CN113447260A - Online-based nondestructive one-way valve fault detection system and method - Google Patents
Online-based nondestructive one-way valve fault detection system and method Download PDFInfo
- Publication number
- CN113447260A CN113447260A CN202110684582.XA CN202110684582A CN113447260A CN 113447260 A CN113447260 A CN 113447260A CN 202110684582 A CN202110684582 A CN 202110684582A CN 113447260 A CN113447260 A CN 113447260A
- Authority
- CN
- China
- Prior art keywords
- data
- fault detection
- online
- way valve
- detection system
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 37
- 238000000034 method Methods 0.000 title claims abstract description 21
- 230000005540 biological transmission Effects 0.000 claims abstract description 22
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 13
- 238000012544 monitoring process Methods 0.000 claims abstract description 7
- 238000006243 chemical reaction Methods 0.000 claims abstract description 4
- 238000012360 testing method Methods 0.000 claims description 24
- 238000007405 data analysis Methods 0.000 claims description 8
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000001228 spectrum Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 5
- 150000001875 compounds Chemical class 0.000 claims description 2
- 238000013178 mathematical model Methods 0.000 claims description 2
- 230000002441 reversible effect Effects 0.000 claims description 2
- 238000005070 sampling Methods 0.000 claims description 2
- 238000000513 principal component analysis Methods 0.000 abstract description 5
- 230000000694 effects Effects 0.000 abstract description 2
- 238000012545 processing Methods 0.000 description 7
- 238000003745 diagnosis Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000010183 spectrum analysis Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012847 principal component analysis method Methods 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000005236 sound signal Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
- G01M13/003—Machine valves
Abstract
The invention relates to an online-based nondestructive one-way valve fault detection system and method, and belongs to the technical field of fault detection. The invention utilizes the acoustic emission signal sensor to collect the operation information of the one-way valve, and transmits the corresponding information to the data processor through the signal amplifier, the analog-to-digital converter and the data first-in first-out arrangement, and finally transmits the information to the host through the ZigBee wireless transmission mode after conversion, and the host obtains the normal operation model and the real-time monitoring model through the principal component analysis based on the wavelet packet on the collected acoustic emission signal, thereby realizing the real-time control. The invention introduces a principal component analysis theory of wavelet packet decomposition, realizes the function of real-time monitoring of the operation of the one-way valve, and ensures that the operation of the one-way valve can obtain the best service life and the best fault detection and prediction effects.
Description
Technical Field
The invention relates to an online-based nondestructive one-way valve fault detection system and method, and belongs to the technical field of fault detection.
Background
The pipeline transportation technology is a fifth transportation mode which is newly created and follows the traditional transportation modes such as road, railway, water transportation, air transportation and the like. The healthy and stable operation of the high-pressure piston diaphragm pump is an important guarantee of a conveying pipeline. Therefore, the method has important practical significance and economic value for health monitoring and fault diagnosis of the high-pressure piston diaphragm pump. Generally, common methods for detecting faults of machines include vibration detection and acoustic signal detection based on acoustic emission, wherein the vibration detection has the disadvantages of inaccurate vibration detection of internal parts of the machines, difficult signal separation due to the need of multipoint distribution and control during directional detection of vibration, and inaccurate vibration detection due to the fact that the whole high-pressure piston diaphragm pump is large and complex, a check valve is one of indispensable directional control valves in the whole pump, and most of valve bodies are located in the pump body.
The sound signal based on acoustic emission contains abundant information, is the most sensitive symptom parameter for representing machine faults, and many faults are represented as sound abnormity. Therefore, fault detection based on acoustic emission is adopted, wavelet packet decomposition is carried out through the collected acoustic emission signals of the one-way valve, energy spectrum analysis is carried out, the obtained energy spectrum of the signal frequency band is used as input, a normal operation model is established, and real-time fault detection of mechanical equipment is realized.
Disclosure of Invention
The invention aims to solve the technical problem of providing a nondestructive one-way valve fault detection system and method based on-line, so as to solve the problems of inaccurate detection and difficult signal acquisition in the existing one-way valve detection method.
The technical scheme of the invention is as follows: a principal component analysis theory method after wavelet packet decomposition is adopted for collected acoustic emission signals, a health model of one-way valve operation under normal working conditions is established according to actually collected normal acoustic emission signals, whether faults occur or not is identified through fault detection statistics in a principal component statistical method, and online fault detection of the one-way valve is achieved, so that the problems that technical workers are inexperienced in detection, resources and funds are wasted due to valve replacement at regular intervals and the like are avoided.
