CN114925614A - Method for predicting residual life of coal mining machine - Google Patents
Method for predicting residual life of coal mining machine Download PDFInfo
- Publication number
- CN114925614A CN114925614A CN202210591322.2A CN202210591322A CN114925614A CN 114925614 A CN114925614 A CN 114925614A CN 202210591322 A CN202210591322 A CN 202210591322A CN 114925614 A CN114925614 A CN 114925614A
- Authority
- CN
- China
- Prior art keywords
- mining machine
- coal mining
- health index
- health
- initial
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
- G06F2218/04—Denoising
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method for predicting the residual life of a coal mining machine, and belongs to the field of coal mine intellectualization. The method comprises the following steps: acquiring initial multi-source signals respectively acquired in each operation process of a coal mining machine; preprocessing the initial multi-source signal acquired in each operation process to obtain a target multi-source signal of each operation process; extracting a health index feature vector in each target multi-source signal; combining the health index characteristic vectors in the target multi-source signals to obtain a health index characteristic matrix of the coal mining machine; and inputting the health index characteristic matrix into a pre-trained residual life prediction model of the coal mining machine to obtain the residual life of the coal mining machine. The invention provides a method for predicting the residual life of a coal mining machine in real time, which has important significance on the operational reliability and safety of the coal mining machine.
Description
Technical Field
The invention relates to the technical field of coal mine intellectualization, in particular to a method for predicting the residual life of a coal mining machine.
Background
With the development of coal mine intelligent technology, the requirements of coal mines on the reliability of fully mechanized mining equipment are continuously improved. The coal mining machine is one of the core devices for coal mining, and the operation stability and the operation rate of the coal mining machine directly determine the safety and the production efficiency of the whole coal mine. However, since the coal mining machine is in a variable working condition environment for a long time and is influenced by an impact load, a fault of the coal mining machine occurs sometimes, which poses a serious threat to the safety production of the coal mine and the life safety of workers, so that it is very important to carry out a residual service life prediction research on the coal mining machine, and the residual service life prediction of the coal mining machine aims at predicting the residual service life (RUL) of the coal mining machine according to a continuous degradation trend observed from state monitoring information.
The residual service life prediction research is carried out on the coal mining machine, so that the reliability of the coal mining machine can be greatly improved, unnecessary halt is avoided, the maximum working capacity of the coal mining machine is ensured, and the method has important significance for ensuring the operation reliability and safety of the coal mining machine. Therefore, it is necessary to provide a method for predicting the remaining life of a shearer.
Disclosure of Invention
In order to solve the technical problem, the invention provides a method for predicting the residual life of a coal mining machine. The technical scheme adopted by the invention is as follows:
a method for predicting the residual life of a coal mining machine comprises the following steps:
s1, acquiring initial multi-source signals respectively acquired in each operation process of the coal mining machine;
s2, preprocessing the initial multi-source signal collected in each operation process to obtain a target multi-source signal in each operation process;
s3, extracting the health index feature vector in each target multi-source signal;
s4, combining the health index feature vectors in the target multi-source signals to obtain a health index feature matrix of the coal mining machine;
and S5, inputting the health index characteristic matrix into a pre-trained residual life prediction model of the coal mining machine to obtain the residual life of the coal mining machine.
Optionally, before inputting the health index feature matrix into the pre-trained remaining life prediction model of the coal mining machine, the S5 further includes:
s51, acquiring a health index feature set determined according to initial multi-source signals acquired in the historical operation process of the coal mining machine;
s52, dividing the health index features in the health index feature set into a training set and a verification set;
s53, performing cluster analysis on the target health index characteristics in the training set and the verification set respectively to divide the health stage of the coal mining machine into three health stages, namely a stable operation stage, an initial degradation stage and an accelerated degradation stage;
s54, respectively calculating the identifiability indexes between all the health index features and the health stages in the training set and the verification set, and screening the health index features in the training set and the verification set according to the calculation result to obtain a representative health index feature matrix;
s55, calculating the remaining service life and the health state of the coal mining machine according to the health stage;
s56, fitting a training set degradation curve family and a verification set degradation curve family of the coal mining machine according to the representative health index characteristic matrix and the health state of the training set and the verification set respectively;
s57, calculating the distance and the similarity between each degradation curve in the training set degradation curve family and each degradation curve in the verification set degradation curve family, and screening a plurality of groups of degradation curves which are most similar to the degradation curves in the verification set degradation curve family from the training set degradation curve family according to the distance and the similarity to serve as a residual life prediction set;
and S58, obtaining the residual life of each degradation curve in the residual life prediction set, and giving a weight to the residual life of each degradation curve in the residual life prediction set according to the similarity to obtain a residual life prediction model of the coal mining machine.
