as "when …" or "upon" or "in response to a determination" or "in response to a detection". Similarly, the phrase "if it is determined" or "if a [ described condition or event ] is detected" may be interpreted depending on the context to mean "upon determining" or "in response to determining" or "upon detecting [ described condition or event ]" or "in response to detecting [ described condition or event ]".
The technical solutions in the embodiments of the present invention are clearly and completely described below with reference to the drawings of the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways than those specifically described and will be readily apparent to those of ordinary skill in the art without departing from the spirit of the present invention, and therefore the present invention is not limited to the specific embodiments disclosed below.
With the development of science and technology, the application of the bearing is more and more extensive. The bearing is an important part in mechanical equipment, and the main function of the bearing is to support a mechanical rotator, reduce the friction coefficient in the movement process of the mechanical rotator and ensure the rotation precision of the mechanical rotator. The bearings are important components of mechanical equipment, for example, a plurality of bearings may be provided at different positions of the numerical control machine tool for maintaining the proper operation of the numerical control machine tool. However, at the same time, the bearing is also one of the components of the mechanical equipment which are prone to faults, and the fault of the bearing will affect the operation of the mechanical equipment, so that the fault state of the bearing needs to be monitored and detected.
In the prior art, a sensor is usually arranged near a bearing, and the fault detection is performed on the bearing directly through data acquired by the sensor. The problem of the prior art is that when the fault detection is directly performed on the bearing through the data acquired by the sensor, the influence of complex environmental information on the data acquired by the sensor is ignored, and the accuracy of the fault detection of the bearing is not improved. For example, in one training scenario, the ambient temperature is 20 degrees celsius, at which time the bearing fails (abnormal heating) when the temperature of the bearing is 26 degrees celsius. In another detection scenario, the ambient temperature is 26 degrees celsius, the operating temperature of the bearing to be detected is 26 degrees celsius, and the bearing is normally operated (does not generate heat abnormally), but according to the prior art, the influence of the ambient information is not considered, and it is considered that the bearing to be detected is abnormally heated and fails, so that erroneous judgment is caused.
Meanwhile, in an application scenario, only a single frequency band data signal acquired during bearing operation is considered, which is not consistent with the actual multi-working-condition operation condition, and the accuracy of bearing fault detection is also influenced.
In order to solve at least one of the problems, in the scheme of the invention, operation data of a bearing to be detected of a numerical control machine tool and environment correction data corresponding to the bearing to be detected are obtained, wherein the operation data comprise a vibration signal, a current signal and a temperature signal when the bearing to be detected runs, and the environment correction data comprise an environment vibration signal, an environment current signal and an environment temperature signal corresponding to the condition that the bearing to be detected stops running; correcting the operation data according to the environment correction data to obtain corrected operation data corresponding to the bearing to be detected; performing wavelet transformation on the corrected operation data to obtain a plurality of sub-band operation data corresponding to the bearing to be detected; performing data fusion on each sub-band operation data to obtain sub-band fusion data corresponding to each sub-band operation data; and inputting the sub-band fusion data into a pre-trained fault detection model, and acquiring a fault detection result of the bearing to be detected according to the fault detection model.
Compared with the scheme of directly detecting the fault of the bearing through the data acquired by the sensor in the prior art, the method and the device for detecting the fault of the bearing further acquire the corresponding environment correction data, correct the operation data of the bearing to be detected according to the environment correction data, and detect the fault of the bearing according to the corrected operation data, so that the influence of complex environment information on the fault detection process of the bearing is eliminated, and the accuracy of the fault detection of the bearing is improved. Meanwhile, the scheme of the invention also utilizes wavelet transformation to convert the acquired single frequency band data into multi-frequency band data, so that the fault detection accuracy in multi-working-condition operation can be improved, the fault bearing can be replaced or maintained in time, and the stability and the safety of the operation of the numerical control machine tool are improved.
Exemplary method
As shown in fig. 1, an embodiment of the present invention provides a method for detecting a fault of a bearing of a numerical control machine tool, specifically, the method includes the following steps:
step S100, obtaining operation data of a bearing to be detected of a numerical control machine tool and environment correction data corresponding to the bearing to be detected, wherein the operation data comprises a vibration signal, a current signal and a temperature signal when the bearing to be detected runs, and the environment correction data comprises an environment vibration signal, an environment current signal and an environment temperature signal corresponding to the bearing to be detected when the bearing to be detected stops running.
In the present embodiment, data detection is performed on a bearing to be detected, which is any one of the bearings in the numerical control machine tool, as an example, the bearing to be detected may be detected as a fault.
The operation data of the bearing to be detected is obtained by monitoring the bearing to be detected in real time, and can be data acquired by a sensor within a period of monitoring time, and the environment correction data corresponding to the bearing to be detected is obtained by acquiring signals in the environment where the bearing to be detected is located in advance.
In this embodiment, as shown in fig. 2, the step S100 specifically includes the following steps:
and S101, acquiring vibration signals, current signals and temperature signals of the bearing to be detected during operation in real time through a plurality of preset sensors, and taking the vibration signals, the current signals and the temperature signals as the operation data.
