CN112418407A - Real-time data early warning analysis method based on neural network - Google Patents
Real-time data early warning analysis method based on neural network Download PDFInfo
- Publication number
- CN112418407A CN112418407A CN202011436234.2A CN202011436234A CN112418407A CN 112418407 A CN112418407 A CN 112418407A CN 202011436234 A CN202011436234 A CN 202011436234A CN 112418407 A CN112418407 A CN 112418407A
- Authority
- CN
- China
- Prior art keywords
- vibration signal
- current frame
- neural network
- component
- vibration signals
- 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
- 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
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Human Resources & Organizations (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Strategic Management (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention provides a real-time data early warning analysis method based on a neural network, which comprises the following steps: acquiring component vibration signals of key components of the engineering machinery in real time through a sensor module; the processing module carries out framing processing according to the part vibration signals acquired in real time, and carries out feature extraction according to the current frame part vibration signals to obtain feature parameters of the current frame part vibration signals; the processing module forms an input vector according to the characteristic parameters of the vibration signals of the current frame component and inputs the input vector into a trained state prediction model based on a neural network, and obtains a state prediction result output by the state prediction model; and when the state prediction result is abnormal, the processing module sends abnormal alarm information. The invention adopts the state prediction model based on the neural network to accurately predict whether the engineering machinery has abnormal conditions or not according to the current operation state of the engineering machinery, can send out early warning information, and improves the intelligent level of the detection aiming at the working state of the engineering machinery.
Description
Technical Field
The invention relates to the technical field of data analysis, in particular to a real-time data early warning analysis method based on a neural network.
Background
Currently, most of the work state monitoring of the engineering machinery depends on the judgment of an operator on site to judge whether the engineering machinery breaks down.
In the prior art, a technical scheme of monitoring the working state of the construction machine by arranging a state monitoring device in the construction machine also appears, but in the scheme, monitoring is usually performed on certain indexes (such as temperature, pressure and other data) of the construction machine, and when the indexes exceed the set indexes, an alarm prompt is sent out. However, the above method cannot predict the working state of the engineering machine in advance, and the intelligence level needs to be improved.
Disclosure of Invention
Aiming at the problems, the invention aims to provide a real-time data early warning analysis method based on a neural network.
The purpose of the invention is realized by adopting the following technical scheme:
the invention discloses a real-time data early warning analysis method based on a neural network, which is characterized by comprising the following steps of:
collecting component vibration signals of key components of the engineering machinery in real time;
performing framing processing according to the part vibration signals acquired in real time, and performing feature extraction according to the current frame part vibration signals to obtain feature parameters of the current frame part vibration signals;
forming an input vector according to the characteristic parameters of the vibration signals of the current frame part, inputting the input vector into a trained state prediction model based on a neural network, and acquiring a state prediction result output by the state prediction model;
and when the state prediction result is abnormal, sending abnormal alarm information.
Optionally, the method further includes the steps of arranging the vibration sensor in a key component of the engineering machine, and acquiring a component vibration signal of the key component of the engineering machine in real time through the vibration sensor.
Optionally, performing framing processing according to the component vibration signal acquired in real time includes:
and performing framing processing on the part vibration signals acquired in real time by adopting a set window and a set step length to acquire each frame of part vibration signals, wherein the latest acquired part vibration signal frame is taken as a current frame part vibration signal Z (t), and t represents the frame number corresponding to the current moment.
Optionally, before performing feature extraction on the current frame component vibration signal z (t), preprocessing is further performed on the current frame component vibration signal z (t).
Optionally, the preprocessing the current frame component vibration signal z (t) includes:
carrying out fast Fourier transform on a received vibration signal Z (t) of the current frame component to obtain a frequency domain amplitude spectrum | G (t, k) | of the vibration signal of the current frame component, wherein t represents the frame number of the vibration signal of the component corresponding to the frequency domain amplitude spectrum, and k represents the kth frequency point in the frequency domain amplitude spectrum;
performing enhancement processing on the acquired frequency domain amplitude spectrum | G (t, k) |, wherein the adopted enhancement processing function is as follows:
in the formula, | Y (t, k) | represents the frequency domain amplitude spectrum after the enhancement processing corresponding to the t-th frame component vibration signal, | G (t, k) | represents the frequency domain amplitude spectrum corresponding to the t-th frame component vibration signal, | S (t, k) | represents the adjustment amplitude spectrum corresponding to the t-th frame component vibration signal, | S (t-2, k) | represents the adjustment amplitude spectrum corresponding to the t-1-th component vibration signal, wherein for the first 2 frames of component vibration signals, the adjustment amplitude spectrum is set
Beta represents a set adjustment factor, wherein beta is larger than or equal to 1, alpha represents a set influence factor, delta represents a set deviation factor, wherein delta epsilon is 0.5, 0.99]And F (k) represents a set reference deviation magnitude spectrum, wherein
ω1And ω2Respectively represent the set weight factors, where1+ω2＝1；
And performing inverse fast Fourier transform according to the obtained frequency domain amplitude spectrum after the enhancement processing to obtain a preprocessed component vibration signal Z' (t).