A nondestructive one-way valve fault detection system based on online comprises a sound acquisition sensor, a signal preamplifier, a data digital-to-analog converter, a first-in first-out arrangement element, a single chip processor, a pulse width modulation module, a clock frequency testing element, a ZigBee wireless transmission module and a host;
the sound collection sensor is connected with the signal preamplifier, the signal preamplifier is connected with the data digital-to-analog converter, the data digital-to-analog converter is connected with the first-in first-out arrangement element, the first-in first-out arrangement element is connected with the single chip microcomputer processor, the single chip microcomputer processor is connected with the ZigBee wireless transmission module, the ZigBee wireless transmission module is connected with the host, the pulse width modulation module is connected with the clock frequency testing element and combined with the clock frequency testing element, and the combined pulse width modulation module is connected with the data digital-to-analog converter and the first-in first-out arrangement element respectively.
The number of the sound collection sensors can be N, N is an integer, and the number of the signal preamplifiers, the number of the data digital-to-analog converters and the number of the first-in first-out arrangement elements are the same as the number of the sound collection sensors.
The sound acquisition sensor, the signal preamplifier, the data digital-to-analog converter and the first-in first-out arrangement element are in a group, each group is connected with the single chip processor, and each group is provided with the pulse width modulation module and the clock frequency test element.
The sound acquisition sensor is used for acquiring data, and the acquired data is transmitted to the singlechip processor through the signal preamplifier and the data digital-to-analog converter for processing.
The data acquisition and transmission can be performed in parallel by means of N sound acquisition sensors and N different channels.
The pulse width modulation module and the clock frequency test element are used for coordinating the transmission and conversion of data.
The pulse width modulation module and the clock frequency testing element control the clock frequency of the AD and the FIFO by utilizing the output of the microprocessor.
The data processed by the single chip processor is transmitted to the host computer through the ZigBee wireless transmission module for data analysis.
A method for carrying out fault detection on a nondestructive one-way valve fault detection system based on-line comprises the following specific steps:
step 1: a sound collection sensor (1) is arranged at each one-way valve body, signals of the sensors are amplified and transmitted to a data digital-to-analog converter (3), then are stored in a single chip processor (5) in a queue form, and finally, the data are transmitted to a host (9) for later analysis;
step 2: establishing a normal model in the running process of the one-way valve to obtain a threshold value of the model in normal running, wherein the specific method for establishing the model comprises the following steps:
according to the collected normal data, hexadecimal machine data is converted into decimal operational data in a host (9), wavelet packet decomposition is carried out on the converted data, signal data are decomposed into approximate signal data and detail signal data by using a high-pass filter and a low-pass filter, a dual-scale equation can be obtained through a scale function and a wavelet function, and the scale function and the wavelet function meet the dual-scale equation under multi-resolution analysis:
where phi (t) is a scale function, phi (t) is a wavelet function, and h0kIs the coefficient of the high-pass filter, h1kIs the coefficient of the low-pass filter, t ∈ [1, N]N is the number of data points, k is N/2lL represents the number of layers of wavelet packet decomposition;
according to the node coefficient after wavelet packet decomposition, obtaining energy values under different frequency bands, and then obtaining energy spectrums under different frequency bands:
E(tj)＝∫R|f(tj)|2dt＝∑|xj|2
wherein R represents a real number domain, f (t)j) Representing the reconstructed signal, E (t)j) Denotes f (t)j) Corresponding energy, xjDenotes f (t)j) The wavelet packet reconstruction coefficients of (a) are,j＝0,1,2,…,2nrepresenting the number of nodes of each layer;
step 3: by Hotelling T in principal component model2And calculating the degree of the data deviating from the normal model by the SPE statistic, and defining a sampling data vector X at a certain moment as follows:
Ti 2＝tiλ-1ti T＝XiPλ-1PTXi T
in the formula, tiIs the score vector of the ith principal component, lambda is a diagonal matrix formed by eigenvalues corresponding to the first i principal elements, and P is a reversible matrix;
when the pressure is within the control limit, the check valve is in a normal state, if the pressure exceeds the control limit, the fault is shown, and Hotelling T2The statistical quantity control limit is:
wherein m is the number of samples, k is the number of pivot elements, Fk,m-1,αAn upper limit value of an F distribution representing a confidence degree α;
for a sample data vector x at a certain time instant, the SPE statistic is defined as follows:
when the SPE is within the control limit of the SPE, the one-way valve is in a normal state, and if the SPE exceeds the control limit, a fault is generated;
the SPE control limits are:
in the formula (I), the compound is shown in the specification,
l is the number of principal elements, λiIs the eigenvalue of the covariance matrix of X, cαIs normally distributed with confidenceIs a statistic of alpha;
step 4: through real-time principal component mathematical model data monitoring, through Hotelling T2And judging whether a fault is generated or not by the control limit expression of the SPE statistic, thereby realizing accurate prediction and monitoring of the fault of the one-way valve, wherein the specific judgment standard is as follows:
if it is
Indicating that the one-way valve is operating normally;
if it is
Indicating that the check valve is in failure;
if SPE is less than or equal to QαIf the check valve is normal, the check valve is indicated to operate normally;
if SPE > QαIt indicates that the check valve is malfunctioning.
