CN114233581A - Intelligent patrol alarm system for fan engine room - Google Patents
Intelligent patrol alarm system for fan engine room Download PDFInfo
- Publication number
- CN114233581A CN114233581A CN202111516143.4A CN202111516143A CN114233581A CN 114233581 A CN114233581 A CN 114233581A CN 202111516143 A CN202111516143 A CN 202111516143A CN 114233581 A CN114233581 A CN 114233581A
- Authority
- CN
- China
- Prior art keywords
- data
- inspection
- sensor
- layer
- terminal software
- 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
- 238000012544 monitoring process Methods 0.000 claims abstract description 36
- 238000007689 inspection Methods 0.000 claims description 46
- 238000011176 pooling Methods 0.000 claims description 36
- 238000013527 convolutional neural network Methods 0.000 claims description 22
- 238000000034 method Methods 0.000 claims description 12
- 238000001228 spectrum Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 11
- 238000004458 analytical method Methods 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 239000013598 vector Substances 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 238000010586 diagram Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 230000009977 dual effect Effects 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 230000003993 interaction Effects 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 238000004904 shortening Methods 0.000 claims description 3
- 230000001960 triggered effect Effects 0.000 claims description 2
- 238000012360 testing method Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000010248 power generation Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03D—WIND MOTORS
- F03D17/00—Monitoring or testing of wind motors, e.g. diagnostics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Sustainable Development (AREA)
- Sustainable Energy (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention discloses an intelligent patrol alarm system for a fan cabin, which comprises state monitoring sensors, an industrial personal computer and terminal software, wherein the industrial personal computer is connected between the state monitoring sensors and the terminal software, the state monitoring sensors detect state information of the fan cabin in real time, the industrial personal computer acquires data of each state monitoring sensor in real time and transmits the data to the terminal software, the terminal software calculates the state of the fan cabin according to the data of the state monitoring sensors, and an alarm signal is generated and transmitted to the state monitoring sensors when an alarm condition is reached; the industrial personal computer generates a polling signal according to the polling plan or the immediate polling instruction of the terminal software and sends the polling signal to the state monitoring sensor.
Description
Technical Field
The invention relates to a fan cabin monitoring system, in particular to an intelligent patrol alarm system for a fan cabin.
Background
With the increasing environmental and energy problems, the development of renewable energy is a necessary trend. Wind power generation is a power generation mode with a mature clean renewable energy development technology, and has received wide attention at present. In recent years, the number of wind fields of the wind turbine is increased sharply, the fault maintenance difficulty of the wind turbine is high, and mature and experienced operation and maintenance personnel are relatively few. A separate monitoring system would be labor intensive for the worker.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides an intelligent inspection alarm system for fan warehousing, which can effectively monitor, analyze and alarm each state of a fan.
In order to solve the technical problem, the technical scheme adopted by the invention is as follows: an intelligent patrol alarm system for a fan engine room comprises a state monitoring sensor, an industrial personal computer and terminal software, wherein the industrial personal computer is connected between the state monitoring sensor and the terminal software and is used for realizing information interaction between the state monitoring sensor and the terminal software; the state monitoring sensors detect state information of the fan cabin in real time, the industrial personal computer collects data of the state monitoring sensors in real time and transmits the data to the terminal software, the terminal software calculates the state of the fan cabin according to the data of the state monitoring sensors, and when an alarm condition is met, an alarm signal is generated and transmitted to the state monitoring sensors; the industrial personal computer generates a polling signal according to a polling plan or an immediate polling instruction of terminal software and sends the polling signal to the state monitoring sensor;
the state monitoring sensor comprises dual-spectrum equipment, a gas sensor, a sound pressure meter and a vibration sensor, and the vibration sensor is arranged in the fan and used for collecting vibration information of the fan; the gas sensor is used for detecting the gas content of the specified gas in the cabin of the fan, and the sound pressure meter is used for detecting the sound pressure inside the fan; the dual spectrum device is used for acquiring the temperature of a specific part of the cabin and providing real-time video preview.