The invention has the beneficial effects that: according to the invention, the state prediction model based on the neural network is adopted to perform early warning analysis processing on the component vibration signals according to the acquired component vibration signals, whether the engineering machinery has abnormal conditions or not can be accurately predicted according to the current running state of the engineering machinery, early warning information can be sent out, and the intelligent level of detection on the working state of the engineering machinery is improved.
Drawings
The invention is further illustrated by means of the attached drawings, but the embodiments in the drawings do not constitute any limitation to the invention, and for a person skilled in the art, other drawings can be obtained on the basis of the following drawings without inventive effort.
Fig. 1 is a flowchart of a method for real-time data early warning analysis based on a neural network according to an embodiment of the present invention.
Detailed Description
The invention is further described in connection with the following application scenarios.
Referring to fig. 1, the embodiment shows a real-time data early warning analysis method based on a neural network, which is characterized by comprising the following steps: acquiring component vibration signals of key components of the engineering machinery in real time through a sensor module;
the processing module carries out framing processing according to the part vibration signals acquired in real time, and carries out feature extraction according to the current frame part vibration signals to obtain feature parameters of the current frame part vibration signals;
the processing module forms an input vector according to the characteristic parameters of the vibration signals of the current frame component and inputs the input vector into a trained state prediction model based on a neural network, and obtains a state prediction result output by the state prediction model;
and when the state prediction result is abnormal, the processing module sends abnormal alarm information.
In the above embodiment, a state prediction model based on a neural network is provided to perform early warning analysis processing on component vibration signals according to collected component vibration signals, so that whether an abnormal condition exists in the engineering machinery can be accurately predicted according to the current operation state of the engineering machinery, an early warning message can be sent out, and the intelligent level of detection on the working state of the engineering machinery is improved.
Optionally, the sensor module is specifically a vibration sensor.
The method further comprises the steps that the vibration sensor is arranged in the key part of the engineering machinery, and part vibration signals of the key part of the engineering machinery are collected in real time through the vibration sensor.
Optionally, the processing module performs framing processing according to the component vibration signal acquired in real time, and includes:
and performing framing processing on the part vibration signals acquired in real time by adopting a set window and a set step length to acquire each frame of part vibration signals, wherein the latest acquired part vibration signal frame is taken as a current frame part vibration signal Z (t), and t represents the frame number corresponding to the current moment.
Optionally, the processing module is configured to perform preprocessing on the current frame component vibration signal Z (t) (or the preprocessed current frame component vibration signal Z' (t)) before performing feature extraction on the current frame component vibration signal Z (t).
Optionally, the processing module performs preprocessing on the current frame component vibration signal z (t), including:
carrying out fast Fourier transform on a received vibration signal Z (t) of the current frame component to obtain a frequency domain amplitude spectrum | G (t, k) | of the vibration signal of the current frame component, wherein t represents the frame number of the vibration signal of the component corresponding to the frequency domain amplitude spectrum, and k represents the kth frequency point in the frequency domain amplitude spectrum;
performing enhancement processing on the acquired frequency domain amplitude spectrum | G (t, k) |, wherein the adopted enhancement processing function is as follows:
in the formula, | Y (t, k) | represents the frequency domain amplitude spectrum after the enhancement processing corresponding to the t-th frame component vibration signal, | G (t, k) | represents the frequency domain amplitude spectrum corresponding to the t-th frame component vibration signal, | S (t, k) | represents the adjustment amplitude spectrum corresponding to the t-th frame component vibration signal, | S (t-2, k) | represents the adjustment amplitude spectrum corresponding to the t-1-th component vibration signal, wherein for the first 2 frames of component vibration signals in the component vibration signal, the adjustment amplitude spectrum is set
Beta represents a set adjustment factor, wherein beta is larger than or equal to 1, alpha represents a set influence factor, delta represents a set deviation factor, wherein delta epsilon is 0.5, 0.99]And F (k) represents a set reference deviation magnitude spectrum, wherein
ω1And ω2Respectively represent the set weight factors, where1+ω2＝1；
And performing inverse fast Fourier transform according to the obtained frequency domain amplitude spectrum after the enhancement processing to obtain a preprocessed component vibration signal Z' (t).
In the above embodiment, a technical scheme for preprocessing a component vibration signal acquired in real time is provided, and a frequency amplitude spectrum of a current frame component vibration signal is acquired as a basis for enhancement processing, so that noise interference contained in the component vibration signal can be effectively removed in a self-adaptive manner.
Optionally, the processing module performs feature extraction according to the current frame component vibration signal to obtain feature parameters of the current frame component vibration signal, and the feature parameters specifically include:
carrying out three-layer wavelet packet decomposition processing on the vibration signal Z (t) of the current frame component to obtain 8 wavelet packet coefficients of the vibration signal of the current frame component
Wherein
Representing the low-frequency wavelet packet coefficients,
representing the nth high frequency wavelet packet coefficient;
respectively reconstructing according to the obtained 8 wavelet packet coefficients to obtain 8 sub-frequency signals
Wherein
Represents the 1 st sub-frequency signal, which is reconstructed from the low-frequency small wavelet coefficients,
to
Representing 2 nd to 8 th sub-frequency signals which are respectively reconstructed according to the 1 st to 7 th high-frequency wavelet packet coefficients;
respectively acquiring energy coefficients of the sub-frequency signals, wherein the adopted energy coefficient acquisition function is as follows:
in the formula (I), the compound is shown in the specification,
an energy coefficient representing an nth sub-frequency signal, wherein n is 1, 2.
Representing the amplitude of the ith sampling point in the nth sub-frequency coefficient, wherein I represents the total number of the sampling points;
the characteristic parameters of the vibration signal of the current frame component constructed according to the acquired energy coefficient are as follows:
wherein
Characteristic parameters representing the component vibration signals of the t-th frame,
in the above embodiment, a method is provided for performing wavelet packet decomposition according to a component vibration signal, constructing characteristic parameters reflecting signal characteristics of the component vibration signal in different frequency ranges according to an obtained wavelet packet coefficient, and representing the characteristics of the component vibration signal by using 8-dimensional characteristic parameters, so that on one hand, the sensitivity of the characteristic parameters to abnormal vibration signals in the vibration signal can be improved, and on the other hand, an input vector of a state prediction model based on a neural network is formed according to the characteristic parameters, so that the state prediction accuracy of the model is improved; the state prediction model based on the neural network can predict the state to achieve the best performance.
Optionally, when the feature extraction is performed according to the current frame component vibration signal, it may also be performed according to the preprocessed current frame component vibration signal. It should be understood by those skilled in the art that, in the embodiment based on the above-mentioned pre-processing of the component vibration signal, the processing method based on the component vibration signal shown later in the method may be replaced by the pre-processed component vibration signal, so as to form a variety of different embodiments, and the description of the present application is not repeated here.
Optionally, input vectors composed of characteristic parameters of vibration signals of current frame components are input into the trained state prediction model based on the neural network, wherein the input vectors adopted include
In thereintRepresenting the input vector for the current time instant,
respectively representing the characteristic parameters obtained according to the component vibration signals of the t-2 th, t-2 th and t-th frames.
According to the embodiment, the characteristics of the vibration signals of the parts can be acquired from the current real time by constructing the 24-dimensional input vector and inputting the 24-dimensional input vector into the trained state prediction model, and the working state of the current engineering machine is well expressed by combining the time domain variation trend characteristics of the signals, so that the working state of the engineering machine can be accurately predicted by the state prediction model based on the neural network according to the input 24-dimensional input vector, and the accuracy of data early warning analysis is improved.
The training method of the state prediction model based on the neural network comprises the steps of intercepting characteristic parameters corresponding to 3 frames of component vibration signals from a pre-acquired component vibration signal and state data corresponding to the signal to form a sample input vector, and taking the state data corresponding to a set time period after the 3 frames of vibration signals as the sample input vector;
and forming a training sample by using the sample input vector and the sample input vector to train the state prediction model based on the neural network, and obtaining the trained state prediction model based on the neural network until the model converges or exceeds a set training period, wherein the model can predict state data after the set period according to the input vector formed by positive parameters corresponding to continuous 3 frames of component vibration signals, and the state comprises normal or abnormal.
Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the protection scope of the present invention, although the present invention is described in detail with reference to the preferred embodiments, it should be analyzed by those skilled in the art that modifications or equivalent substitutions can be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (5)
1. A real-time data early warning analysis method based on a neural network is characterized by comprising the following steps:
collecting component vibration signals of key components of the engineering machinery in real time;
performing framing processing according to the part vibration signals acquired in real time, and performing feature extraction according to the current frame part vibration signals to obtain feature parameters of the current frame part vibration signals;
forming an input vector according to the characteristic parameters of the vibration signals of the current frame part, inputting the input vector into a trained state prediction model based on a neural network, and obtaining a state prediction result output by the state prediction model;
and when the state prediction result is abnormal, sending abnormal alarm information.
2. The real-time data early warning analysis method based on the neural network as claimed in claim 1, further comprising: the method comprises the steps of arranging a vibration sensor in a key part of the engineering machinery, and collecting a part vibration signal of the key part of the engineering machinery in real time through the vibration sensor.
3. The real-time data early warning analysis method based on the neural network as claimed in claim 2, wherein the framing processing is performed according to the component vibration signals collected in real time, and the method comprises the following steps:
and performing framing processing on the part vibration signals acquired in real time by adopting a set window and a set step length to acquire part vibration signals of each frame, wherein the latest acquired part vibration signal frame is the current frame part vibration signal Z (t).
4. The real-time data early warning analysis method based on the neural network as claimed in claim 3, wherein before the feature extraction of the vibration signal Z (t) of the current frame component, the method further comprises preprocessing the vibration signal Z (t) of the current frame component.
5. The real-time data early warning analysis method based on the neural network as claimed in claim 4, wherein the preprocessing of the vibration signal Z (t) of the current frame component comprises:
carrying out fast Fourier transform on a received vibration signal Z (t) of the current frame component to obtain a frequency domain amplitude spectrum | G (t, k) | of the vibration signal of the current frame component, wherein t represents the frame number of the vibration signal of the component corresponding to the frequency domain amplitude spectrum, and k represents the kth frequency point in the frequency domain amplitude spectrum;
performing enhancement processing on the acquired frequency domain amplitude spectrum | G (t, k) |, wherein the adopted enhancement processing function is as follows:
in the formula, | Y (t, k) | represents the frequency domain amplitude spectrum after the enhancement processing corresponding to the t-th frame component vibration signal, | G (t, k) | represents the frequency domain amplitude spectrum corresponding to the t-th frame component vibration signal, | S (t, k) | represents the adjustment amplitude spectrum corresponding to the t-th frame component vibration signal, | S (t-2, k) | represents the adjustment amplitude spectrum corresponding to the t-1-th component vibration signal, wherein for the first 2 frames of component vibration signals, the adjustment amplitude spectrum is set
Beta represents a set regulating factor, wherein beta is more than or equal to 1, alpha represents a set influencing factor,delta represents a set deviation factor, where delta e 0.5, 0.99]And F (k) represents a set reference deviation magnitude spectrum, wherein
ω1And ω2Respectively represent the set weight factors, where1+ω2＝1；
And performing inverse fast Fourier transform according to the obtained frequency domain amplitude spectrum after the enhancement processing to obtain a preprocessed component vibration signal Z' (t).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011436234.2A CN112418407B (en) | 2020-12-10 | 2020-12-10 | Real-time data early warning analysis method based on neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011436234.2A CN112418407B (en) | 2020-12-10 | 2020-12-10 | Real-time data early warning analysis method based on neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112418407A true CN112418407A (en) | 2021-02-26 |
| CN112418407B CN112418407B (en) | 2022-03-11 |
Family
ID=74776275
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011436234.2A Active CN112418407B (en) | 2020-12-10 | 2020-12-10 | Real-time data early warning analysis method based on neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112418407B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115264408A (en) * | 2022-06-23 | 2022-11-01 | 大连理工大学 | Pipeline leakage detection method and system based on audio processing |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6301572B1 (en) * | 1998-12-02 | 2001-10-09 | Lockheed Martin Corporation | Neural network based analysis system for vibration analysis and condition monitoring |
| US20050149234A1 (en) * | 2003-12-30 | 2005-07-07 | Vian John L. | Methods and systems for analyzing engine unbalance conditions |
| CN102778358A (en) * | 2012-06-04 | 2012-11-14 | 上海东锐风电技术有限公司 | Failure prediction model establishing method and system as well as fan monitoring pre-warning system and method |
| CN109374270A (en) * | 2018-09-19 | 2019-02-22 | 国网甘肃省电力公司电力科学研究院 | A kind of analysis of GIS abnormal vibrations and mechanical fault diagnosis device and method |
| CN109946055A (en) * | 2019-03-22 | 2019-06-28 | 武汉源海博创科技有限公司 | A kind of sliding rail of automobile seat abnormal sound detection method and system |
| CN110490071A (en) * | 2019-07-12 | 2019-11-22 | 国网上海市电力公司 | A kind of substation's Abstraction of Sound Signal Characteristics based on MFCC |
| CN110987434A (en) * | 2019-12-18 | 2020-04-10 | 中国民航大学 | Rolling bearing early fault diagnosis method based on denoising technology |
-
2020
- 2020-12-10 CN CN202011436234.2A patent/CN112418407B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6301572B1 (en) * | 1998-12-02 | 2001-10-09 | Lockheed Martin Corporation | Neural network based analysis system for vibration analysis and condition monitoring |
| US20050149234A1 (en) * | 2003-12-30 | 2005-07-07 | Vian John L. | Methods and systems for analyzing engine unbalance conditions |
| CN102778358A (en) * | 2012-06-04 | 2012-11-14 | 上海东锐风电技术有限公司 | Failure prediction model establishing method and system as well as fan monitoring pre-warning system and method |
| CN109374270A (en) * | 2018-09-19 | 2019-02-22 | 国网甘肃省电力公司电力科学研究院 | A kind of analysis of GIS abnormal vibrations and mechanical fault diagnosis device and method |
| CN109946055A (en) * | 2019-03-22 | 2019-06-28 | 武汉源海博创科技有限公司 | A kind of sliding rail of automobile seat abnormal sound detection method and system |
| CN110490071A (en) * | 2019-07-12 | 2019-11-22 | 国网上海市电力公司 | A kind of substation's Abstraction of Sound Signal Characteristics based on MFCC |
| CN110987434A (en) * | 2019-12-18 | 2020-04-10 | 中国民航大学 | Rolling bearing early fault diagnosis method based on denoising technology |
Non-Patent Citations (2)
| Title |
|---|
| 潘楠等: "基于频域盲解卷积的机械设备状态监测与故障诊断", 《振动与冲击》 * |
| 郑晴晴等: "CHMM在滚动轴承故障诊断中的应用研究", 《现代制造工程》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115264408A (en) * | 2022-06-23 | 2022-11-01 | 大连理工大学 | Pipeline leakage detection method and system based on audio processing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112418407B (en) | 2022-03-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111259717B (en) | Method and system for judging abnormal state of rotating equipment | |
| CN109670485B (en) | Rotary machine local fault remote diagnosis method based on multi-data compression tracking algorithm | |
| CN108445868B (en) | Intelligent automobile fault diagnosis system and method based on modern signal processing technology | |
| CN106500735A (en) | A kind of FBG signal adaptive restorative procedures based on compressed sensing | |
| CN107356432A (en) | Fault Diagnosis of Roller Bearings based on frequency domain window experience small echo resonance and demodulation | |
| CN109855874B (en) | Random resonance filter for enhancing detection of weak signals in vibration assisted by sound | |
| CN112729381B (en) | Fault diagnosis method of high-voltage circuit breaker based on neural network | |
| CN112418407B (en) | Real-time data early warning analysis method based on neural network | |
| CN109507510A (en) | A kind of transformer fault diagnosis system | |
| CN112329914B (en) | Fault diagnosis method and device for buried transformer substation and electronic equipment | |
| CN110501631A (en) | A kind of online intermittent fault detection and diagnostic method | |
| CN114850968B (en) | Cutter abrasion monitoring method, device, terminal and medium based on vibration model | |
| CN114004256A (en) | Fault diagnosis method for manufacturing equipment main bearing based on digital twin body | |
| CN109236587A (en) | It is a kind of for detecting the alarm system of wind-driven generator abnormal work | |
| CN111791720A (en) | Electric vehicle control system | |
| CN208207843U (en) | A kind of slush pump trouble-shooter | |
| CN112327734A (en) | Engineering machine tool remote monitering system based on internet | |
| CN110457979A (en) | The Diagnosis Method of Diesel Fault of fuzzy control is decomposed based on tensor Tucker | |
| CN115310477A (en) | Pump equipment fault sound detection method and system based on fractal features and predator algorithm | |
| CN107860958B (en) | Noise reduction method for real-time monitoring current value of underwater robot propeller and real-time monitoring system thereof | |
| CN114966477A (en) | Transformer voiceprint analysis method and system | |
| JPH08114638A (en) | Machinery abnormality diagnosing apparatus | |
| Zhao et al. | An intelligent fault diagnosis method for a diesel engine valve based on improved wavelet packet-Mel frequency and convolutional neural network | |
| Niu et al. | A fault diagnosis method based on singular spectrum decomposition and envelope autocorrelation for rolling bearing | |
| Zhuge et al. | Signature analysis for reciprocating machinery with adaptive signal processing |
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 |