Optionally, when the health index feature set determined according to the initial multi-source signal acquired during the historical operation process of the coal mining machine is acquired in the S51, the method includes:
s511, acquiring initial multi-source signals respectively acquired in each historical operation process of the coal mining machine;
s512, preprocessing the initial multi-source signal acquired in each historical running process to obtain a target multi-source signal in each historical running process;
s513, extracting the health index characteristic vector in each target multi-source signal, and combining the health index characteristic vectors in each target multi-source signal to obtain the health index characteristic set of the coal mining machine.
Optionally, the S52, when dividing the health index features in the health index feature set into a training set and a verification set, includes:
s521, performing Z-Score standardization processing on the health index features in the health index feature set;
and S522, dividing the health index feature set subjected to the standardization treatment into a training set and a verification set by adopting a k-fold cross verification method.
Optionally, the target health indicator characteristic is root mean square.
Optionally, the S54 is implemented by the following formula when calculating the identifiability indexes between all the health index features and the health phases in the training set and the verification set respectively:
wherein:
is a matrix of inter-class scatter,
is an intra-class scattering matrix, n s Is the number of samples of the s-th class, m s Is the mean of the health indicator features of class s, m being the average of all the health indicator featuresThe mean value, Ω, represents the set of health index features of the s-th class.
Optionally, the S55 is implemented by the following formula when calculating the remaining life and the health state of the shearer according to the health stage:
wherein:
the service life of the glass is prolonged to the maximum,
to accelerate the initial residual life of the degradation phase; epsilon (t) is random noise and conforms to normal distribution with the mean value of 0; theta (t) is the slope of the initial degradation stage and conforms to normal distribution with the mean value of theta; theta.theta. 0 (t) logarithmic normal distribution with mean theta, beta (t) normal distribution with mean beta, sigma 2 Is the variance of the noise; HS is 0,1,2 respectively represent that the healthy stage is a smooth operation stage, an initial degradation stage and an accelerated degradation stage, RUL is the remaining life, and HD is the healthy state.
Optionally, the initial multi-source signal includes an initial vibration signal, an initial temperature signal, and an initial current signal.
Optionally, when the S2 preprocesses the multi-source signal collected in each operation process to obtain the target multi-source signal in each operation process, the method includes:
s21, performing drying and filtering processing on the initial vibration signal acquired in each operation process to obtain a target vibration signal of each operation process;
and S22, carrying out abnormal value processing on the initial temperature signal and the initial current signal acquired in each operation process to obtain a target temperature signal and a target current signal in each operation process.
Optionally, the S3, when extracting the health indicator feature vector in each target multi-source signal, includes:
s31, extracting a time domain feature vector, a frequency domain feature vector and a time frequency domain feature vector of the target vibration signal as a health index feature vector of the target vibration signal, wherein the time domain feature vector comprises vibration variance, skewness, a peak factor, kurtosis, a peak value, a kurtosis factor, an average value, a wave form factor, a skewness factor, a standard deviation and a root mean square, the frequency domain feature vector comprises amplitude average value, frequency variance, center of gravity frequency, root mean square frequency, mean square frequency and frequency amplitude variance, and the time frequency domain feature vector comprises Hilbert yellow spectrogram interval mean variance;
s32, extracting the maximum temperature value, the minimum temperature value, the mean temperature value and the temperature variance as the health index feature vector of the target temperature signal;
and S33, extracting the current maximum value, the current minimum value, the current mean value, the current variance and the current effective value as the health index feature vector of the target current signal.