Further, vibration information acquired by the vibration sensor is transmitted to an improved convolutional neural network to perform fault analysis on the vibration data, wherein the improved convolutional neural network comprises a plurality of convolutional pooling layers, an enhancement convolutional layer connected behind the plurality of convolutional pooling layers, a full-connection layer connected behind the enhancement convolutional layer and an output layer connected behind the full-connection layer;
the improved convolutional neural network carries out fault analysis on the vibration data in the following process:
s01), converting the one-dimensional time domain vibration signal into a two-dimensional matrix, wherein the conversion mode is as follows: firstly, adding a window function to a time domain vibration signal, dividing the time domain vibration signal into a plurality of segments in a sliding window mode, and performing fast Fourier transform on each segment to obtain a real-time spectrogram of vibration data, wherein the real-time spectrogram is a two-dimensional matrix;
s02), transmitting the real-time spectrogram of the vibration data to an improved convolutional neural network, wherein the improved convolutional neural network firstly carries out convolution calculation on the input real-time spectrogram through a plurality of convolution pooling layers, extracts features from the input image and outputs feature vectors;
s03), in order to mine more fault features and make the judgment result more accurate, transmitting the feature vectors generated by a plurality of convolution pooling layers into the enhanced convolution layer, and performing convolution operation again;
s04), flattening the eigenvector obtained in the step S03), and then transmitting the eigenvector into a full connection layer, wherein the full connection layer carries out secondary classification on the eigenvector obtained before;
s05), the classification result of the full connection layer is transmitted to the output layer, the output layer maps a plurality of scalars output by the full connection layer into a normalized probability distribution through the classifier, and the confidence coefficient of the classification result is output.
Furthermore, the convolution layer of the convolution pooling layer is composed of a plurality of convolution kernels with the same size, the convolution kernels and the corresponding image pixel arrangement are convoluted, the features are extracted from the input image, and a feature map is output; the convolution operation is linear operation, and after the convolution operation, nonlinear mapping is carried out; and inputting the feature map generated by the convolutional layer into a pooling layer of the convolutional pooling layer, wherein the pooling layer is used for carrying out rectangular segmentation on the feature map, combining adjacent pixels in an image area into a single representative value, reducing the size of the feature map and deleting redundant information, thereby reducing the size of the model and shortening the training time.
Further, the pooling layer selects the maximum pooling scheme, and selects the maximum value among the adjacent pixels to be output as the representative value.
Further, the output layer outputs the probability of failure and the probability of no failure, and when the probability of failure is more than 80%, the output layer judges that the vibration is abnormal and triggers an alarm.
Furthermore, data collected by the temperature sensor, the sound pressure sensor and the gas sensor are compared with a preset threshold value, and when the collected data are not in the range of the preset threshold value, alarm information is generated according to the collected data.
Further, the industrial personal computer obtains all sensor information of the fan from the terminal software server after operation, if the server is not connected, the sensor information which is operated last time is obtained from the configuration file, real-time data is collected according to the sensor information and stored in the data server, and the terminal software obtains the real-time data of each sensor from the data server.
Further, the industrial personal computer acquires related information of timing inspection from the terminal software server, if the industrial personal computer is not connected to the front-end server software, the last timing inspection information is acquired from the configuration file, the equipment performs inspection according to the inspection plan according to the acquired timing inspection information, and if an immediate inspection instruction of the terminal software is received, the equipment immediately starts inspection.
Furthermore, in the inspection process, the double-spectrum equipment cruises at preset important positions, the crusing time and speed can be set, and if the double-spectrum equipment receives alarm information sent by a server in the inspection process, inspection is immediately stopped.
Furthermore, after equipment inspection is finished, inspection files of all sensors are generated, the generated inspection files are uploaded to the FTP server, and the industrial personal computer sends the path of the inspection files to terminal software, so that inspection records can be conveniently inquired later.