And step S102, obtaining an environmental vibration signal, an environmental current signal and an environmental temperature signal which are obtained by measuring through the sensor when the bearing to be detected stops running and other bearings of the numerical control machine tool run in advance, and using the environmental vibration signal, the environmental current signal and the environmental temperature signal as the environmental correction data.
In this embodiment, the signals corresponding to the operation data and the environmental correction data respectively include three types of signals, i.e., a vibration signal, a current signal, and a temperature signal, and therefore three types of sensors, i.e., an acceleration sensor, a current sensor, and a temperature sensor, are also preset around the bearing to be detected, the acceleration sensor is used for acquiring the vibration signal and the environmental vibration signal, the current sensor is used for acquiring the current signal and the environmental current signal, and the temperature sensor is used for acquiring the temperature signal and the environmental temperature signal. In an application scenario, the operation data and the environmental correction data may further include corresponding other signals, such as a voltage signal and an environmental voltage signal, a resistance signal and an environmental resistance signal, and corresponding other types of sensors are also provided, which is not limited herein.
The current signal, the voltage signal, the resistance signal, the environment current signal, the voltage signal, and the environment resistance signal are acquired by a control circuit of the bearing.
Further, in this embodiment, for each category of sensor, the numerical control machine may set a plurality of specific sensors within a preset range of the bearing to be detected, collect signals of the same category, and perform weighted average according to weights to obtain corresponding signals. For example, a plurality of temperature sensors are arranged in the preset range of the bearing to be detected, each temperature sensor simultaneously collects temperature signals of the bearing to be detected, and then weighted average is performed on the temperature signals, so that the influence of abnormal data is reduced, and the accuracy of fault detection is improved. The weight corresponding to each temperature sensor can be determined according to the distance between the temperature sensor for counter use and the bearing to be detected.
The environment correction data is an environment signal acquired in advance when the bearing to be detected stops running. It should be noted that a plurality of bearings may be provided in a numerical control machine, for example, the spindle bearing of the numerical control machine has two arrangements of front and rear two supports and three arrangements of front, middle and rear three supports. Through the environmental correction data acquired in the embodiment, the influence of other bearings in the numerical control machine tool on the detection of the to-be-detected bearing carrying operating state can be eliminated.
It should be noted that, for a numerical control machine, the environment correction data corresponding to each bearing may be acquired in advance, and an environment correction data list is generated, so that the environment correction data corresponding to the bearing to be detected may be quickly obtained through table lookup, so as to improve the efficiency of fault detection. It should be noted that each signal in the environmental correction data may also be a weighted average of signals collected by a plurality of sensors, so as to further improve the accuracy of fault detection.
And S200, correcting the operation data according to the environment correction data to obtain corrected operation data corresponding to the bearing to be detected.
Specifically, the operating data can be corrected through the environmental correction data, so that the influence of environmental signals on each signal in the operating data is reduced, and the accuracy of fault detection is improved. In this embodiment, as shown in fig. 3, the step S200 specifically includes the following steps:
step S201, obtaining an operation time length corresponding to the operation data and a measurement time length corresponding to the environmental correction data.
Step S202, adjusting the environmental correction data according to the running time length and the measurement time length to obtain target correction data, wherein the time length corresponding to the target correction data is the same as the running time length.
Step S203, subtracting a signal in the operation data from a corresponding signal in the target correction data to obtain the corrected operation data, wherein the corrected operation data includes a corrected vibration signal, a corrected current signal, and a corrected temperature signal.
Specifically, in this embodiment, the operation data and the environmental correction data are acquired within a certain time period, and the corresponding time period may be preset or may be set and adjusted according to actual requirements. And the time period corresponding to the operating data and the time period corresponding to the environmental correction data may have different lengths, and the operating data can be corrected only by adjusting the time period of the environmental correction data. It should be noted that, if each signal in the operation data and the environment correction data is composed of discrete data, the corresponding operation time length and measurement time length may be determined according to the number of the discrete data and the unit time of data acquisition.
Specifically, when the operating time length is equal to the measurement time length, the environmental correction data may be directly used as the target correction data.
In one application scenario, when the running time length is less than the measurement time length, a continuous piece of data may be randomly intercepted from the environment modification data as the target modification data. Alternatively, when the operating time length is longer than the measurement time length, a continuous piece of data may be randomly selected from the environment correction data and combined after the environment correction data as the target correction data.
In this embodiment, as shown in fig. 4, the step S202 specifically includes the following steps:
step S2021, acquiring a segment duration and a preset segment number, where the segment duration is an absolute value of a difference between the running time length and the measurement time length.
Step S2022, when the running time length is less than the measuring time length, randomly selecting a number of segments to be deleted from the environmental correction data and deleting the segments to obtain the target correction data, where a sum of the time lengths of the segments to be deleted is equal to the segment duration.
Step S2023, when the running time length is greater than the measurement time length, obtaining the target correction data after randomly selecting a number of segments to be added from the environmental correction data and adding the segments to the environmental correction data, where a sum of time lengths of the segments to be added is equal to the segment time length.