The invention has the beneficial effects that:
the method for predicting the residual life of the coal mining machine in real time is provided by pre-training a residual life prediction model of the coal mining machine, acquiring initial multi-source signals in each operation process of the coal mining machine in the operation process of the coal mining machine and pre-training the residual life prediction model of the coal mining machine on the basis of the acquired initial multi-source signals.
Drawings
FIG. 1 is a flow chart of the present invention.
FIG. 2 is a diagram of a health indicator feature vector and a health indicator feature matrix in a target multi-source signal.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples.
As shown in fig. 1, a method for predicting the remaining life of a coal mining machine in the present embodiment includes the following steps:
and S1, acquiring initial multi-source signals respectively acquired in each operation process of the coal mining machine.
Wherein each operation process can be a process from starting to stopping of the coal mining machine for multiple times. The initial multi-source signal includes an initial vibration signal, an initial temperature signal, and an initial current signal. When the initial multi-source signal is obtained, the initial multi-source signal can be obtained from a vibration sensor, a temperature sensor and an ammeter which are arranged on a coal mining machine.
By acquiring initial multi-source signals acquired in each operation process of the coal mining machine, state data acquired in multiple operation processes of the coal mining machine can be acquired, multiple groups of state data capable of indicating the operation states of the coal mining machine are acquired, and high accuracy of residual life prediction of the coal mining machine according to the state data is ensured.
And S2, preprocessing the initial multi-source signals acquired in each operation process to obtain target multi-source signals in each operation process.
On the basis of the initial multi-source signal type, when the multi-source signal acquired in each operation process is preprocessed by the S2 to obtain a target multi-source signal of each operation process, the method includes the following steps:
and S21, performing drying filtering processing on the initial vibration signal acquired in each operation process to obtain a target vibration signal of each operation process.
And S22, carrying out abnormal value processing on the initial temperature signal and the initial current signal acquired in each operation process to obtain a target temperature signal and a target current signal in each operation process.
Through preprocessing, the initial multi-source signal which obviously does not have research value can be removed, so that the data volume of the initial multi-source signal can be reduced, invalid calculation is reduced, and the calculation efficiency is improved.
And S3, extracting the health index feature vector in each target multi-source signal.
On the basis of S1 and S2, when extracting the health index feature vector in each target multi-source signal, the S3 includes the following steps:
s31, extracting a time domain feature vector, a frequency domain feature vector and a time-frequency domain feature vector of the target vibration signal as a health index feature vector of the target vibration signal, wherein the time domain feature vector comprises vibration variance, skewness, a peak factor, kurtosis, a peak value, a kurtosis factor, an average value, a wave form factor, a skewness factor, a standard deviation and a root mean square, the frequency domain feature vector comprises amplitude average value, frequency variance, center of gravity frequency, root mean square frequency, mean square frequency and frequency amplitude variance, and the time-frequency domain feature vector comprises Hilbert yellow spectrogram interval mean value variance.
When extracting the frequency domain feature vector, the frequency domain feature vector can be obtained by performing fourier transform on the target vibration signal. When the frequency domain feature vector is extracted, the frequency domain feature vector can be obtained by performing time-frequency joint processing on the target vibration signal based on Empirical Mode Decomposition (EMD) and Hilbert-Huang transform (HHT).
And S32, extracting the maximum temperature value, the minimum temperature value, the mean temperature value and the temperature variance as the health index feature vector of the target temperature signal.
And S33, extracting the current maximum value, the current minimum value, the current mean value, the current variance and the current effective value as the health index feature vector of the target current signal.
And S4, combining the health index characteristic vectors in the target multi-source signals to obtain a health index characteristic matrix of the coal mining machine.
Fig. 2 is a schematic diagram of a feature vector and a health index feature matrix in a target multi-source signal. Each column in the health indicator feature matrix shown in fig. 2 includes an acquisition time (ti) of a target multi-source signal and a health indicator feature vector (xij) in the target multi-source signal.
And S5, inputting the health index characteristic matrix into a pre-trained residual life prediction model of the coal mining machine to obtain the residual life of the coal mining machine.