The invention has the beneficial effects that: the invention provides an intelligent patrol alarm system for a fan cabin, which can be used for carrying out unified centralized monitoring and management on fans in a plurality of wind fields, displaying various data collected in the cabin in real time, and triggering alarm when detecting that the fan cabin is abnormal, thereby greatly reducing the labor intensity of workers and helping technical workers to find and process the abnormality more quickly. The improved CNN model is provided for carrying out fault judgment on vibration data, and the fault judgment accuracy of time domain vibration signals is enhanced.
Drawings
FIG. 1 is a functional block diagram of the present invention;
fig. 2 is a schematic block diagram of an improved CNN network.
Detailed Description
The invention is further described with reference to the following figures and specific embodiments.
Example 1
The embodiment discloses an intelligent patrol alarm system for a fan engine room, which comprises a state monitoring sensor, an industrial personal computer and terminal software, wherein the industrial personal computer is connected between the state monitoring sensor and the terminal software and is used for realizing information interaction between the state monitoring sensor and the terminal software; the state monitoring sensors detect state information of the fan cabin in real time, the industrial personal computer collects data of the state monitoring sensors in real time and transmits the data to the terminal software, the terminal software calculates the state of the fan cabin according to the data of the state monitoring sensors, and when an alarm condition is met, an alarm signal is generated and transmitted to the state monitoring sensors; the industrial personal computer generates a polling signal according to the polling plan or the immediate polling instruction of the terminal software and sends the polling signal to the state monitoring sensor.
The state monitoring sensor comprises dual-spectrum equipment, a gas sensor, a sound pressure meter and a vibration sensor, and the vibration sensor is arranged in the fan and used for collecting vibration information of the fan; the gas sensor is used for detecting the gas content of the specified gas in the cabin of the fan, and the sound pressure meter is used for detecting the sound pressure inside the fan; the dual spectrum device is used for acquiring the temperature of a specific part of the cabin and providing real-time video preview.
The terminal software is divided into a client and a server, and the server mainly has the functions of managing fans of each wind field, acquiring and storing real-time fan working condition data, recording management of alarm data, inspection data, log data and some basic historical data, persistently storing data of each sensor and the like. The client software mainly realizes the functions of real-time working condition, routing inspection management, alarm processing, various data query, log browsing and the like.
In this embodiment, the vibration information acquired by the vibration sensor is transferred to the improved convolutional neural network to perform fault analysis on the vibration data, as shown in fig. 2, the improved convolutional neural network includes a plurality of convolutional pooling layers, an enhanced convolutional layer connected after the plurality of convolutional pooling layers, a full-link layer connected after the enhanced convolutional layer, and an output layer connected after the full-link layer;
the improved convolutional neural network carries out fault analysis on the vibration data in the following process:
s01), converting the one-dimensional time domain vibration signal into a two-dimensional matrix, wherein the conversion mode is as follows: firstly, adding a window function to a time domain vibration signal, dividing the time domain vibration signal into a plurality of segments in a sliding window mode, and performing fast Fourier transform on each segment to obtain a real-time spectrogram of vibration data, wherein the real-time spectrogram is a two-dimensional matrix;
s02), transmitting the real-time spectrogram of the vibration data to an improved convolutional neural network, wherein the improved convolutional neural network firstly carries out convolution calculation on the input real-time spectrogram through a plurality of convolution pooling layers, extracts features from the input image and outputs feature vectors;
s03), in order to mine more fault features and make the judgment result more accurate, transmitting the feature vectors generated by a plurality of convolution pooling layers into the enhanced convolution layer, and performing convolution operation again;
s04), flattening the eigenvector obtained in the step S03), and then transmitting the eigenvector into a full connection layer, wherein the full connection layer carries out secondary classification on the eigenvector obtained before;
s05), the classification result of the full connection layer is transmitted to the output layer, the output layer maps a plurality of scalars output by the full connection layer into a normalized probability distribution through the classifier, and the confidence coefficient of the classification result is output.
The convolution layer of the convolution pooling layer is composed of a plurality of convolution kernels with the same size, the convolution kernels are arranged with corresponding image pixels for convolution, characteristics are extracted from the input image, and a characteristic diagram is output; the convolution operation is linear operation, and after the convolution operation, nonlinear mapping is carried out; and inputting the feature map generated by the convolutional layer into a pooling layer of the convolutional pooling layer, wherein the pooling layer is used for carrying out rectangular segmentation on the feature map, combining adjacent pixels in an image area into a single representative value, reducing the size of the feature map and deleting redundant information, thereby reducing the size of the model and shortening the training time.
The pooling mode is divided into maximum pooling and average pooling, wherein the maximum pooling selects the maximum value from adjacent pixels to be output as a representative value, and the average pooling is that the average value of the adjacent pixels is taken to be output as the representative value. The pooling regime selected in the pooling layer in the present system is maximum pooling. And the output layer outputs the probability of failure and the probability of no failure, and when the probability of failure is more than 80%, the judgment is that the vibration is abnormal and an alarm is triggered.
The improved CNN network is trained before being used, and vibration data in samples are added with response fault state labels to be used as a sample pair in collected fault samples. 70% of the samples were taken as the training set and 30% as the test set. And the training set is used for improving the training of the CNN model, and vibration data in the training set is learned with the fault label. And after the training is finished, sending the test set without the label into the CNN model for testing to obtain a fault judgment result, evaluating the generalization capability of the improved CNN model compared with a real result, updating parameters in the CNN model by using an SGDM algorithm if the evaluation result does not meet the training termination condition, and repeating the training process until the evaluation result meets the training termination condition.
And comparing the data acquired by the temperature sensor, the sound pressure sensor and the gas sensor with a preset threshold value, and analyzing and generating alarm information according to the acquired data when the acquired data is not in the range of the preset threshold value.
The industrial personal computer obtains all sensor information of the fan from the terminal software server after running, if the server is not connected, the sensor information which runs last time is obtained from the configuration file, real-time data are collected according to the sensor information and stored in the data server, and the terminal software obtains the real-time data of each sensor from the data server.
The industrial personal computer acquires relevant information of timing inspection from the terminal software server, if the industrial personal computer is not connected to the front-end server software, the last timing inspection information is acquired from the configuration file, the equipment inspects according to the inspection plan according to the acquired timing inspection information, and if an immediate inspection instruction of the terminal software is received, the equipment immediately starts inspection.
And in the inspection process, the double-spectrum equipment cruises at the preset important part, the crusing time and speed can be set, and if the double-spectrum equipment receives alarm information sent by a server in the inspection process, the inspection is immediately stopped.
After equipment inspection is completed, inspection files of all sensors are generated, the generated inspection files are uploaded to the FTP server, and the industrial personal computer sends the path of the inspection files to terminal software, so that inspection records can be conveniently inquired later.
The foregoing description is only for the basic principle and the preferred embodiments of the present invention, and modifications and substitutions by those skilled in the art are included in the scope of the present invention.
Claims (10)
1. The utility model provides a fan cabin intelligence patrol alarm system which characterized in that: the industrial personal computer is connected between the state monitoring sensor and the terminal software and is used for realizing information interaction between the state monitoring sensor and the terminal software; the state monitoring sensors detect state information of the fan cabin in real time, the industrial personal computer collects data of the state monitoring sensors in real time and transmits the data to the terminal software, the terminal software calculates the state of the fan cabin according to the data of the state monitoring sensors, and when an alarm condition is met, an alarm signal is generated and transmitted to the state monitoring sensors; the industrial personal computer generates a polling signal according to a polling plan or an immediate polling instruction of terminal software and sends the polling signal to the state monitoring sensor;
the state monitoring sensor comprises dual-spectrum equipment, a gas sensor, a sound pressure meter and a vibration sensor, and the vibration sensor is arranged in the fan and used for collecting vibration information of the fan; the gas sensor is used for detecting the gas content of the specified gas in the cabin of the fan, and the sound pressure meter is used for detecting the sound pressure inside the fan; the dual spectrum device is used for acquiring the temperature of a specific part of the cabin and providing real-time video preview.
2. The intelligent patrol alarm system for the wind turbine engine room as claimed in claim 1, wherein: the method comprises the following steps that vibration information collected by a vibration sensor is transmitted to an improved convolutional neural network to carry out fault analysis on vibration data, wherein the improved convolutional neural network comprises a plurality of convolutional pooling layers, an enhanced convolutional layer connected behind the plurality of convolutional pooling layers, a full-connection layer connected behind the enhanced convolutional layer and an output layer connected behind the full-connection layer;
the improved convolutional neural network carries out fault analysis on the vibration data in the following process:
s01), converting the one-dimensional time domain vibration signal into a two-dimensional matrix, wherein the conversion mode is as follows: firstly, adding a window function to a time domain vibration signal, dividing the time domain vibration signal into a plurality of segments in a sliding window mode, and performing fast Fourier transform on each segment to obtain a real-time spectrogram of vibration data, wherein the real-time spectrogram is a two-dimensional matrix;
s02), transmitting the real-time spectrogram of the vibration data to an improved convolutional neural network, wherein the improved convolutional neural network firstly carries out convolution calculation on the input real-time spectrogram through a plurality of convolution pooling layers, extracts features from the input image and outputs feature vectors;
s03), in order to mine more fault features and make the judgment result more accurate, transmitting the feature vectors generated by a plurality of convolution pooling layers into the enhanced convolution layer, and performing convolution operation again;
s04), flattening the eigenvector obtained in the step S03), and then transmitting the eigenvector into a full connection layer, wherein the full connection layer carries out secondary classification on the eigenvector obtained before;
s05), the classification result of the full connection layer is transmitted to the output layer, the output layer maps a plurality of scalars output by the full connection layer into a normalized probability distribution through the classifier, and the confidence coefficient of the classification result is output.
3. The intelligent patrol alarm system for the wind turbine engine room as claimed in claim 2, wherein: the convolution layer of the convolution pooling layer is composed of a plurality of convolution kernels with the same size, the convolution kernels are arranged with corresponding image pixels for convolution, characteristics are extracted from the input image, and a characteristic diagram is output; the convolution operation is linear operation, and after the convolution operation, nonlinear mapping is carried out; and inputting the feature map generated by the convolutional layer into a pooling layer of the convolutional pooling layer, wherein the pooling layer is used for carrying out rectangular segmentation on the feature map, combining adjacent pixels in an image area into a single representative value, reducing the size of the feature map and deleting redundant information, thereby reducing the size of the model and shortening the training time.
4. The intelligent patrol alarm system for the wind turbine engine room as claimed in claim 3, wherein: the pooling layer selects the maximum pooling scheme, and selects the maximum value among the adjacent pixels to be output as a representative value.
5. The intelligent patrol alarm system for the wind turbine engine room as claimed in claim 2, wherein: and the output layer outputs the probability of failure and the probability of no failure, and when the probability of failure is more than 80%, the judgment is that the vibration is abnormal and an alarm is triggered.
6. The intelligent patrol alarm system for the wind turbine engine room as claimed in claim 1, wherein: and comparing the data acquired by the temperature sensor, the sound pressure sensor and the gas sensor with a preset threshold value, and analyzing and generating alarm information according to the acquired data when the acquired data is not in the range of the preset threshold value.
7. The intelligent patrol alarm system for the wind turbine engine room as claimed in claim 1, wherein: the industrial personal computer obtains all sensor information of the fan from the terminal software server after running, if the server is not connected, the sensor information which runs last time is obtained from the configuration file, real-time data are collected according to the sensor information and stored in the data server, and the terminal software obtains the real-time data of each sensor from the data server.