The number of the segments may be preset or adjusted according to actual requirements, and is not specifically limited herein. For example, the number of segments may be set to be 3, and at this time, the sum of the time lengths of the obtained 3 segments to be deleted is equal to the segment time length, and the time lengths of the segments to be deleted may be the same or different, and are not limited specifically herein. It should be noted that there is no overlapping portion between the segments to be deleted, and there may be an overlapping portion between the segments to be added.
In another application scenario, a number of segments may be randomly selected from the environmental correction data, and the segments are combined to form corresponding target correction data, wherein a time length of each segment is equal to a value obtained by dividing the running time length by the number of segments.
It should be noted that, the adjusting of the environmental correction data is to adjust each signal in the environmental correction data respectively, and the time lengths of each signal in the target correction data, the environmental correction data or the operation data are the same, for example, the time lengths of the operation data corresponding to the vibration signal, the current signal and the temperature signal when the bearing to be detected operates are the same.
Thus, after the operation data and the target correction data with the same time length are obtained, the signal in the operation data and the corresponding signal in the target correction data may be directly subtracted to obtain the corrected operation data, for example, the vibration signal in the operation data and the target corrected vibration signal in the target correction data are subtracted to obtain the corrected vibration signal in the corrected operation data, and so on, which is not described herein again.
And step S300, performing wavelet transformation on the corrected operation data to obtain a plurality of sub-band operation data corresponding to the bearing to be detected.
Specifically, discrete wavelet transform is performed on the corrected operation data, the corrected operation data is divided into a plurality of sub-bands, and a plurality of sub-band operation data corresponding to the bearing to be detected is obtained, wherein each sub-band operation data includes a sub-band corrected vibration signal, a sub-band corrected current signal, and a sub-band corrected temperature signal.
The discrete wavelet transform is used to divide a signal into different sub-bands, and when different signals show different frequency characteristics, corresponding differences are shown in one sub-band. Features may thus be generated in the sub-bands and then trained using the features as input to the classifier. For a trained classifier, different types of signals (e.g., signals of different fault types) can be distinguished based on the input features. In the embodiment, the collected data of a single frequency band is converted into the data of multiple frequency bands by using wavelet transformation, so that the fault detection accuracy in multi-working-condition operation is improved. It should be noted that the number of the sub-band operation data obtained by dividing may be preset, or may be adjusted in real time according to actual requirements, which is not specifically limited herein.
Step S400, performing data fusion on each of the sub-band operation data to obtain sub-band fusion data corresponding to each of the sub-band operation data.
Specifically, the subband correction vibration signal, the subband correction current signal, and the subband correction temperature signal in each of the subband operation data are adaptively weighted and fused to obtain each of the subband fusion data.
Wherein, a sub-band fusion data comprises a fusion signal, each value in the fusion signal is obtained after adaptive weighted fusion according to the sub-band correction vibration signal, the sub-band correction current signal and the sub-band correction temperature signal. Therefore, a signal is obtained after a plurality of signals are fused, the efficiency of feature extraction and fault detection is improved, and the required time is shortened.
Optionally, other data fusion manners may also be adopted, for example, arithmetic mean fusion or weighted fusion according to a preset fusion weight value, and the like, which are not specifically limited herein.
And S500, inputting the sub-band fusion data into a pre-trained fault detection model, and acquiring a fault detection result of the bearing to be detected according to the fault detection model.
The fault detection model is a Gated cycle Unit (GRU) neural network model, and the Gated cycle Unit neural network model is trained in advance through the following steps:
acquiring a training data set, wherein the training data set comprises a plurality of fault operation data, training environment correction data corresponding to the fault operation data and fault category labels corresponding to the fault operation data, each fault operation data comprises a training vibration signal, a training current signal and a training temperature signal when a training bearing operates, and the training environment correction data comprises a training environment vibration signal, a training environment current signal and a training environment temperature signal corresponding to the training bearing when the training bearing stops operating;
correcting the fault operation data according to the training environment correction data to obtain training correction fault data corresponding to the training bearing;
performing wavelet transformation on the training corrected fault data to obtain a plurality of sub-band training data corresponding to the training bearing;
respectively carrying out data fusion on each sub-band training data to obtain sub-band training fusion data corresponding to each sub-band training data and obtain sub-band fault class labels corresponding to each sub-band training fusion data;
and performing iterative training on the gate control cycle unit neural network model according to the subband training fusion data and the subband fault class label, and taking the trained gate control cycle unit neural network model as the fault detection model.
Specifically, low and the training time is long when carrying out fault detection based on prior art, compares with prior art, uses GRU neural network training with higher speed in this embodiment, can reduce the training required time of fault detection model to improve the generalization and the accuracy of the fault detection model that the digit control machine tool corresponds.
The training data set is a set of pre-collected training data, which may include fault operation data, or data of the training bearing during normal operation and its corresponding label. The model of the training bearing is the same as that of the bearing to be detected. Further, in this embodiment, the training bearing is a bearing on a training numerical control machine corresponding to the bearing to be detected, and signals of the training numerical control machine and the numerical control machine where the bearing to be detected are located are the same.
