CN112101450A - Non-contact vibration measurement equipment and method based on deep learning and multi-sensor fusion - Google Patents
Non-contact vibration measurement equipment and method based on deep learning and multi-sensor fusion Download PDFInfo
- Publication number
- CN112101450A CN112101450A CN202010959133.7A CN202010959133A CN112101450A CN 112101450 A CN112101450 A CN 112101450A CN 202010959133 A CN202010959133 A CN 202010959133A CN 112101450 A CN112101450 A CN 112101450A
- Authority
- CN
- China
- Prior art keywords
- detection
- trolley
- vibration
- equipment
- deep learning
- 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
- G06F18/25—Fusion techniques
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H9/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves by using radiation-sensitive means, e.g. optical means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention discloses a non-contact vibration measurement device and method based on deep learning and multi-sensing fusion, and solves the problem of visual vibration measurement of a water pump house device based on deep learning. The invention relates to a trackless automatic driving detection moving trolley, wherein a high-definition camera, an infrared thermometer, a laser micro-vibration tester and other equipment are arranged on a trolley body. The detection trolley moves to the position right ahead of the detected equipment, the detection camera, the infrared thermometer and the laser micro-vibration tester are all integrated on the detection holder, and the detection holder can rotate in 360 degrees in the horizontal direction and 180 degrees in the vertical direction. The laser micro-vibration tester is arranged right above the detection holder, the detection camera and the infrared thermometer are distributed on two sides of the detection holder, the system can be activated according to the result detected by the laser micro-vibration tester if the detected result is slightly abnormal, and the system can further analyze the current abnormal condition by combining a high-definition video and an infrared video to achieve the function of visual detection equipment micro-vibration detection.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to a non-contact vibration measurement device and method based on deep learning and multi-sensing fusion.
Background
The pump house in the water utilities, because its physical characteristic, can produce the vibration, the detection means of equipment vibration at present mainly relies on the scheme that sets up the vibration detector on the equipment surface, and its principle is: the vibration measurement probe is attached to a position where vibration needs to be detected, information is transmitted out of the equipment through various communication equipment, construction is complex, and the communication equipment is preferably laid completely during early pump house construction. Later development of technology, a contactless laser tester comes out, but because the equipment is expensive, each monitoring point cannot be installed, operation and maintenance personnel need to hold the tester to detect the equipment, and due to various reasons, the comprehensive coverage cannot be achieved.
Disclosure of Invention
The invention aims to provide non-contact vibration measurement equipment and a non-contact vibration measurement method based on deep learning and multi-sensing fusion, which solve the problems of visualization and full coverage of vibration measurement in a pump room, can visualize fault prediction, has abnormity on vibration measurement and can carry out video analysis.
In order to achieve the purpose, the invention is realized by the following technical scheme:
a non-contact vibration measurement device based on deep learning and multi-sensing fusion comprises a non-trolley, a detection cradle head, a detection camera, an infrared thermometer, a laser micro-vibration tester and an edge calculation controller; the detection cloud platform is arranged on the upper portion of the trolley, the laser micro-vibration tester is arranged right above the detection cloud platform, the detection camera is arranged on the left side of the detection cloud platform, the infrared thermometer is arranged on the right side of the detection cloud platform, and the edge calculation controller is arranged on the right side of the trolley.
Preferably, the trolley is a trackless automatic driving trolley which can move at any position in a navigation map based on a SLAM algorithm.
Preferably, the detection holder comprises a connecting rod connected above the trolley and a holder which can rotate by 360 degrees in the horizontal direction and 180 degrees in the vertical direction and is connected to the connecting rod.
A non-contact vibration measurement method based on deep learning and multi-sensing fusion comprises the following steps:
1. and the trackless automatic driving trolley stops right in front of the detection equipment through the task list and rotates the position of the detection holder to the angle of the task point.
2. When the trolley and the detection holder are parked at the position corresponding to the task in the database, a plurality of sensors carried on the trolley start to work, and the laser micro-vibration tester can perform vibration analysis on the detection equipment in real time and output the vibration curve condition of the corresponding equipment.
3. The detection camera and the infrared thermometer can perform model matching on the equipment in real time, perform image video acquisition on the equipment and perform infrared thermography imaging.
4. After all the information is collected, the edge calculation controller based on the deep learning algorithm can carry out video analysis on the abnormal data detection equipment of the tester, and the abnormal conditions of the equipment are analyzed according to real-time video processing.
The invention has the advantages that: the problem of in the pump room vibration measurement visual with full coverage is solved to can visual failure prediction, simplify the detection degree of difficulty, need not artifical the detection, detection device can survey by oneself. In addition, the abnormal vibration measurement can be analyzed and solved through the video shot by the detection camera.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention.
Fig. 1 is a schematic structural diagram of the vibration measuring apparatus of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
A non-contact vibration measurement device and method based on deep learning and multi-sensing fusion comprises a trackless automatic driving detection moving trolley 1, a detection cloud deck 2, a detection camera 3, an infrared thermometer 5, a laser micro-vibration tester 4 and an edge calculation controller 6. The trackless automatic driving detection moving trolley 1 is based on an SLAM algorithm and can move at any position in a navigation map. The trolley 1 is arranged right ahead of the detected equipment, and the detection cradle head 2, the detection camera 3, the infrared thermometer 5 and the laser micro-vibration tester 4 are respectively integrated on the detection trolley 1. The detection camera 3, the infrared thermometer 5 and the laser micro-vibration tester 4 are all arranged on the detection holder 2 in a centralized way, and the detection holder 2 can rotate by 360 degrees in the horizontal direction and 180 degrees in the vertical direction. The laser micro-vibration tester 4 is arranged right above the detection holder 2, and the detection camera 3 and the infrared thermometer 5 are distributed on two sides of the detection holder 2. When management software of the trolley 1 sends a task to the trolley 1, the trolley 1 automatically stops before equipment needing to detect vibration, the detection cloud deck 2 is rotated according to database information to reach a vibration detection point, the detection camera 3 and the infrared thermometer 5 simultaneously take pictures and process heat maps of the detection equipment, when a measurement result of the laser micro-vibration tester 4 is abnormal, the detection camera 3 in the trolley 1 starts to record videos of the monitoring point in real time to perform background analysis, and by combining an infrared thermal imaging map and an edge depth learning algorithm, the vibration condition of the equipment is further analyzed, which fault and the heating condition of the equipment exist, so that operation and maintenance personnel can know the real-time condition of a site more accurately at the first time conveniently, and the vibration detection result is further verified.
A non-contact vibration measurement method based on deep learning and multi-sensing fusion is implemented by the following steps:
1. and the trackless automatic driving trolley 1 stops right in front of the detection equipment through the task list and rotates the position of the detection cloud platform 2 to the angle of the task point.
2. When the trolley 1 and the detection holder 2 are parked at the positions corresponding to the tasks in the database, a plurality of sensors carried on the trolley 1 start to work, and the laser micro-vibration tester 4 can perform vibration analysis on the detection equipment in real time and output the vibration curve conditions of the corresponding equipment.
3. The detection camera 3 and the infrared thermometer 5 can perform model matching on the equipment in real time, perform image video acquisition on the equipment and perform infrared thermography imaging.
4. After collecting all the information, the edge calculation controller 6 based on the deep learning algorithm performs video analysis on the abnormal data detection equipment of the tester, and analyzes the abnormal conditions of the equipment according to real-time video processing.
Claims (4)
1. A non-contact vibration measurement device based on deep learning and multi-sensing fusion is characterized by comprising a non-trolley (1), a detection cloud deck (2), a detection camera (3), an infrared thermometer (5), a laser micro-vibration tester (4) and an edge calculation controller (6); the detection cloud deck (2) is arranged on the upper portion of the trolley (1), the laser micro-vibration tester (4) is arranged right above the detection cloud deck (2), the detection camera (3) is arranged on the left side of the detection cloud deck, the infrared thermometer (5) is arranged on the right side of the detection cloud deck (2), and the edge calculation controller (6) is arranged on the right side of the trolley (1).
2. The contactless vibration measurement device based on deep learning and multi-sensing fusion of claim 1 is characterized in that the trolley (1) is a trackless automatic driving trolley which can realize the movement of any position in a navigation map based on SLAM algorithm.
3. The non-contact vibration measurement equipment based on deep learning and multi-sensing fusion of claim 1 is characterized in that the detection cradle head (2) comprises a connecting rod connected above the trolley (1) and a cradle head which can rotate 360 degrees in the horizontal direction and 180 degrees in the vertical direction and is connected to the connecting rod.
4. A method for non-contact vibration measurement based on deep learning and multi-sensing fusion according to any one of claims 1-3, which is characterized by comprising the following steps:
1) the trackless automatic driving trolley (1) is used for carrying various sensors, automatically driving the trolley to relevant equipment, and rotating the detection cloud deck (2) to reach a vibration measurement point according to the information of the database for detection;
2) when the trolley (1) and the detection holder (2) are parked at the position corresponding to the task in the database, a plurality of sensors carried on the trolley (1) start to work, and the laser micro-vibration meter (4) can carry out vibration analysis on detection equipment in real time and output the vibration curve condition of the corresponding equipment;
3) the detection camera (3) and the infrared thermometer (5) can perform model matching on the equipment in real time, acquire images and videos of the equipment and perform infrared thermograph imaging;
4) after all information is collected, the edge calculation controller (6) based on the deep learning algorithm can carry out video analysis on abnormal data detection equipment of the laser micro-vibration meter (4), and the abnormal conditions of the equipment are analyzed according to real-time video processing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010959133.7A CN112101450A (en) | 2020-09-14 | 2020-09-14 | Non-contact vibration measurement equipment and method based on deep learning and multi-sensor fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010959133.7A CN112101450A (en) | 2020-09-14 | 2020-09-14 | Non-contact vibration measurement equipment and method based on deep learning and multi-sensor fusion |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112101450A true CN112101450A (en) | 2020-12-18 |
Family
ID=73752594
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010959133.7A Pending CN112101450A (en) | 2020-09-14 | 2020-09-14 | Non-contact vibration measurement equipment and method based on deep learning and multi-sensor fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112101450A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113155269A (en) * | 2021-05-08 | 2021-07-23 | 景德镇陶瓷大学 | Non-contact vibration signal acquisition device |
| CN113657426A (en) * | 2021-06-28 | 2021-11-16 | 国网江苏省电力有限公司电力科学研究院 | Heating-vibration combined detection method, device and system for GIL electric contact state |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106774318A (en) * | 2016-12-14 | 2017-05-31 | 智易行科技(武汉)有限公司 | Multiple agent interactive environment is perceived and path planning kinematic system |
| CN207163563U (en) * | 2017-09-18 | 2018-03-30 | 浙江国自机器人技术有限公司 | A kind of contactless vibration detection device |
| CN207301793U (en) * | 2017-04-28 | 2018-05-01 | 南昌航空大学 | A kind of unmanned intelligent vehicle of image recognition processing |
| CN109902640A (en) * | 2019-03-05 | 2019-06-18 | 江南大学 | Video quality abnormality detection system and its detection method based on edge calculations and machine learning |
| CN110329377A (en) * | 2019-06-21 | 2019-10-15 | 广东科学技术职业学院 | A kind of multi-functional detection trolley |
| CN110749372A (en) * | 2018-07-18 | 2020-02-04 | 上海数深智能科技有限公司 | Motor vibration movement intelligent diagnosis system and use method thereof |
| CN110864739A (en) * | 2019-11-28 | 2020-03-06 | 浙江翰德圣智能再制造技术有限公司 | Equipment monitoring and analyzing system based on wireless Internet of things and monitoring and analyzing method thereof |
-
2020
- 2020-09-14 CN CN202010959133.7A patent/CN112101450A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106774318A (en) * | 2016-12-14 | 2017-05-31 | 智易行科技(武汉)有限公司 | Multiple agent interactive environment is perceived and path planning kinematic system |
| CN207301793U (en) * | 2017-04-28 | 2018-05-01 | 南昌航空大学 | A kind of unmanned intelligent vehicle of image recognition processing |
| CN207163563U (en) * | 2017-09-18 | 2018-03-30 | 浙江国自机器人技术有限公司 | A kind of contactless vibration detection device |
| CN110749372A (en) * | 2018-07-18 | 2020-02-04 | 上海数深智能科技有限公司 | Motor vibration movement intelligent diagnosis system and use method thereof |
| CN109902640A (en) * | 2019-03-05 | 2019-06-18 | 江南大学 | Video quality abnormality detection system and its detection method based on edge calculations and machine learning |
| CN110329377A (en) * | 2019-06-21 | 2019-10-15 | 广东科学技术职业学院 | A kind of multi-functional detection trolley |
| CN110864739A (en) * | 2019-11-28 | 2020-03-06 | 浙江翰德圣智能再制造技术有限公司 | Equipment monitoring and analyzing system based on wireless Internet of things and monitoring and analyzing method thereof |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113155269A (en) * | 2021-05-08 | 2021-07-23 | 景德镇陶瓷大学 | Non-contact vibration signal acquisition device |
| CN113657426A (en) * | 2021-06-28 | 2021-11-16 | 国网江苏省电力有限公司电力科学研究院 | Heating-vibration combined detection method, device and system for GIL electric contact state |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021068848A1 (en) | Tunnel structure disease multi-scale measurement and intelligent diagnosis system and method | |
| CN106192634B (en) | A kind of railroad track elastic bar fastener condition automatic detection device and method | |
| CN102567983B (en) | Determining method for positions of monitored targets in instant infrared chart and application | |
| CN109060821B (en) | Tunnel disease detection method and tunnel disease detection device based on laser detection | |
| CN110766785B (en) | Real-time positioning and three-dimensional reconstruction device and method for underground pipeline | |
| CN108733053A (en) | A kind of Intelligent road detection method based on robot | |
| CN206194076U (en) | Substation equipment detecting system | |
| CN109688388A (en) | A method of using the comprehensive real time monitoring of tunnel crusing robot | |
| BR112019018930B1 (en) | METHOD AND ARRANGEMENT FOR MONITORING A CONDITION OF AN INSTALLATION WITH MEANS OF OPERATION | |
| CN102182137A (en) | Pavement defect detection system and method | |
| CN104749187A (en) | Tunnel lining disease detection device based on infrared temperature field and gray level image | |
| CN206628891U (en) | Substation equipment monitoring system | |
| CN115657662A (en) | Autonomous navigation inspection robot based on distributed framework | |
| CN112101450A (en) | Non-contact vibration measurement equipment and method based on deep learning and multi-sensor fusion | |
| CN110850723A (en) | Fault diagnosis and positioning method based on transformer substation inspection robot system | |
| CN105841629A (en) | Photogrammetry monitoring system for monitoring inclination and sedimentation of cultural building relics | |
| CN108956640A (en) | Vehicle-mounted detection apparatus and detection method suitable for distribution line inspection | |
| KR102298643B1 (en) | 3D modeling method of underwater surfaces using infrared thermal imaging camera and drone | |
| CN111610193A (en) | System and method for inspecting structural defects of subway tunnel segment by adopting multi-lens shooting | |
| CN113376252A (en) | Substation main equipment operation state acoustics removes inspection device | |
| CN103729908A (en) | Intelligent inspection device of railway tunnel and application method thereof | |
| CN115793649B (en) | Automatic cable pit inspection device and inspection method | |
| CN104973479A (en) | System and method for monitoring motion state of construction vertical shaft sinking bucket | |
| CN207816842U (en) | A kind of lossless device for fast detecting of cable tunnel defect | |
| Belloni et al. | Tack project: tunnel and bridge automatic crack monitoring using deep learning and photogrammetry |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201218 |
|
| RJ01 | Rejection of invention patent application after publication |