The invention has the beneficial effects that:
1. from data acquisition, the reasonable configuration of the amplifier, the digital-to-analog converter and the FIFO realizes the multi-channel acquisition of data, and the efficiency of each part is utilized to the maximum extent and the accurate acquisition of the data is realized.
2. The wavelet packet decomposition method establishes a concept of time-frequency space, provides a flexible time-frequency window, can have fine time resolution at a high frequency position and good frequency resolution at a low frequency position, can visually identify the reflection of fault characteristic information on different frequency channels and the distribution condition of energy, has the capability of hiding detection in data which is not available in other signal analysis technologies, and is particularly important for damage detection.
3. Data are collected through hardware equipment, are not subjected to terrain limit value wireless transmission, can be transmitted to a host computer for data analysis at the first time, are more accurate than manual judgment, and can also judge the fault of the check valve instantly through real-time online analysis, so that the accuracy and the rapidness are realized.
4. Due to the fact that real-time detection is achieved, timely adjustment can be conducted in the first time of failure, the probability that damage to the diaphragm pump is caused by valve body damage is reduced, unnecessary valve body replacement is avoided, production efficiency is improved, replacement cost of the one-way valve is reduced, and the effect of energy conservation and economy is achieved.
Drawings
FIG. 1 is a schematic diagram of the system of the present invention;
FIG. 2 is a flow chart of data analysis according to the present invention.
In the figure: the system comprises a sound acquisition sensor, a 2-signal preamplifier, a 3-data digital-to-analog converter, a 4-first-in first-out arrangement element, a 5-single chip processor, a 6-pulse width modulation module, a 7-clock frequency testing element, an 8-ZigBee wireless transmission module and a 9-host.
Detailed Description
The invention is further described with reference to the following drawings and detailed description.
Example 1: as shown in fig. 1, an online nondestructive one-way valve fault detection system comprises a sound collection sensor 1, a signal preamplifier 2, a data digital-to-analog converter 3, a first-in first-out arrangement element 4, a single chip processor 5, a pulse width modulation module 6, a clock frequency testing element 7, a ZigBee wireless transmission module 8 and a host 9;
the sound collection sensor 1 is connected with the signal preamplifier 2, the signal preamplifier 2 is connected with the data digital-to-analog converter 3, the data digital-to-analog converter 3 is connected with the first-in first-out arrangement element 4, the first-in first-out arrangement element 4 is connected with the single chip microcomputer processor 5, the single chip microcomputer processor 5 is connected with the ZigBee wireless transmission module 8, the ZigBee wireless transmission module 8 is connected with the host 9, the pulse width modulation module 6 is connected with the clock frequency testing element 7 and combined with the clock frequency testing element 7, and the combined signal is connected with the data digital-to-analog converter 3 and the first-in first-out arrangement element 4 respectively.
The number of the sound collection sensors 1 can be N, where N is an integer, and the number of the signal preamplifiers 2, the number of the data digital-to-analog converters 3, and the number of the first-in first-out arrangement elements 4 are the same as the number of the sound collection sensors 1.
The sound collecting sensor 1, the signal preamplifier 2, the data digital-to-analog converter 3 and the first-in first-out arrangement element 4 are in a group, each group is connected with the single chip microcomputer processor 5, and each group is provided with the pulse width modulation module 6 and the clock frequency testing element 7.
The sound collection sensor 1 is used for collecting data, and the collected data are transmitted to the singlechip processor 5 through the signal preamplifier 2 and the data digital-to-analog converter 3 for processing.
The data acquisition and transmission can be performed in parallel by means of N sound acquisition sensors 1 and N different channels.
The pulse width modulation module 6 and the clock frequency test element 7 are used to coordinate the transmission and conversion of data.