It should be noted that, in this embodiment, since the operation data is corrected by the environment correction data, the working environment of the trained nc machine tool and the operation environment of the nc machine tool where the bearing to be detected is located are not required to be the same during training, so that the fault detection model trained in one working environment can be used for performing fault detection on other nc machine tools to be detected (i.e., the nc machine tool where the bearing to be detected is located) in different working environments, which is beneficial to improving the applicability of the fault detection model.
Specifically, for each fault operation data in the training data set, correction processing is performed through corresponding training environment correction data, then wavelet transformation and data fusion are performed, and after fusion, the data is input into a preset GRU neural network model for training. For the specific processing flow of the fault operation data, the specific processing flow of the operation data may be referred to, and details are not described herein.
It should be noted that, one subband training fused data corresponds to one subband fault class label, and one subband training fused data corresponds to one subband training data, and the subband fault class label corresponding to one subband training fused data is the fault class label occupying the most sample data (i.e., the data of each signal obtained by sampling) among all fault class labels corresponding to the subband training data, or the fault class label appearing the most times in the subband training data.
Specifically, the iteratively training the gated loop unit neural network model according to the subband training fusion data and the subband fault class label includes:
inputting the sub-band training fusion data and the sub-band fault class labels into an ith updated gating cycle unit neural network model, and respectively performing feature extraction on each sub-band training fusion data through the ith updated gating cycle unit neural network model to obtain sub-band features, wherein i is any integer greater than or equal to 0, and the 0 th updated gating cycle unit neural network model is a preset initial gating unit neural network model;
fault identification is carried out on the sub-band characteristics through a preset normalization index (softmax) function, corresponding identification faults are obtained, and loss values between the identification faults and corresponding sub-band fault category labels are calculated according to a preset cross entropy loss function;
when the loss value is larger than a preset loss threshold value, updating the parameters of the gate control cycle unit neural network model after the ith updating by a minimum gradient descent method, and obtaining the gate control cycle unit neural network model after the (i + 1) th updating;
and when the loss value is not greater than the loss threshold value, taking the gate control cycle unit neural network model after the ith updating as the gate control cycle unit neural network model after training.
In this embodiment, through the specific steps of the iterative training, the training is performed sequentially from the 0 th updated gate control cycle unit neural network model, and after the ith updated gate control cycle unit neural network model is trained, the (i + 1) th updated gate control cycle unit neural network model is trained until the trained gate control cycle unit neural network model is obtained. Wherein, the parameters of the initial gate control unit neural network model and the gate control unit neural network model constructed in advance can be preset according to the actual requirements without specific limitation,
it should be noted that, in this embodiment, an iteration threshold is also preset as another condition for finishing training, and i +1 is not greater than the preset iteration threshold. For example, when i +1 is equal to the preset iteration threshold, the obtained (i + 1) th updated gated loop unit neural network model is directly used as the trained gated loop unit neural network model.
Therefore, the GRU can be used for extracting features according to fusion data input into the GRU in the training process, the fusion data is updated, forgotten and learned by using an updating gate and a resetting gate of the GRU, the features output after each training of the GRU are transmitted to a softmax function for fault recognition, loss values of recognized faults and real faults are calculated based on a cross entropy loss function, GRU neural network parameters are updated by using a minimum gradient descent method, and finally a trained fault detection model is obtained. The trained fault detection model can obtain the corresponding fault category according to the input fusion data.
The fault detection result may be any one of a plurality of fault categories, such as normal operation, outer ring fault, inner ring fault, rolling element fault, and the like, and is not specifically limited herein.
Further, after the sub-band fusion data is input into a pre-trained fault detection model and a fault detection result of the bearing to be detected is obtained according to the fault detection model, the method further includes: and acquiring a fault processing scheme corresponding to the fault detection result according to a preset fault processing scheme list and executing the fault processing scheme.
The fault processing scheme list is a preset processing scheme corresponding to different fault categories, and can be set and adjusted according to actual requirements. For example, the fault detection result can be sent to a preset fault warning terminal, so that a user can conveniently know the fault condition of the bearing in time and replace and maintain the bearing; and when the fault type is an outer ring fault, controlling the numerical control machine tool to stop running so as to avoid the numerical control machine tool from being damaged, and the like, wherein the fault type is not specifically limited.