The residual service life of the coal mining machine can be predicted through the steps. However, before predicting the remaining life of the coal mining machine through the residual life prediction model of the coal mining machine and the health index feature matrix, the residual life prediction model of the coal mining machine needs to be trained, and the following description will describe a training process of the residual life prediction model of the coal mining machine. Specifically, when training the residual life prediction model of the coal mining machine, the method comprises the following steps:
and S51, acquiring a health index feature set determined according to the initial multi-source signals acquired in the historical operation process of the coal mining machine.
The method for determining the health index feature set comprises the following steps of S51, wherein when the health index feature set determined according to initial multi-source signals collected in the historical operation process of the coal mining machine is obtained:
and S511, acquiring initial multi-source signals respectively acquired in each historical operation process of the coal mining machine.
S512, preprocessing the initial multi-source signals acquired in each historical running process to obtain target multi-source signals in each historical running process.
S513, extracting the health index characteristic vector in each target multi-source signal, and combining the health index characteristic vectors in each target multi-source signal to obtain the health index characteristic set of the coal mining machine.
Specifically, the principle of steps S511 to S513 is the same as that of steps S1 to S4, and reference may be made to the contents of steps S1 to S4, which are not described herein again.
And S52, dividing the health index features in the health index feature set into a training set and a verification set.
Wherein, when the health index features in the health index feature set are divided into a training set and a verification set, the S52 includes the following steps:
and S521, performing Z-Score standardization processing on the health index features in the health index feature set so as to uniformly measure the health index features of different magnitudes by uniformly using the calculated Z-Score values.
And S522, dividing the health index feature set subjected to the standardization treatment into a training set and a verification set by adopting a k-fold cross verification method.
And S53, performing cluster analysis on the target health index characteristics in the training set and the verification set respectively to divide the health stage of the coal mining machine into three health stages, namely a stable operation stage, an initial degradation stage and an accelerated degradation stage.
Wherein the target health indicator characteristic includes, but is not limited to, root mean square. Simulation tests show that the target health index features are selected to be root mean square, so that the divided health stages are accurate.
And S54, respectively calculating the identifiability indexes between all the health index characteristics in the training set and the verification set and the health stage, and screening the health index characteristics in the training set and the verification set according to the calculation result to obtain a representative health index characteristic matrix.
Specifically, when calculating the identifiability indexes between all the health index features and the health phases in the training set and the verification set respectively, the S54 may be implemented by the following formula:
wherein:
is a matrix of inter-class scatter,
is an intra-class scattering matrix, n s Is the number of samples of class s, m s The s-th class is the mean value of the health index features, m is the mean value of all the health index features, and Ω represents the health index feature set of the s-th class.
Further, when the health index features in the training set and the verification set are screened according to the calculation result, the calculated identifiable indexes can be sorted, and a plurality of health index features arranged at the tail end can be removed according to the requirement. For example, when the identifiability indexes between the maximum current value, the minimum current value, the maximum temperature value, the minimum temperature value and the health stage are ranked behind the identifiability indexes of other health index features, the health index features are proved to have smaller influence on the health stage, and can be filtered from the training set and the verification set so as to simplify the training set and the verification set and reduce invalid calculation.
And S55, calculating the remaining service life and the health state of the coal mining machine according to the health stage.
Wherein, when calculating the remaining life and the health state of the shearer according to the health stage, the S55 can be realized by the following formula:
wherein:
the service life of the glass is prolonged to the maximum,
to accelerate the initial residual life of the degradation stage; epsilon (t) is random noise and conforms to normal distribution with the mean value of 0; theta (t) is the slope of the initial degradation stage and conforms to normal distribution with the mean value of theta; theta 0 (t) is in accordance with a lognormal distribution with mean theta, beta (t) is in accordance with a normal distribution with mean beta, sigma 2 Is the noise variance; HS 0,1 and 2 respectively represent the healthy stage as the steady operation stage, the initial degradation stage and the accelerated degradation stage, RUL is the residual life, and HD is healthyStatus.
And S56, fitting a training set degradation curve family and a verification set degradation curve family of the coal mining machine according to the representative health index characteristic matrix and the health state of the training set and the verification set respectively.