8. The intelligent patrol alarm system for the wind turbine engine room as claimed in claim 1, wherein: the industrial personal computer acquires relevant information of timing inspection from the terminal software server, if the industrial personal computer is not connected to the front-end server software, the last timing inspection information is acquired from the configuration file, the equipment inspects according to the inspection plan according to the acquired timing inspection information, and if an immediate inspection instruction of the terminal software is received, the equipment immediately starts inspection.
9. The intelligent patrol alarm system for the wind turbine engine room as claimed in claim 1, wherein: and in the inspection process, the double-spectrum equipment cruises at the preset important part, the crusing time and speed can be set, and if the double-spectrum equipment receives alarm information sent by a server in the inspection process, the inspection is immediately stopped.
10. The intelligent patrol alarm system for the wind turbine engine room as claimed in claim 1, wherein: after equipment inspection is completed, inspection files of all sensors are generated, the generated inspection files are uploaded to the FTP server, and the industrial personal computer sends the path of the inspection files to terminal software, so that inspection records can be conveniently inquired later.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111516143.4A CN114233581A (en) | 2021-12-13 | 2021-12-13 | Intelligent patrol alarm system for fan engine room |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111516143.4A CN114233581A (en) | 2021-12-13 | 2021-12-13 | Intelligent patrol alarm system for fan engine room |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114233581A true CN114233581A (en) | 2022-03-25 |
Family
ID=80755140
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111516143.4A Pending CN114233581A (en) | 2021-12-13 | 2021-12-13 | Intelligent patrol alarm system for fan engine room |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114233581A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116232123A (en) * | 2023-05-06 | 2023-06-06 | 太原理工大学 | Energy self-adaptive conversion device and method based on mining air duct vibration spectrum |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103106765A (en) * | 2013-01-11 | 2013-05-15 | 中国船舶重工集团公司第七二六研究所 | Wind-power cabin fire hazard early-stage monitoring system and monitoring method thereof |
| CN203519144U (en) * | 2013-08-12 | 2014-04-02 | 国电联合动力技术有限公司 | Aerogenerator blade and tower-barrel state monitoring system |
| CN103809556A (en) * | 2013-12-12 | 2014-05-21 | 神华集团有限责任公司 | Fan state monitoring system and method |
| CN106302567A (en) * | 2015-05-14 | 2017-01-04 | 北京三叶瑞风能源科技有限公司 | A kind of blower fan pylon remote real time monitoring system and method |
| CN108120495A (en) * | 2017-12-28 | 2018-06-05 | 东北电力大学 | A kind of wind generating set vibration condition monitoring system based on wireless network |
| CN109214356A (en) * | 2018-09-29 | 2019-01-15 | 南京东振测控技术有限公司 | A kind of fan transmission system intelligent fault diagnosis method based on DCNN model |
| CN109774740A (en) * | 2019-02-03 | 2019-05-21 | 湖南工业大学 | A kind of wheel tread damage fault diagnostic method based on deep learning |
| CN112324628A (en) * | 2020-09-22 | 2021-02-05 | 大唐可再生能源试验研究院有限公司 | Wind turbine generator system hanger rail formula cabin system of patrolling and examining |
| CN112541233A (en) * | 2019-09-20 | 2021-03-23 | 宫文峰 | Rotary machine fault diagnosis method based on improved convolutional neural network |
| CN112621745A (en) * | 2020-11-25 | 2021-04-09 | 中国大唐集团新能源科学技术研究院有限公司 | Wind turbine generator system inspection robot system |
-
2021
- 2021-12-13 CN CN202111516143.4A patent/CN114233581A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103106765A (en) * | 2013-01-11 | 2013-05-15 | 中国船舶重工集团公司第七二六研究所 | Wind-power cabin fire hazard early-stage monitoring system and monitoring method thereof |
| CN203519144U (en) * | 2013-08-12 | 2014-04-02 | 国电联合动力技术有限公司 | Aerogenerator blade and tower-barrel state monitoring system |
| CN103809556A (en) * | 2013-12-12 | 2014-05-21 | 神华集团有限责任公司 | Fan state monitoring system and method |
| CN106302567A (en) * | 2015-05-14 | 2017-01-04 | 北京三叶瑞风能源科技有限公司 | A kind of blower fan pylon remote real time monitoring system and method |
| CN108120495A (en) * | 2017-12-28 | 2018-06-05 | 东北电力大学 | A kind of wind generating set vibration condition monitoring system based on wireless network |
| CN109214356A (en) * | 2018-09-29 | 2019-01-15 | 南京东振测控技术有限公司 | A kind of fan transmission system intelligent fault diagnosis method based on DCNN model |
| CN109774740A (en) * | 2019-02-03 | 2019-05-21 | 湖南工业大学 | A kind of wheel tread damage fault diagnostic method based on deep learning |
| CN112541233A (en) * | 2019-09-20 | 2021-03-23 | 宫文峰 | Rotary machine fault diagnosis method based on improved convolutional neural network |
| CN112324628A (en) * | 2020-09-22 | 2021-02-05 | 大唐可再生能源试验研究院有限公司 | Wind turbine generator system hanger rail formula cabin system of patrolling and examining |
| CN112621745A (en) * | 2020-11-25 | 2021-04-09 | 中国大唐集团新能源科学技术研究院有限公司 | Wind turbine generator system inspection robot system |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116232123A (en) * | 2023-05-06 | 2023-06-06 | 太原理工大学 | Energy self-adaptive conversion device and method based on mining air duct vibration spectrum |
| CN116232123B (en) * | 2023-05-06 | 2023-08-08 | 太原理工大学 | Energy self-adaptive conversion device and method based on mining air duct vibration spectrum |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20230152187A1 (en) | Fault signal locating and identifying method of industrial equipment based on microphone array | |
| CN111060337B (en) | Running equipment real-time fault diagnosis method based on expert system | |
| CN104386449B (en) | On-line checking intelligent protection device is taken turns end to end for mining belt conveyer | |
| KR102427205B1 (en) | Apparatus and method for generating training data of artificial intelligence model | |
| CN111080775A (en) | Server routing inspection method and system based on artificial intelligence | |
| CN117421994A (en) | Edge application health monitoring method and system | |
| CN113962308A (en) | Aviation equipment fault prediction method | |
| CN117975372B (en) | Construction site safety detection system and method based on YOLOv and transducer encoder | |
| CN114233581A (en) | Intelligent patrol alarm system for fan engine room | |
| CN117114420B (en) | Image recognition-based industrial and trade safety accident risk management and control system and method | |
| CN111597948A (en) | Fault detection and classification method for bearing vibration signals | |
| Shaowu et al. | Study on the health condition monitoring method of hydraulic pump based on convolutional neural network | |
| CN117782198B (en) | Highway electromechanical equipment operation monitoring method and system based on cloud edge architecture | |
| CN117932358A (en) | Intelligent remote electric field fault diagnosis method and system | |
| CN113450827A (en) | Equipment abnormal condition voiceprint analysis algorithm based on compressed neural network | |
| CN116168019B (en) | Power grid fault detection method and system based on machine vision technology | |
| CN117825864A (en) | Power distribution network line short-circuit capacity monitoring and diagnosing method and system | |
| CN115826477A (en) | Water area monitoring system and method based on data visualization | |
| CN115931141A (en) | Temperature identification method of infrared temperature measurement map based on improved ANN algorithm | |
| CN113780224B (en) | Unmanned inspection method and system for transformer substation | |
| CN113284103B (en) | Substation equipment defect online detection method based on space transformation fast R-CNN model | |
| CN118172647B (en) | Fusion model debris flow infrasound recognition method based on deep learning | |
| KR102647331B1 (en) | System for providing time-series data based data sampling service | |
| CN118035873B (en) | Fault diagnosis method for parallel convolution improved triple network | |
| CN115001138A (en) | Main network maintenance single-start completion automatic permission system and method for power 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 |