As can be seen from the above, in the method for detecting a bearing fault of a numerical control machine tool provided by the embodiment of the present invention, operation data of a bearing to be detected of the numerical control machine tool and environment correction data corresponding to the bearing to be detected are obtained, where the operation data includes a vibration signal, a current signal and a temperature signal when the bearing to be detected operates, and the environment correction data includes an environment vibration signal, an environment current signal and an environment temperature signal corresponding to when the bearing to be detected stops operating; correcting the operation data according to the environment correction data to obtain corrected operation data corresponding to the bearing to be detected; performing wavelet transformation on the corrected operation data to obtain a plurality of sub-band operation data corresponding to the bearing to be detected; performing data fusion on each sub-band operation data to obtain sub-band fusion data corresponding to each sub-band operation data; and inputting the sub-band fusion data into a pre-trained fault detection model, and acquiring a fault detection result of the bearing to be detected according to the fault detection model. Compared with the scheme of directly detecting the fault of the bearing through the data acquired by the sensor in the prior art, the method and the device for detecting the fault of the bearing further acquire the corresponding environment correction data, correct the operation data of the bearing to be detected according to the environment correction data, and detect the fault of the bearing according to the corrected operation data, so that the method and the device are beneficial to eliminating the influence of complex environment information on the fault detection process of the bearing and improving the accuracy of the fault detection of the bearing.
It should be noted that the bearing fault detection method for the numerical control machine tool can also be used for simultaneously detecting faults of a plurality of bearings to be detected, and in this embodiment, the fault detection of one bearing to be detected is taken as an example, but not specifically limited.
Exemplary device
As shown in fig. 5, an embodiment of the present invention further provides a system for detecting a fault of a bearing of a numerical control machine, corresponding to the method for detecting a fault of a bearing of a numerical control machine, where the system for detecting a fault of a bearing of a numerical control machine includes:
the data acquisition module 610 is configured to acquire operation data of a bearing to be detected of the numerical control machine tool and environment correction data corresponding to the bearing to be detected, where the operation data includes a vibration signal, a current signal and a temperature signal when the bearing to be detected operates, and the environment correction data includes an environment vibration signal, an environment current signal and an environment temperature signal corresponding to when the bearing to be detected stops operating.
The numerical control machine tool can be provided with a plurality of bearings, and each bearing can be subjected to fault detection based on the bearing fault detection system of the numerical control machine tool.
The operation data of the bearing to be detected is obtained by monitoring the bearing to be detected in real time, and can be data acquired by a sensor within a period of monitoring time, and the environment correction data corresponding to the bearing to be detected is obtained by acquiring signals in the environment where the bearing to be detected is located in advance.
And a data correction module 620, configured to correct the operation data according to the environment correction data, so as to obtain corrected operation data corresponding to the bearing to be detected.
Specifically, the operating data can be corrected through the environment correction data, so that the influence of the environment signal on each signal in the operating data is reduced, and the accuracy of fault detection is improved.
And a data transformation module 630, configured to perform wavelet transformation on the corrected operation data to obtain multiple sub-band operation data corresponding to the bearing to be detected.
Specifically, discrete wavelet transform is performed on the corrected operation data, the corrected operation data is divided into a plurality of sub-bands, and a plurality of sub-band operation data corresponding to the bearing to be detected are obtained, wherein each sub-band operation data comprises a sub-band corrected vibration signal, a sub-band corrected current signal and a sub-band corrected temperature signal.
The data fusion module 640 is configured to perform data fusion on each of the subband operating data to obtain subband fusion data corresponding to each of the subband operating data.
Specifically, the subband correction vibration signal, the subband correction current signal, and the subband correction temperature signal in each subband operation data are adaptively weighted and fused to obtain each subband fusion data.
And the fault detection module 650 is configured to input the subband fusion data into a pre-trained fault detection model, and obtain a fault detection result of the bearing to be detected according to the fault detection model.
Specifically, in this embodiment, the specific functions of the bearing fault detection system of the numerical control machine and each module thereof may refer to the corresponding descriptions in the bearing fault detection method of the numerical control machine, and are not described herein again.
It should be noted that, the dividing manner of each module of the above-mentioned bearing fault detection system for a numerical control machine is not unique, and is not limited specifically here.
The embodiment of the invention also provides a computer-readable storage medium, wherein the computer-readable storage medium is stored with a bearing fault detection program of the numerical control machine tool, and the bearing fault detection program of the numerical control machine tool realizes the steps of any bearing fault detection method of the numerical control machine tool provided by the embodiment of the invention when being executed by a processor.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an 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.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned functions may be distributed as different functional units and modules according to needs, that is, the internal structure of the system may be divided into different functional units or modules to implement all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the above embodiments, the description of each embodiment has its own emphasis, and reference may be made to the related description of other embodiments for parts that are not described or recited in any embodiment.
Those of ordinary skill in the art would appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed system/intelligent terminal and method can be implemented in other ways. For example, the above-described system/intelligent terminal embodiments are merely illustrative, and for example, the division of the above modules or units is only one logical function division, and the actual implementation may be implemented by another division, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed.
The integrated modules/units described above, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium and can implement the steps of the embodiments of the method when the computer program is executed by a processor. The computer program includes computer program code, and the computer program code may be in a source code form, an object code form, an executable file or some intermediate form. The computer readable medium may include: any entity or device capable of carrying the above-described computer program code, recording medium, U disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier signal, telecommunications signal, software distribution medium, and the like. It should be noted that the contents contained in the computer-readable storage medium can be increased or decreased as required by legislation and patent practice in the jurisdiction.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those skilled in the art; the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the embodiments of the present invention, and they should be construed as being included therein.