According to the formula (4), the health state of the coal mining machine is always 1 in the stable operation stage, then gradually decays to 0 along with the degradation of the coal mining machine, the health state HD is used as output, the representative health index characteristic matrixes of the training set and the verification set obtained by screening in S54 are used as input, the input and the output are fitted in sections according to the health stage, and smoothing is carried out to obtain a training set degradation curve family and a verification set degradation curve family of the coal mining machine.
And S57, calculating the distance and the similarity between each degradation curve in the training set degradation curve family and each degradation curve in the verification set degradation curve family, and screening a plurality of groups of degradation curves which are most similar to the degradation curves in the verification set degradation curve family from the training set degradation curve family according to the distance and the similarity to serve as the residual life prediction set.
The distance can be calculated by adopting an Euclidean distance equidistance calculation formula. The similarity is calculated by using a similarity algorithm. The number of degradation curves in the remaining life prediction set may be selected as desired. The degradation curves in the residual life prediction set are a plurality of degradation curves with the minimum distance and the maximum similarity between the training set and the verification set degradation curve family.
And S58, obtaining the residual life of each degradation curve in the residual life prediction set, and giving a weight to the residual life of each degradation curve in the residual life prediction set according to the similarity to obtain a residual life prediction model of the coal mining machine.
The remaining life of each degradation curve in the remaining life prediction set may be obtained from the degradation curve. The sum of the weights of all the degradation curves in the remaining life prediction set is 1, and the degradation curve with higher similarity has higher weight.
According to the embodiment of the invention, a coal mining machine degradation curve family is constructed according to initial multi-source data of a plurality of groups of coal mining machines of the same type in the operation process, and the remaining life of the coal mining machine is predicted by calculating a distance and similarity screening verification set and giving a weight. A coal mining machine subsection degradation model is provided according to theoretical analysis and on-site actual experience, the degradation process of the coal mining machine is scientifically and reasonably summarized, and a new thought is provided for residual life prediction and health management of the coal mining machine.
It will be understood that the above embodiments are merely exemplary embodiments taken to illustrate the principles of the present invention, which is not limited thereto. It will be apparent to those skilled in the art that various modifications and improvements can be made without departing from the spirit and scope of the invention, and such modifications and improvements are also considered to be within the scope of the invention.
Claims (10)
1. A method for predicting the residual life of a coal mining machine is characterized by comprising the following steps:
s1, acquiring initial multi-source signals respectively acquired in each operation process of the coal mining machine;
s2, preprocessing the initial multi-source signals acquired in each operation process to obtain target multi-source signals in each operation process;
s3, extracting the health index feature vector in each target multi-source signal;
s4, combining the health index feature vectors in each target multi-source signal to obtain a health index feature matrix of the coal mining machine;
and S5, inputting the health index characteristic matrix into a pre-trained residual life prediction model of the coal mining machine to obtain the residual life of the coal mining machine.
2. The method for predicting the residual life of the coal mining machine according to claim 1, wherein the S5 further comprises, before inputting the health index feature matrix into a pre-trained residual life prediction model of the coal mining machine:
s51, acquiring a health index feature set determined according to initial multi-source signals acquired in the historical operation process of the coal mining machine;
s52, dividing the health index features in the health index feature set into a training set and a verification set;
s53, performing cluster analysis on the target health index characteristics in the training set and the verification set respectively to divide the health stage of the coal mining machine into three health stages, namely a stable operation stage, an initial degradation stage and an accelerated degradation stage;
s54, respectively calculating the identifiability indexes between all the health index features and the health stages in the training set and the verification set, and screening the health index features in the training set and the verification set according to the calculation result to obtain a representative health index feature matrix;
s55, calculating the remaining service life and the health state of the coal mining machine according to the health stage;
s56, fitting a training set degradation curve family and a verification set degradation curve family of the coal mining machine according to the representative health index characteristic matrix and the health state of the training set and the verification set respectively;
s57, calculating the distance and the similarity between each degradation curve in the training set degradation curve family and each degradation curve in the verification set degradation curve family, and screening a plurality of groups of degradation curves which are most similar to the degradation curves in the verification set degradation curve family from the training set degradation curve family according to the distance and the similarity to serve as a residual life prediction set;
and S58, obtaining the residual life of each degradation curve in the residual life prediction set, and giving a weight to the residual life of each degradation curve in the residual life prediction set according to the similarity to obtain a residual life prediction model of the coal mining machine.
3. The method for predicting the residual life of the coal mining machine according to claim 2, wherein the step S51, when obtaining the health index feature set determined according to the initial multi-source signals collected during the historical operation process of the coal mining machine, comprises the following steps:
s511, acquiring initial multi-source signals respectively acquired in each historical operation process of the coal mining machine;
s512, preprocessing the initial multi-source signal acquired in each historical running process to obtain a target multi-source signal in each historical running process;
s513, extracting the health index characteristic vector in each target multi-source signal, and combining the health index characteristic vectors in each target multi-source signal to obtain the health index characteristic set of the coal mining machine.
4. The method for predicting the remaining life of the coal mining machine according to claim 2, wherein the S52, when dividing the health index features in the health index feature set into a training set and a verification set, includes:
s521, performing Z-Score standardization processing on the health index features in the health index feature set;
and S522, dividing the health index feature set subjected to the standardization treatment into a training set and a verification set by adopting a k-fold cross verification method.
5. The method for predicting the remaining life of a coal mining machine according to claim 2, wherein the target health indicator is characterized by a root mean square.
6. The method for predicting the remaining life of the coal mining machine according to claim 2, wherein the step S54 is implemented by the following formula when calculating the identifiability indexes between all the health index features and the health stages in the training set and the verification set respectively:
wherein:
is an inter-class scatter matrix that is,
is an intra-class scattering matrix, n s Is the number of samples of the s-th class, m s The s-th class is the mean value of the health index features, m is the mean value of all the health index features, and Ω represents the health index feature set of the s-th class.
7. The method for predicting the remaining life of a shearer according to claim 2, wherein the S55 is implemented by the following formula when calculating the remaining life and the health state of the shearer according to the health stage:
wherein:
the service life of the glass is prolonged to the maximum,
to accelerate the initial residual life of the degradation phase; epsilon (t) is random noise and conforms to normal distribution with the mean value of 0; theta (t) is the slope of the initial degradation stage and conforms to normal distribution with the mean value of theta; theta 0 (t) is in accordance with a lognormal distribution with mean theta, beta (t) is in accordance with a normal distribution with mean beta, sigma 2 Is the variance of the noise; HS is 0,1,2 respectively represents that the healthy stage is a smooth operation stage, an initial degradation stage and an accelerated degradation stage, RUL is the remaining life, and HD is the healthy state.
8. The method for predicting the remaining life of a shearer according to claim 1, wherein the initial multi-source signal comprises an initial vibration signal, an initial temperature signal and an initial current signal.
9. The method for predicting the remaining life of the coal mining machine according to claim 8, wherein the S2, when preprocessing the multi-source signal collected in each operation process to obtain the target multi-source signal of each operation process, includes:
s21, performing drying and filtering processing on the initial vibration signal acquired in each operation process to obtain a target vibration signal of each operation process;
and S22, carrying out abnormal value processing on the initial temperature signal and the initial current signal acquired in each operation process to obtain a target temperature signal and a target current signal in each operation process.