The pulse width modulation module 6 and the clock frequency test element 7 control the clock frequency of the AD and FIFO using the output of the microprocessor.
The data processed by the singlechip processor 5 is transmitted to the host 9 through the ZigBee wireless transmission module 8 for data analysis.
The working process of the system is as follows: the data acquisition is divided into a plurality of channels for simultaneous acquisition, and each channel is a complete acquisition system; each sound collection sensor 1 is arranged at the one-way valve body, the single chip processor 5 is used as core equipment for data processing, is used for processing collected data and sending the data to the host 9, and the collection speed is adjusted through the pulse width modulation module 6 and the clock frequency testing element 7.
Taking the S-1 channel as an example, when the one-way valve operates and collects data, the sound collection sensor 1 starts to work to collect sound data, the collected data signal enters the next link after being amplified by the signal preamplifier 2, the signal amplified by the signal preamplifier 2 is received, the data digital-to-analog converter 3 converts the analog signal into a digital signal, the data converted into the digital signal is processed by the first-in first-out arrangement element 4 and then input into the singlechip processor 5 for processing, and finally sent to the host computer 9 through the ZigBee wireless transmission module 8, at this moment, the pulse width modulation module 6 and the clock frequency test element 7 can correspondingly adjust the data digital-to-analog converter 3 and the first-in first-out arrangement element 4 according to the processing and running conditions of the singlechip processor 5, so that the reasonable speed processing requirement is met, and the high running efficiency of the singlechip processor 5 is ensured.
In order to acquire accurate signals, N channels can be installed to acquire the operation data of the one-way valve at the same time, and the operation modes and the acquisition processes of other channels are completely the same as those of S-1.
As shown in FIG. 2, C-1 is the acoustic emission signal collected by the data collection system as an input to the data analysis system. The core part of the data analysis system is a principal component analysis method using wavelet packet decomposition, which is a spectrum analysis method and is often used as a basis for fault diagnosis of equipment such as machinery. Principal component analysis is a feature extraction method, namely, after certain transformation, when detecting whether the data contains process fault information, hypothesis test can be carried out by establishing statistic to judge whether the process data deviates from a principal component model. The implementation process is as follows: normal data of the one-way valve operation is collected, a normal one-way valve operation model is established through a data analysis system and is used as a standard to be compared with subsequent models and data, and a fault diagnosis result is obtained. The model is established through data construction, after data acquisition, node coefficients of wavelet decomposition are obtained in a frequency domain through wavelet packet decomposition, energy spectrums of all frequency bands of signals are obtained through 2-norm of the node coefficients, the energy spectrums represent the comprehensive content of the signals and can be used as input data to represent information represented by the signals, so that a normal model for the operation of the one-way valve can be established accurately by using the energy spectrums as input principal component analysis, and a test model is established for comparing later-acquired test data to determine the operation condition of the test data.
While the present invention has been described in detail with reference to the embodiments shown in the drawings, the present invention is not limited to the embodiments, and various changes can be made without departing from the spirit and scope of the present invention.
Claims (9)
1. The utility model provides a harmless check valve fault detection system based on it is online which characterized in that: the system comprises a sound acquisition sensor (1), a signal preamplifier (2), a data digital-to-analog converter (3), a first-in first-out arrangement element (4), a singlechip processor (5), a pulse width modulation module (6), a clock frequency testing element (7), a ZigBee wireless transmission module (8) and a host (9);
the sound collection sensor (1) is connected with the signal preamplifier (2), the signal preamplifier (2) is connected with the data digital-to-analog converter (3), the data digital-to-analog converter (3) is connected with the first-in first-out arrangement element (4), the first-in first-out arrangement element (4) is connected with the single chip microcomputer processor (5), the single chip microcomputer processor (5) is connected with the ZigBee wireless transmission module (8), the ZigBee wireless transmission module (8) is connected with the host (9), the pulse width modulation module (6) is connected with the clock frequency testing element (7) and combined, and the combined signal is connected with the data digital-to-analog converter (3) and the first-in first-out arrangement element (4) respectively.
2. The online-based nondestructive unidirectional valve fault detection system of claim 1 wherein: the number of the sound collection sensors (1) can be N, N is an integer, and the number of the signal preamplifiers (2), the number of the data digital-to-analog converters (3) and the number of the first-in first-out arrangement elements (4) are the same as that of the sound collection sensors (1).