Claims (10)
1. A bearing fault detection method for a numerical control machine tool is characterized by comprising the following steps:
the method comprises the steps of obtaining operation data of a bearing to be detected of the numerical control machine tool and environment correction data corresponding to the bearing to be detected, wherein the operation data comprise a vibration signal, a current signal and a temperature signal when the bearing to be detected operates, and the environment correction data comprise an environment vibration signal, an environment current signal and an environment temperature signal corresponding to the bearing to be detected when the bearing to be detected stops operating;
correcting the operation data according to the environment correction data to obtain corrected operation data corresponding to the bearing to be detected;
performing wavelet transformation on the corrected operation data to obtain a plurality of sub-band operation data corresponding to the bearing to be detected;
performing data fusion on each sub-band operation data respectively to obtain sub-band fusion data corresponding to each sub-band operation data;
and inputting the sub-band fusion data into a pre-trained fault detection model, and acquiring a fault detection result of the bearing to be detected according to the fault detection model.
2. The method for detecting the bearing fault of the numerical control machine tool according to claim 1, wherein the step of acquiring the operation data of one bearing to be detected of the numerical control machine tool and the environment correction data corresponding to the bearing to be detected comprises the following steps:
acquiring vibration signals, current signals and temperature signals of the bearing to be detected during operation in real time through a plurality of preset sensors, and taking the signals as the operation data;
and acquiring an environmental vibration signal, an environmental current signal and an environmental temperature signal which are obtained by measuring through the sensor when the bearing to be detected stops running and other bearings of the numerical control machine tool run in advance, and taking the environmental vibration signal, the environmental current signal and the environmental temperature signal as the environmental correction data.
3. The method for detecting the bearing fault of the numerical control machine according to claim 1, wherein the step of correcting the operation data according to the environment correction data to obtain corrected operation data corresponding to the bearing to be detected comprises the following steps:
acquiring the running time length corresponding to the running data and the measuring time length corresponding to the environment correction data;
adjusting the environment correction data according to the running time length and the measurement time length and obtaining target correction data, wherein the time length corresponding to the target correction data is the same as the running time length;
and subtracting a corresponding signal in the target correction data from a signal in the operation data to obtain the corrected operation data, wherein the corrected operation data comprises a corrected vibration signal, a corrected current signal and a corrected temperature signal.
4. The method for detecting bearing faults of numerical control machine tools according to claim 3, wherein the adjusting the environment correction data according to the running time length and the measuring time length and obtaining target correction data comprises:
acquiring a segmentation time length and a preset segmentation number, wherein the segmentation time length is an absolute value of a difference between the running time length and the measurement time length;
when the running time length is smaller than the measuring time length, randomly selecting a segmentation number of segments to be deleted from the environment correction data and deleting the segments to obtain the target correction data, wherein the sum of the time lengths of the segments to be deleted is equal to the segmentation time length;
and when the running time length is greater than the measuring time length, randomly selecting a segment number of segments to be added from the environment correction data and adding the segments to the environment correction data to obtain the target correction data, wherein the sum of the time lengths of the segments to be added is equal to the segment time length.
5. The method for detecting the bearing fault of the numerical control machine tool according to claim 3, wherein the step of performing wavelet transformation on the corrected operation data to obtain a plurality of sub-band operation data corresponding to the bearing to be detected comprises the following steps:
and performing discrete wavelet transformation on the corrected operation data, dividing the corrected operation data into a plurality of sub-bands and obtaining a plurality of sub-band operation data corresponding to the bearing to be detected, wherein each sub-band operation data comprises a sub-band corrected vibration signal, a sub-band corrected current signal and a sub-band corrected temperature signal.
6. The method for detecting bearing faults of a numerical control machine according to claim 5, wherein the step of respectively performing data fusion on each sub-band operation data to obtain sub-band fusion data corresponding to each sub-band operation data comprises the following steps:
and respectively carrying out self-adaptive weighted fusion on the sub-band correction vibration signal, the sub-band correction current signal and the sub-band correction temperature signal in each sub-band operation data to obtain each sub-band fusion data.
7. The method for detecting bearing faults of a numerically-controlled machine tool according to any one of claims 1 to 6, wherein the fault detection model is a gated cyclic unit neural network model, and the gated cyclic unit neural network model is trained in advance through the following steps:
acquiring a training data set, wherein the training data set comprises a plurality of fault operation data, training environment correction data corresponding to each fault operation data and a fault category label corresponding to each fault operation data, each fault operation data comprises a training vibration signal, a training current signal and a training temperature signal when a training bearing operates, and the training environment correction data comprises a training environment vibration signal, a training environment current signal and a training environment temperature signal corresponding to when the training bearing stops operating;
correcting the fault operation data according to the training environment correction data to obtain training correction fault data corresponding to the training bearing;
performing wavelet transformation on the training corrected fault data to obtain a plurality of sub-band training data corresponding to the training bearing;
respectively carrying out data fusion on each sub-band training data to obtain sub-band training fusion data corresponding to each sub-band training data and obtain sub-band fault category labels corresponding to each sub-band training fusion data;
and performing iterative training on the gated circulation unit neural network model according to the subband training fusion data and the subband fault class label, and taking the trained gated circulation unit neural network model as the fault detection model.
