CN111027260A - Reciprocating compressor fault diagnosis method based on neural network - Google Patents
Reciprocating compressor fault diagnosis method based on neural network Download PDFInfo
- Publication number
- CN111027260A CN111027260A CN201911345187.8A CN201911345187A CN111027260A CN 111027260 A CN111027260 A CN 111027260A CN 201911345187 A CN201911345187 A CN 201911345187A CN 111027260 A CN111027260 A CN 111027260A
- Authority
- CN
- China
- Prior art keywords
- signals
- reciprocating compressor
- neural network
- fault
- temperature
- 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
- 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
- G06F18/24—Classification techniques
-
- 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
Abstract
The invention discloses a fault diagnosis method for a reciprocating compressor based on a neural network, which uses an artificial neural network for fault classification of the reciprocating compressor and can realize intelligent diagnosis of faults of the reciprocating compressor. The method of the invention utilizes vibration signals, physical phase signals, dynamic pressure signals, temperature signals of all levels, temperature signals of all valves, flow signals and current signals of a motor to extract the characteristics of the running state of the reciprocating compressor from a plurality of angles, and then combines a neural network to realize accurate memory of the fault mode. The method of the invention automatically diagnoses the fault of the reciprocating compressor and has wide industrial application prospect.
Description
Technical Field
The invention relates to the field of pattern recognition and fault detection, in particular to a fault diagnosis method for a reciprocating compressor based on a neural network.
Background
The reciprocating compressor is a general mechanical device, mainly moves in a reciprocating way, and is widely applied to engineering practice. Fault diagnosis of the reciprocating compressor is very difficult due to the complexity of moving parts and the number of excitation sources in operation. The degree of deterioration is a typical index for identifying a fault of the reciprocating compressor, but it is often impossible to accurately determine which type of fault is simply based on the degree of deterioration.
With the rapid development of computer technology, signal processing technology, and artificial intelligence, intelligent fault diagnosis of a reciprocating compressor has begun to be of interest. At present, fault diagnosis of the reciprocating compressor is developing towards networking and intellectualization. Therefore, it has become an important direction to apply the latest technology of artificial intelligence to the fault diagnosis of the reciprocating compressor. By utilizing an information fusion technology, the intelligent diagnosis of the fault of the reciprocating compressor becomes a new problem in the field of fault diagnosis of the reciprocating compressor.
Disclosure of Invention
The invention discloses a fault diagnosis method of a reciprocating compressor based on a neural network, aiming at the problem of intelligent diagnosis of faults of the reciprocating compressor.
In order to achieve the above purpose, the specific scheme of the invention is as follows:
step 1, collecting operation state signals of a reciprocating compressor, wherein the operation state signals comprise: vibration signals, physical phase signals, dynamic pressure signals, temperature signals of all levels, temperature signals of all valves, flow signals and motor current signals;
step 2, processing the signals acquired in the step 1, and extracting the characteristics of fault signals;
step 3, establishing a sample library by using the fault characteristics extracted in the step 2 and combining fault types;
step 4, constructing an artificial neural network;
step 5, training the constructed neural network, and memorizing the fault mode of the reciprocating compressor;
and 6, carrying out fault identification on the fault signal of the reciprocating compressor by utilizing the trained neural network, and giving an identification result.
Advantageous effects
The method of the invention uses the artificial neural network for fault classification of the reciprocating compressor, and can realize intelligent diagnosis of the fault of the reciprocating compressor. The method of the invention utilizes the vibration signal, the physical phase signal, the dynamic pressure signal, the temperature signals of all levels, the temperature signals of all valves, the flow signal and the motor current signal to carry out characteristic extraction on the operation state of the reciprocating compressor from a plurality of angles, and then combines the neural network to realize accurate memory of the fault mode. The method of the invention automatically diagnoses the fault of the reciprocating compressor and has wide industrial application prospect.
Drawings
FIG. 1 is a flow chart of a neural network based fault diagnosis method of a reciprocating compressor of the present invention;
Detailed Description
The invention will be described in detail with reference to the drawings, and it should be noted that the following description is made for better understanding of the process of the invention and is not intended to be limiting.
The invention aims to provide a fault diagnosis method of a reciprocating compressor based on a neural network, which realizes intelligent diagnosis of faults of the reciprocating compressor by using the neural network and has wide industrial application prospect.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Fig. 1 is a flowchart of a fault diagnosis method of a neural network-based reciprocating compressor according to an embodiment of the present invention. As shown in fig. 1, a fault diagnosis method of a reciprocating compressor based on a neural network, the fault diagnosis method of the reciprocating compressor comprising:
step 1, collecting operation state signals of a reciprocating compressor, wherein the operation state signals comprise: vibration signals, physical phase signals, dynamic pressure signals, temperature signals of all levels, temperature signals of all valves, flow signals and motor current signals;
the vibration signal comprises vibration signals measured by the vibration sensors of one or more channels; the physical phase signal comprises a pulse signal measured by a rotating shaft key phase sensor; the dynamic pressure signals comprise dynamic pressure signals measured by dynamic pressure sensors of the cylinders at all levels; the temperature signals of all levels comprise temperature signals measured by the compression inlet and outlet temperature sensors of all levels; the temperature signals of all the valves comprise temperature signals measured by air valve temperature sensors at the inlet and the outlet of each stage of air cylinder; the flow signals comprise flow signals measured by flow sensors at all levels;
step 2, processing the signals acquired in the step 1, and extracting the characteristics of fault signals;
the signal processing comprises the steps of carrying out envelope analysis, Fourier transform processing, short-time Fourier processing, wavelet analysis processing, EMD processing and statistical signal processing on the vibration signals, and extracting envelope spectrum characteristics, frequency spectrum characteristics and time domain statistical characteristics; extracting phase characteristics of the physical phase signals; normalizing the dynamic pressure signal, the temperature signals of all levels, the temperature signals of all valves, the flow signal and the motor current signal to obtain a dynamic pressure characteristic, an indicator diagram characteristic, a temperature characteristic, a flow characteristic and a motor current characteristic;
step 3, establishing a sample library by using the fault characteristics extracted in the step 2 and combining fault types;
the sample library consists of a plurality of samples, each sample has a sample label, and a plurality of samples can correspond to one same label;
step 4, constructing an artificial neural network;
the neural network consists of an input layer, a hidden layer and an output layer;
step 5, training the constructed neural network, and memorizing the fault mode of the reciprocating compressor;
and 6, carrying out fault identification on the fault signal of the reciprocating compressor by utilizing the trained neural network, and giving an identification result.
Although the steps of the present invention are described with reference to the drawings, the present invention is not limited thereto. All modifications made on the basis of the scheme of the invention are within the protection scope of the invention.
Claims (3)
1. A fault diagnosis method of a reciprocating compressor based on a neural network is characterized in that: the method comprises the following steps:
step 1, collecting operation state signals of a reciprocating compressor, wherein the operation state signals comprise: vibration signals, physical phase signals, dynamic pressure signals, temperature signals of all levels, temperature signals of all valves, flow signals and motor current signals;
step 2, processing the signals acquired in the step 1, and extracting the characteristics of fault signals;
step 3, establishing a sample library by using the fault characteristics extracted in the step 2 and combining fault types;
the sample library consists of a plurality of samples, each sample has a sample label, and a plurality of samples can correspond to one same label;
step 4, constructing an artificial neural network;
the neural network consists of an input layer, a hidden layer and an output layer;
step 5, training the constructed neural network, and memorizing the fault mode of the reciprocating compressor;
and 6, carrying out fault identification on the fault signal of the reciprocating compressor by utilizing the trained neural network, and giving an identification result.
2. The neural network based reciprocating compressor fault diagnosis method as claimed in claim 1, wherein in the step 1, the vibration signal comprises a vibration signal measured by a vibration sensor of one or more channels; the physical phase signal comprises a pulse signal measured by a rotating shaft key phase sensor; the dynamic pressure signals comprise dynamic pressure signals measured by dynamic pressure sensors of the cylinders at all levels; the temperature signals of all levels comprise temperature signals measured by the compression inlet and outlet temperature sensors of all levels; the temperature signals of all the valves comprise temperature signals measured by air valve temperature sensors at the inlet and the outlet of each stage of air cylinder; the flow signals comprise flow signals measured by flow sensors at all levels.
3. The neural network based reciprocating compressor fault diagnosis method as claimed in claim 1, wherein in the step 2, the signal processing is performed by performing envelope analysis, fourier transform processing, short time fourier processing, wavelet analysis processing, EMD processing and statistical signal processing on the vibration signal to extract envelope spectrum features, spectrum features and time domain statistical features; extracting phase characteristics of the physical phase signals; and carrying out normalization processing on the dynamic pressure signals, the temperature signals of all levels, the temperature signals of all valves, the flow signals and the motor current signals to obtain dynamic pressure characteristics, indicator diagram characteristics, temperature characteristics, flow characteristics and motor current characteristics.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911345187.8A CN111027260A (en) | 2019-12-24 | 2019-12-24 | Reciprocating compressor fault diagnosis method based on neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911345187.8A CN111027260A (en) | 2019-12-24 | 2019-12-24 | Reciprocating compressor fault diagnosis method based on neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111027260A true CN111027260A (en) | 2020-04-17 |
Family
ID=70211968
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911345187.8A Pending CN111027260A (en) | 2019-12-24 | 2019-12-24 | Reciprocating compressor fault diagnosis method based on neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111027260A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112766260A (en) * | 2021-01-15 | 2021-05-07 | 哈尔滨市科佳通用机电股份有限公司 | Image identification method and system for positioning air reservoir for accelerating and relieving railway train |
| CN112766301A (en) * | 2020-12-11 | 2021-05-07 | 南京富岛信息工程有限公司 | Similarity judgment method for indicator diagram of oil extraction machine |
| CN113435111A (en) * | 2021-06-08 | 2021-09-24 | 西安交通大学 | Fault diagnosis method and system for reciprocating compressor |
| CN113435453A (en) * | 2021-06-11 | 2021-09-24 | 西安交通大学 | Reciprocating compressor fault diagnosis method and system based on convolutional neural network |
| CN113554000A (en) * | 2021-09-17 | 2021-10-26 | 武汉飞恩微电子有限公司 | Pressure sensor fault diagnosis method and device based on deep learning |
| CN115596654A (en) * | 2022-09-21 | 2023-01-13 | 西安交通大学（Cn） | Reciprocating compressor fault diagnosis method and system based on state parameter learning |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104712542A (en) * | 2015-01-12 | 2015-06-17 | 北京博华信智科技股份有限公司 | Reciprocating compressor sensitive characteristic extracting and fault diagnosis method based on internet of things |
| CN107013449A (en) * | 2017-04-18 | 2017-08-04 | 山东万腾电子科技有限公司 | Voice signal based on deep learning recognizes the method and system of compressor fault |
| CN107908812A (en) * | 2017-10-10 | 2018-04-13 | 电子科技大学 | A kind of valve fault diagnosis method based on HHT and neutral net |
| CN109779894A (en) * | 2018-12-29 | 2019-05-21 | 西安交通大学 | A kind of reciprocating compressor fault diagnosis system and method based on neural network algorithm |
-
2019
- 2019-12-24 CN CN201911345187.8A patent/CN111027260A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104712542A (en) * | 2015-01-12 | 2015-06-17 | 北京博华信智科技股份有限公司 | Reciprocating compressor sensitive characteristic extracting and fault diagnosis method based on internet of things |
| CN107013449A (en) * | 2017-04-18 | 2017-08-04 | 山东万腾电子科技有限公司 | Voice signal based on deep learning recognizes the method and system of compressor fault |
| CN107908812A (en) * | 2017-10-10 | 2018-04-13 | 电子科技大学 | A kind of valve fault diagnosis method based on HHT and neutral net |
| CN109779894A (en) * | 2018-12-29 | 2019-05-21 | 西安交通大学 | A kind of reciprocating compressor fault diagnosis system and method based on neural network algorithm |
Non-Patent Citations (3)
| Title |
|---|
| 彭琦 等: "《概率神经网络在往复压缩机多故障诊断技术研究中的应用》", 《机械设计与制造》 * |
| 杨洪柏 等: "《基于原始振动信号的往复压缩机卷积神经网络故障诊断》", 《机械设计与制造工程》 * |
| 罗鑫: "《基于优化神经网络的压缩机故障诊断研究》", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112766301A (en) * | 2020-12-11 | 2021-05-07 | 南京富岛信息工程有限公司 | Similarity judgment method for indicator diagram of oil extraction machine |
| CN112766301B (en) * | 2020-12-11 | 2024-04-12 | 南京富岛信息工程有限公司 | Oil extraction machine indicator diagram similarity judging method |
| CN112766260A (en) * | 2021-01-15 | 2021-05-07 | 哈尔滨市科佳通用机电股份有限公司 | Image identification method and system for positioning air reservoir for accelerating and relieving railway train |
| CN112766260B (en) * | 2021-01-15 | 2021-09-14 | 哈尔滨市科佳通用机电股份有限公司 | Image identification method and system for positioning air reservoir for accelerating and relieving railway train |
| CN113435111A (en) * | 2021-06-08 | 2021-09-24 | 西安交通大学 | Fault diagnosis method and system for reciprocating compressor |
| CN113435111B (en) * | 2021-06-08 | 2022-10-25 | 西安交通大学 | Fault diagnosis method and system for reciprocating compressor |
| CN113435453A (en) * | 2021-06-11 | 2021-09-24 | 西安交通大学 | Reciprocating compressor fault diagnosis method and system based on convolutional neural network |
| CN113435453B (en) * | 2021-06-11 | 2023-04-07 | 西安交通大学 | Reciprocating compressor fault diagnosis method and system based on convolutional neural network |
| CN113554000A (en) * | 2021-09-17 | 2021-10-26 | 武汉飞恩微电子有限公司 | Pressure sensor fault diagnosis method and device based on deep learning |
| CN113554000B (en) * | 2021-09-17 | 2021-12-14 | 武汉飞恩微电子有限公司 | Pressure sensor fault diagnosis method and device based on deep learning |
| CN115596654A (en) * | 2022-09-21 | 2023-01-13 | 西安交通大学（Cn） | Reciprocating compressor fault diagnosis method and system based on state parameter learning |
| CN115596654B (en) * | 2022-09-21 | 2023-12-22 | 西安交通大学 | Reciprocating compressor fault diagnosis method and system based on state parameter learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111027260A (en) | Reciprocating compressor fault diagnosis method based on neural network | |
| CN110059601B (en) | Intelligent fault diagnosis method for multi-feature extraction and fusion | |
| CN109858352B (en) | Fault diagnosis method based on compressed sensing and improved multi-scale network | |
| CN110135492B (en) | Equipment fault diagnosis and abnormality detection method and system based on multiple Gaussian models | |
| Guo et al. | Rolling bearing fault classification based on envelope spectrum and support vector machine | |
| CN111562108A (en) | Rolling bearing intelligent fault diagnosis method based on CNN and FCMC | |
| CN111307438B (en) | Rotary machine vibration fault diagnosis method and system based on information entropy | |
| CN107631867A (en) | A kind of rotating machinery fault intelligent method for classifying based on deep learning | |
| CN109932179A (en) | A kind of rolling bearing fault testing method based on the reconstruct of DS Adaptive spectra | |
| Lu et al. | CEEMD-assisted bearing degradation assessment using tight clustering | |
| CN111964909A (en) | Rolling bearing operation state detection method, fault diagnosis method and system | |
| CN110849625A (en) | Bearing fault diagnosis method under variable working condition based on mixed entropy and joint distribution adaptation | |
| CN113569990B (en) | Strong noise interference environment-oriented performance equipment fault diagnosis model construction method | |
| JP2021018818A (en) | Propeller cavitation state detection method based on wavelet and principal component analysis | |
| CN111122162A (en) | Industrial system fault detection method based on Euclidean distance multi-scale fuzzy sample entropy | |
| CN116738221B (en) | Pressurized pipeline gas analysis method and system | |
| CN117171655A (en) | Intelligent judging method and device for coal mine production state based on spectrum analysis | |
| CN116935892A (en) | Industrial valve anomaly detection method based on audio key feature dynamic aggregation | |
| CN116541771A (en) | Unbalanced sample bearing fault diagnosis method based on multi-scale feature fusion | |
| CN111025100A (en) | Transformer ultrahigh frequency partial discharge signal mode identification method and device | |
| CN115795341A (en) | Two-dimensional piston pump health state assessment method based on variable rotating speed | |
| Hao et al. | New fusion features convolutional neural network with high generalization ability on rolling bearing fault diagnosis | |
| CN113095364B (en) | High-speed rail seismic event extraction method, medium and equipment using convolutional neural network | |
| CN108984997B (en) | Centrifugal pump fault diagnosis method based on entropy value | |
| Tossavainen | Sound based fault detection system |
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 |