3. The online-based nondestructive unidirectional valve fault detection system of claim 2 wherein: the sound collection sensor (1), the signal preamplifier (2), the data digital-to-analog converter (3) and the first-in first-out arrangement element (4) are in a group, each group is connected with the single chip processor (5), and each group is provided with the pulse width modulation module (6) and the clock frequency test element (7).
4. The online-based nondestructive unidirectional valve fault detection system of claim 2 wherein: the sound collection sensor (1) is used for collecting data, and the collected data are transmitted to the single chip processor (5) through the signal preamplifier (2) and the data digital-to-analog converter (3) to be processed.
5. The online-based nondestructive unidirectional valve fault detection system of claim 4 wherein: the data acquisition and transmission can be performed in parallel by means of N sound acquisition sensors (1) and N different channels.
6. The online-based nondestructive unidirectional valve fault detection system of claim 1 wherein: the pulse width modulation module (6) and the clock frequency test element (7) are used to coordinate the transmission and conversion of data.
7. The online-based nondestructive unidirectional valve fault detection system of claim 3 wherein: the pulse width modulation module (6) and the clock frequency test element (7) utilize the output of the microprocessor to control the clock frequency of the AD and the FIFO.
8. The online-based nondestructive unidirectional valve fault detection system of claim 3 wherein: the data processed by the single chip processor (5) are transmitted to a host (9) through a ZigBee wireless transmission module (8) for data analysis.
9. The method for fault detection in an online-based nondestructive unidirectional valve fault detection system of claim 1 wherein:
step 1: a sound collection sensor (1) is arranged at each one-way valve body, signals of the sensors are amplified and transmitted to a data digital-to-analog converter (3), then are stored in a single chip processor (5) in a queue form, and finally, the data are transmitted to a host (9) for later analysis;
step 2: establishing a normal model in the running process of the one-way valve to obtain a threshold value of the model in normal running, wherein the specific method for establishing the model comprises the following steps:
according to the collected normal data, hexadecimal machine data is converted into decimal operation data in a host (9), wavelet packet decomposition is carried out on the converted data, signal data are decomposed into approximate signal data and detail signal data by a high-pass filter and a low-pass filter, and a dual-scale equation is obtained through a scale function and a wavelet function:
where phi (t) is a scale function, phi (t) is a wavelet function, and h0kIs the coefficient of the high-pass filter, h1kIs the coefficient of the low-pass filter, t ∈ [1, N]N is the number of data points, k is N/2lL represents the number of layers of wavelet packet decomposition;
according to the node coefficient after wavelet packet decomposition, obtaining energy values under different frequency bands, and then obtaining energy spectrums under different frequency bands:
E(tj)＝∫R|f(tj)|2dt＝∑|xj|2
wherein R represents a real number domain, f (t)j) Representing the reconstructed signal, E (t)j) Denotes f (t)j) Corresponding energy, xjDenotes f (t)j) J is 0,1,2, …,2nRepresenting the number of nodes of each layer;
step 3: by Hotelling T in principal component model2And calculating the degree of the data deviating from the normal model by the SPE statistic, and defining a sampling data vector X at a certain moment as follows:
Ti 2＝tiλ-1ti T＝XiPλ-1PTXi T
in the formula, tiIs the score vector of the ith principal component, lambda is a diagonal matrix formed by eigenvalues corresponding to the first i principal elements, and P is a reversible matrix;
when the pressure is within the control limit, the check valve is in a normal state, if the pressure exceeds the control limit, the fault is shown, and Hotelling T2The statistical quantity control limit is:
wherein m is the number of samples, k is the number of pivot elements, Fk,m-1,αAn upper limit value of an F distribution representing a confidence degree α;
for a sample data vector x at a certain time instant, the SPE statistic is defined as follows:
when the SPE is within the control limit of the SPE, the one-way valve is in a normal state, and if the SPE exceeds the control limit, a fault is generated;
the SPE control limits are:
in the formula (I), the compound is shown in the specification,
l is the number of principal elements, λiIs the eigenvalue of the covariance matrix of X, cαStatistics with normal distribution confidence coefficient alpha;
step 4: through real-time principal component mathematical model data monitoring, through Hotelling T2And judging whether a fault is generated or not by the control limit expression of the SPE statistic, thereby realizing accurate prediction and monitoring of the fault of the one-way valve, wherein the specific judgment standard is as follows:
if it is
Indicating that the one-way valve is operating normally;
if it is
Indicating that the check valve is in failure;
if SPE is less than or equal to QαIf the check valve is normal, the check valve is indicated to operate normally;
if SPE > QαIt indicates that the check valve is malfunctioning.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110684582.XA CN113447260A (en) | 2021-06-21 | 2021-06-21 | Online-based nondestructive one-way valve fault detection system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110684582.XA CN113447260A (en) | 2021-06-21 | 2021-06-21 | Online-based nondestructive one-way valve fault detection system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113447260A true CN113447260A (en) | 2021-09-28 |
Family
ID=77811978
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110684582.XA Pending CN113447260A (en) | 2021-06-21 | 2021-06-21 | Online-based nondestructive one-way valve fault detection system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113447260A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114460456A (en) * | 2022-04-13 | 2022-05-10 | 天津美腾科技股份有限公司 | Electromagnetic valve fault detection method, device and system and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN206056770U (en) * | 2016-07-04 | 2017-03-29 | 广东理工学院 | Check valve acoustic emission signal acquisition system |
| CN206280231U (en) * | 2016-10-18 | 2017-06-27 | 广东理工学院 | A kind of fault monitoring device of positive displacement pump |
-
2021
- 2021-06-21 CN CN202110684582.XA patent/CN113447260A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN206056770U (en) * | 2016-07-04 | 2017-03-29 | 广东理工学院 | Check valve acoustic emission signal acquisition system |
| CN206280231U (en) * | 2016-10-18 | 2017-06-27 | 广东理工学院 | A kind of fault monitoring device of positive displacement pump |
Non-Patent Citations (2)
| Title |
|---|
| 田宁: "单向阀声发射信号的故障诊断研究", 《中国优秀硕士学位论文全文数据库 (基础科学辑)》, no. 2, pages 034 - 14 * |
| 田宁等: "单向阀的小波包核主元分析故障检测", 《计算机应用》, vol. 33, no. 1, pages 291 - 294 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114460456A (en) * | 2022-04-13 | 2022-05-10 | 天津美腾科技股份有限公司 | Electromagnetic valve fault detection method, device and system and storage medium |
| CN114460456B (en) * | 2022-04-13 | 2022-07-12 | 天津美腾科技股份有限公司 | Electromagnetic valve fault detection method, device and system and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112200244B (en) | Intelligent detection method for anomaly of aerospace engine based on hierarchical countermeasure training | |
| CN102072829B (en) | Iron and steel continuous casting equipment oriented method and device for forecasting faults | |
| CN109029589B (en) | Bridge structures safety condition monitoring system | |
| JP7261427B2 (en) | Myoelectric Signal-Torque Matching Method Based on Multi-grain Parallelized CNN Model | |
| CN109396954B (en) | Embedded axis system abnormality intelligent measurement and information push-delivery apparatus | |
| CN109443719B (en) | Drill bit vibration signal online virtual test method and system thereof | |
| CN110824281A (en) | Method and system for on-line monitoring and fault diagnosis of synchronous phase modulator | |
| CN108435819B (en) | Energy consumption abnormity detection method for aluminum profile extruder | |
| CN111679241B (en) | Multi-information-channel automatic switching system and method for electric energy meter verification assembly line | |
| CN113027658B (en) | Real-time state evaluation method for water turbine runner and application thereof | |
| CN113447260A (en) | Online-based nondestructive one-way valve fault detection system and method | |
| CN107607342B (en) | Healthy energy efficiency detection method for air conditioner room equipment group | |
| CN110632484A (en) | ELM-based GIS partial discharge defect diagnosis and classification system and method | |
| CN116517860A (en) | Ventilator fault early warning system based on data analysis | |
| CN111523572A (en) | Real-time bridge structure damage state identification method and system | |
| CN201035376Y (en) | Failure diagnosis device under small sample conditional in the process of manufacturing production | |
| CN211478951U (en) | Fault diagnosis device and fault diagnosis system | |
| CN112749764B (en) | Aeroengine running state classification method based on QAR data | |
| CN114330489A (en) | Fault diagnosis method and system for monitoring equipment | |
| CN114354184A (en) | Deep learning-based method and device for establishing health early warning model of main shaft of large-scale rotating equipment | |
| CN114492146B (en) | Bolt group loosening positioning and quantitative analysis method and system based on transfer learning | |
| CN115684908A (en) | State monitoring method for power GIS equipment, storage medium and electronic device | |
| CN114233581A (en) | Intelligent patrol alarm system for fan engine room | |
| CN206056770U (en) | Check valve acoustic emission signal acquisition system | |
| CN109102001A (en) | A kind of gene improve the rotor on-line fault diagnosis method of neural network |
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 |