8. The method for detecting the bearing fault of the numerical control machine tool according to claim 7, wherein the iteratively training the gated cyclic unit neural network model according to the subband training fusion data and the subband fault class label comprises:
inputting the sub-band training fusion data and the sub-band fault class labels into the ith updated gating cycle unit neural network model, and respectively performing feature extraction on each sub-band training fusion data through the ith updated gating cycle unit neural network model to obtain sub-band features, wherein i is any integer larger than or equal to 0, and the 0 th updated gating cycle unit neural network model is a preset initial gating unit neural network model;
fault identification is carried out on the sub-band characteristics through a preset normalization index function, corresponding identification faults are obtained, and loss values between the identification faults and corresponding sub-band fault category labels are calculated according to a preset cross entropy loss function;
when the loss value is larger than a preset loss threshold value, updating the parameters of the neural network model of the gating cycle unit after the ith updating by a minimum gradient descent method, and obtaining the neural network model of the gating cycle unit after the (i + 1) th updating;
and when the loss value is not greater than the loss threshold value, taking the gate control cycle unit neural network model after the ith updating as the gate control cycle unit neural network model after training.
9. The method for detecting the bearing fault of the numerical control machine tool according to claim 1, wherein after the sub-band fusion data is input into a fault detection model trained in advance and the fault detection result of the bearing to be detected is obtained according to the fault detection model, the method further comprises the following steps:
and acquiring a fault processing scheme corresponding to the fault detection result according to a preset fault processing scheme list and executing the fault processing scheme.
10. The utility model provides a digit control machine tool bearing fault detection system which characterized in that, digit control machine tool bearing fault detection system includes:
the data acquisition module is used for acquiring operation data of a bearing to be detected of the numerical control machine tool and environment correction data corresponding to the bearing to be detected, wherein the operation data comprises a vibration signal, a current signal and a temperature signal when the bearing to be detected operates, and the environment correction data comprises an environment vibration signal, an environment current signal and an environment temperature signal corresponding to the bearing to be detected when the bearing to be detected stops operating;
the data correction module is used for correcting the operation data according to the environment correction data to obtain corrected operation data corresponding to the bearing to be detected;
the data transformation module is used for performing wavelet transformation on the corrected operation data to obtain a plurality of sub-band operation data corresponding to the bearing to be detected;
the data fusion module is used for respectively carrying out data fusion on each sub-band operation data to obtain sub-band fusion data corresponding to each sub-band operation data;
and the fault detection module is used for inputting the sub-band fusion data into a pre-trained fault detection model and acquiring a fault detection result of the bearing to be detected according to the fault detection model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210415151.8A CN114742108B (en) | 2022-04-20 | 2022-04-20 | Method and system for detecting fault of bearing of numerical control machine tool |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210415151.8A CN114742108B (en) | 2022-04-20 | 2022-04-20 | Method and system for detecting fault of bearing of numerical control machine tool |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114742108A true CN114742108A (en) | 2022-07-12 |
| CN114742108B CN114742108B (en) | 2022-12-20 |
Family
ID=82283171
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210415151.8A Active CN114742108B (en) | 2022-04-20 | 2022-04-20 | Method and system for detecting fault of bearing of numerical control machine tool |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114742108B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118194206A (en) * | 2024-05-15 | 2024-06-14 | 深圳市盛格纳电子有限公司 | Intelligent fault diagnosis method and system for production equipment |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108227676A (en) * | 2017-12-28 | 2018-06-29 | 浙江工业大学 | The online fault detect of valve-controlled cylinder electrohydraulic servo system, estimation and localization method |
| CN110471376A (en) * | 2019-07-10 | 2019-11-19 | 深圳市乾行达科技有限公司 | A kind of industry spot fault detection method and equipment |
| CN110738717A (en) * | 2019-10-16 | 2020-01-31 | 网易（杭州）网络有限公司 | Method and device for correcting motion data and electronic equipment |
| CN111209891A (en) * | 2020-01-15 | 2020-05-29 | 佛山科学技术学院 | Deep neural network-based bearing working condition detection method and system |
| CN111695618A (en) * | 2020-06-01 | 2020-09-22 | 清华大学深圳国际研究生院 | Electric vehicle motor fault detection method based on OBD data |
| CN111947928A (en) * | 2020-08-10 | 2020-11-17 | 山东大学 | Multi-source information fusion bearing fault prediction system and method |