10. The method for predicting the residual life of the coal mining machine according to claim 9, wherein the S3, when extracting the health index feature vector in each target multi-source signal, comprises:
s31, extracting a time domain feature vector, a frequency domain feature vector and a time-frequency domain feature vector of the target vibration signal as a health index feature vector of the target vibration signal, wherein the time domain feature vector comprises vibration variance, skewness, a peak factor, kurtosis, a peak value, a kurtosis factor, an average value, a wave form factor, a skewness factor, a standard deviation and a root mean square, the frequency domain feature vector comprises amplitude average value, frequency variance, center of gravity frequency, root mean square frequency, mean square frequency and frequency amplitude variance, and the time-frequency domain feature vector comprises Hilbert yellow spectrogram interval mean variance;
s32, extracting the maximum temperature value, the minimum temperature value, the mean temperature value and the temperature variance as the health index feature vector of the target temperature signal;
and S33, extracting the current maximum value, the current minimum value, the current mean value, the current variance and the current effective value as the health index feature vector of the target current signal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210591322.2A CN114925614A (en) | 2022-05-27 | 2022-05-27 | Method for predicting residual life of coal mining machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210591322.2A CN114925614A (en) | 2022-05-27 | 2022-05-27 | Method for predicting residual life of coal mining machine |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114925614A true CN114925614A (en) | 2022-08-19 |
Family
ID=82811277
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210591322.2A Pending CN114925614A (en) | 2022-05-27 | 2022-05-27 | Method for predicting residual life of coal mining machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114925614A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115470717A (en) * | 2022-10-31 | 2022-12-13 | 四川工程职业技术学院 | Method, device, equipment and storage medium for predicting remaining life of robot |
| CN116825243A (en) * | 2023-05-09 | 2023-09-29 | 安徽工程大学 | Multi-source data-based thermal barrier coating service life prediction method and system |
-
2022
- 2022-05-27 CN CN202210591322.2A patent/CN114925614A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115470717A (en) * | 2022-10-31 | 2022-12-13 | 四川工程职业技术学院 | Method, device, equipment and storage medium for predicting remaining life of robot |
| CN116825243A (en) * | 2023-05-09 | 2023-09-29 | 安徽工程大学 | Multi-source data-based thermal barrier coating service life prediction method and system |
| CN116825243B (en) * | 2023-05-09 | 2024-01-16 | 安徽工程大学 | Multi-source data-based thermal barrier coating service life prediction method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114925614A (en) | Method for predicting residual life of coal mining machine | |
| CN109063308B (en) | Health assessment method based on deep quantum learning | |
| CN112098848B (en) | Battery discharge capacity prediction method and system and readable storage medium | |
| CN105300692B (en) | A kind of bearing failure diagnosis and Forecasting Methodology based on expanded Kalman filtration algorithm | |
| CN104792529A (en) | Rolling bearing life prediction method based on state-space model | |
| CN105550943A (en) | Method for identifying abnormity of state parameters of wind turbine generator based on fuzzy comprehensive evaluation | |
| CN110059845B (en) | Metering device clock error trend prediction method based on time sequence evolution gene model | |
| CN111414703B (en) | Method and device for predicting residual life of rolling bearing | |
| CN111669123B (en) | Method and device for fault diagnosis of photovoltaic string | |
| CN110765699B (en) | Method and device for evaluating health state of fracturing equipment during operation | |
| CN110261746B (en) | Cable defect detection method based on periodic attenuation characteristics of oscillating wave voltage | |
| CN114861827B (en) | Coal mining machine predictive diagnosis and health management method based on multi-source data fusion | |
| CN111458149B (en) | Method and system for predicting performance and service life of rolling bearing | |
| CN111881594B (en) | Non-stationary signal state monitoring method and system for nuclear power equipment | |
| CN113987294A (en) | CVT (continuously variable transmission) online fault diagnosis method based on genetic optimization GRU (generalized regression Unit) neural network | |
| CN117076955A (en) | Fault detection method and system for high-voltage frequency converter | |
| CN114323642A (en) | Wind turbine generator vibration data processing system and data dilution method | |
| CN115600928A (en) | OAO-RVM-based GIS basin-type insulator state evaluation method | |
| CN105334472A (en) | Online remaining life prediction method for mining intrinsic safety power supply | |
| CN108536877B (en) | Method and system for evaluating vibration degree of wind generating set | |
| CN117172601A (en) | Non-invasive load monitoring method based on residual total convolution neural network | |
| CN107727392B (en) | State index evaluation and optimization method based on signal detection and ROC analysis | |
| CN114547796B (en) | Ball mill feature fusion fault diagnosis method based on optimized BN network | |
| CN115293189A (en) | Rotating machinery state monitoring method based on stack self-coding dimension reduction | |
| CN117273547B (en) | Production equipment operation data processing method based on edge calculation |
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 |