| CN113176092A (en) * | 2021-04-25 | 2021-07-27 | 江苏科技大学 | Motor bearing fault diagnosis method based on data fusion and improved experience wavelet transform |
| CN113221280A (en) * | 2021-05-14 | 2021-08-06 | 西安交通大学 | Rolling bearing modeling and model updating method and system based on digital twinning |
| CN113670610A (en) * | 2021-06-09 | 2021-11-19 | 广州大学 | Fault detection method, system and medium based on wavelet transformation and neural network |
| CN113902946A (en) * | 2021-10-08 | 2022-01-07 | 武汉大学 | Power system fault direction judging method and device, terminal equipment and storage medium |
| CN113933054A (en) * | 2021-09-23 | 2022-01-14 | 吴江万工机电设备有限公司 | Rolling bearing fault monitoring and diagnosing method, equipment, medium and processor |
| CN114004262A (en) * | 2021-11-29 | 2022-02-01 | 华东交通大学 | Gearbox bearing fault detection method and system |
-
2022
- 2022-04-20 CN CN202210415151.8A patent/CN114742108B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108227676A (en) * | 2017-12-28 | 2018-06-29 | 浙江工业大学 | The online fault detect of valve-controlled cylinder electrohydraulic servo system, estimation and localization method |
| CN110471376A (en) * | 2019-07-10 | 2019-11-19 | 深圳市乾行达科技有限公司 | A kind of industry spot fault detection method and equipment |
| CN110738717A (en) * | 2019-10-16 | 2020-01-31 | 网易（杭州）网络有限公司 | Method and device for correcting motion data and electronic equipment |
| CN111209891A (en) * | 2020-01-15 | 2020-05-29 | 佛山科学技术学院 | Deep neural network-based bearing working condition detection method and system |
| CN111695618A (en) * | 2020-06-01 | 2020-09-22 | 清华大学深圳国际研究生院 | Electric vehicle motor fault detection method based on OBD data |
| CN111947928A (en) * | 2020-08-10 | 2020-11-17 | 山东大学 | Multi-source information fusion bearing fault prediction system and method |
| CN113176092A (en) * | 2021-04-25 | 2021-07-27 | 江苏科技大学 | Motor bearing fault diagnosis method based on data fusion and improved experience wavelet transform |
| CN113221280A (en) * | 2021-05-14 | 2021-08-06 | 西安交通大学 | Rolling bearing modeling and model updating method and system based on digital twinning |
| CN113670610A (en) * | 2021-06-09 | 2021-11-19 | 广州大学 | Fault detection method, system and medium based on wavelet transformation and neural network |
| CN113933054A (en) * | 2021-09-23 | 2022-01-14 | 吴江万工机电设备有限公司 | Rolling bearing fault monitoring and diagnosing method, equipment, medium and processor |
| CN113902946A (en) * | 2021-10-08 | 2022-01-07 | 武汉大学 | Power system fault direction judging method and device, terminal equipment and storage medium |
| CN114004262A (en) * | 2021-11-29 | 2022-02-01 | 华东交通大学 | Gearbox bearing fault detection method and system |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118194206A (en) * | 2024-05-15 | 2024-06-14 | 深圳市盛格纳电子有限公司 | Intelligent fault diagnosis method and system for production equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114742108B (en) | 2022-12-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7105932B2 (en) | Anomaly detection using deep learning on time series data related to application information | |
| CN113328908B (en) | Abnormal data detection method and device, computer equipment and storage medium | |
| CN115580445B (en) | Unknown attack intrusion detection method, unknown attack intrusion detection device and computer readable storage medium | |
| CN110333078B (en) | Rolling bearing degradation state stage determination method | |
| CN114742108B (en) | Method and system for detecting fault of bearing of numerical control machine tool | |
| JP7548843B2 (en) | Anomaly Degree Calculation System and Method | |
| CN118154174B (en) | Intelligent operation and maintenance cloud platform for industrial equipment | |
| CN114091553A (en) | Diagnosis method for rolling bearing fault | |
| CN112465001B (en) | Classification method and device based on logistic regression | |
| CN116910493A (en) | Construction method and device of equipment fault diagnosis model based on multi-source feature extraction | |
| CN116956197B (en) | Deep learning-based energy facility fault prediction method and device and electronic equipment | |
| CN114690706A (en) | Error prediction compensation method and system for spindle of numerical control machine tool | |
| CN116976530B (en) | Cable equipment state prediction method, device and storage medium | |
| CN115841278B (en) | Method, system, equipment and medium for evaluating running error state of electric energy metering device | |
| CN114372324B (en) | Method and equipment for predicting service degradation track of key parts of rotary mechanical equipment | |
| CN112738098A (en) | Anomaly detection method and device based on network behavior data | |
| CN112202630A (en) | Network quality abnormity detection method and device based on unsupervised model | |
| CN116451081A (en) | Data drift detection method, device, terminal and storage medium | |
| CN118093290A (en) | Method, device, equipment and medium for detecting server heat dissipation abnormality | |
| CN112380073B (en) | Fault position detection method and device and readable storage medium | |
| CN117435937A (en) | Smart electric meter abnormal data identification method, device, equipment and storage medium | |
| CN115758086A (en) | Method, device and equipment for detecting faults of cigarette cut-tobacco drier and readable storage medium | |
| CN113747270B (en) | Cloud data center thing allies oneself with management and control system | |
| CN116150666B (en) | Energy storage system fault detection method and device and intelligent terminal | |
| CN118033219B (en) | Power utilization management method and system based on AI current fingerprint |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |