CN202339410U - Radar fault diagnosis system based on back propagation (BP) neural network - Google Patents
Radar fault diagnosis system based on back propagation (BP) neural network Download PDFInfo
- Publication number
- CN202339410U CN202339410U CN2011204761003U CN201120476100U CN202339410U CN 202339410 U CN202339410 U CN 202339410U CN 2011204761003 U CN2011204761003 U CN 2011204761003U CN 201120476100 U CN201120476100 U CN 201120476100U CN 202339410 U CN202339410 U CN 202339410U
- Authority
- CN
- China
- Prior art keywords
- klystron
- output terminal
- data collecting
- data acquisition
- collecting card
- 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.)
- Expired - Fee Related
Links
Images
Abstract
The utility model discloses a radar fault diagnosis system based on a back propagation (BP) neural network, which is mainly composed of a solid state power amplifier (1), a solid state power amplifier data acquisition card (2), a klystron (3), a filament supply (4), a filament supply data acquisition card (5), a beam supply (6), a beam supply data acquisition card (7), a cooling system (8), a cooling system temperature data acquisition card (9), a klystron data acquisition card (10), a high-power circulator (11), a high-power circulator data acquisition card (12), a computer server (13) and a processing display unit (14). The radar fault diagnosis system can monitor performance states of a radar in real time when radar equipment works and timely provide early warning information.
Description
Technical field
The utility model relates to the radar equipment fault diagnosis field, especially relates to a kind of radar fault diagnostic system based on the BP neural network.
Background technology
Each item technical indicator, automaticity and the complicacy of large-scale boat-carrying observing and controlling radar are higher.In so complicated system, a trickle independent failure just is enough to make total system to lose efficacy, and the high reliability of equipment is with maintainable most important for radar system.
The fault diagnosis of current radar system mainly relies on hand inspection; This depends critically upon personnel's experience and technology, and fault diagnosis is random big, and accuracy rate is low; Labor intensive material resources and time are many; Diagnosis efficiency is low, also needs during fault diagnosis equipment is dismantled, detected and installs, and is big to equipment harmfulness.
How fault location rapidly under complex electromagnetic environments and dynamic condition is the target that equipment user is pursued always.Because neural network has nonlinear function and approaches arbitrarily and self-learning capability, so can utilize nerual network technique to carry out the detection and the diagnosis of fault.
The utility model content
The utility model is difficult to the problem of location fast in order to solve present radar fault; Studied the application of BP nerual network technique in the radar fault diagnosis; Set up a kind of radar fault diagnostic system based on the BP neural network; Mainly form by solid state power amplifier 1, solid state power amplifier data collecting card 2, klystron 3, filament supply 4, filament supply data collecting card 5, beam power supply 6, beam current Source Data Acquisition card 7, cooling system 8, cooling system temperature data acquisition card 9, klystron data collecting card 10, high-power circulator 11, high-power circulator data collecting card 12, computer server 13 and processes and displays unit 14; Said solid state power amplifier 1 output terminal is connected with klystron 3 input ends with solid state power amplifier data collecting card 2 input ends; Said klystron 3 input ends are connected with filament supply 4 output terminals, beam power supply 6 output terminals, cooling system 8 output terminals; Filament supply 4 output terminals are connected with filament supply data collecting card 5 input ends; Beam power supply 6 output terminals are connected with beam current Source Data Acquisition card 7 input ends; Cooling system 8 output terminals are connected with cooling system temperature data acquisition card 9 input ends; Klystron 3 output terminals are connected with klystron data collecting card 10 input ends, high-power circulator 11 input ends; High-power circulator 11 output terminals are connected with high-power circulator data collecting card 12 input ends; Solid state power amplifier data collecting card 2 output terminals, filament supply data collecting card 5 output terminals, beam current Source Data Acquisition card 7 output terminals, cooling system temperature data acquisition card 9 output terminals, klystron data collecting card 10 output terminals, high-power circulator data collecting card 12 output terminals are connected with computer server 13 input ends respectively, and computer server 13 output terminals are connected with processes and displays unit 14 input ends.
The implementation procedure of the utility model: solid state power amplifier data collecting card 2 is gathered power input and output power signal from solid state power amplifier 1, outputs to computer server 13 after the processing; Radiofrequency signal outputs to klystron 3 through solid state power amplifier 1; Radiofrequency signal outputs to high-power circulator 11 after klystron 3 amplifies; Filament supply 4 provides emission to gather filament voltage and filament current signal with electronics, filament supply data collecting card 5 from filament supply 4 for klystron 3, outputs to computer server 13 after the processing; Beam power supply 6 improves high pressure for klystron 3; Beam current Source Data Acquisition card 7 is gathered beam voltage and beam current signal from beam power supply 6, outputs to computer server 13 after the processing; Cooling system 8 cooling klystrons 3; Cooling system temperature data acquisition card 9 is gathered wind flow or the water flow signal that cools off klystron from cooling system 8, outputs to computer server 13 after the processing; Klystron data collecting card 10 is gathered income power and output power signal from klystron 3, outputs to computer server 13 after the processing; High-power circulator data collecting card 12 is gathered reflected power signal from high-power circulator 11, outputs to computer server 13 after the processing; Computer server 13 carries out various types of signal to output to processes and displays unit 14 after the simple process.
The beneficial effect of the utility model is:
Equipment fault diagnosis system based on the BP neural network combines radar fault recognition technology, nerual network technique and computer technology; Possess rapid, accurate, the safe characteristics of radar fault diagnosis, avoided simple dependence personal experience to carry out the limitation of fault judgement.
This fault diagnosis system also has stronger adaptability, to different Device Diagnostic objects, as long as gather new apparatus characteristic information, and the threshold values and the training parameter of BP neural network is changed, and just can carry out fault diagnosis to new equipment.
Description of drawings
The utility model will explain through example and with reference to the mode of accompanying drawing, wherein:
Fig. 1 is based on the radar fault diagnostic system structural representation of BP neural network.
Embodiment
Disclosed all characteristics in this instructions, or the step in disclosed all methods or the process except mutually exclusive characteristic and/or the step, all can make up by any way.
Disclosed arbitrary characteristic in this instructions (comprising any accessory claim, summary and accompanying drawing) is only if special narration all can be replaced by other equivalences or the alternative features with similar purpose.That is, only if special narration, each characteristic is an example in a series of equivalences or the similar characteristics.
BP neural network failure diagnostic method schematic diagram as shown in Figure 1; Mainly form by solid state power amplifier 1, solid state power amplifier data collecting card 2, klystron 3, filament supply 4, filament supply data collecting card 5, beam power supply 6, beam current Source Data Acquisition card 7, cooling system 8, cooling system temperature data acquisition card 9, klystron data collecting card 10, high-power circulator 11, high-power circulator data collecting card 12, computer server 13 and processes and displays unit 14; Said solid state power amplifier 1 output terminal is connected with klystron 3 input ends with solid state power amplifier data collecting card 2 input ends; Said klystron 3 input ends are connected with filament supply 4 output terminals, beam power supply 6 output terminals, cooling system 8 output terminals; Filament supply 4 output terminals are connected with filament supply data collecting card 5 input ends; Beam power supply 6 output terminals are connected with beam current Source Data Acquisition card 7 input ends; Cooling system 8 output terminals are connected with cooling system temperature data acquisition card 9 input ends; Klystron 3 output terminals are connected with klystron data collecting card 10 input ends, high-power circulator 11 input ends; High-power circulator 11 output terminals are connected with high-power circulator data collecting card 12 input ends; Solid state power amplifier data collecting card 2 output terminals, filament supply data collecting card 5 output terminals, beam current Source Data Acquisition card 7 output terminals, cooling system temperature data acquisition card 9 output terminals, klystron data collecting card 10 output terminals, high-power circulator data collecting card 12 output terminals are connected with computer server 13 input ends respectively, and computer server 13 output terminals are connected with processes and displays unit 14 input ends.
Solid state power amplifier data collecting card 2 is gathered power input and output power signal from solid state power amplifier 1, outputs to computer server 13 after the processing; Radiofrequency signal outputs to klystron 3 through solid state power amplifier 1; Radiofrequency signal outputs to high-power circulator 11 after klystron 3 amplifies; Filament supply 4 provides emission to gather filament voltage and filament current signal with electronics, filament supply data collecting card 5 from filament supply 4 for klystron 3, outputs to computer server 13 after the processing; Beam power supply 6 improves high pressure for klystron 3; Beam current Source Data Acquisition card 7 is gathered beam voltage and beam current signal from beam power supply 6, outputs to computer server 13 after the processing; Cooling system 8 cooling klystrons 3; Cooling system temperature data acquisition card 9 is gathered wind flow or the water flow signal that cools off klystron from cooling system 8, outputs to computer server 13 after the processing; Klystron data collecting card 10 is gathered income power and output power signal from klystron 3, outputs to computer server 13 after the processing; High-power circulator data collecting card 12 is gathered reflected power signal from high-power circulator 11, outputs to computer server 13 after the processing; Computer server 13 carries out various types of signal to output to processes and displays unit 14 after the simple process.
The utility model is not limited to aforesaid embodiment.The utility model expands to any new feature or any new combination that discloses in this manual, and the arbitrary new method that discloses or step or any new combination of process.
Claims (1)
1. radar fault diagnostic system based on the BP neural network; Mainly form by solid state power amplifier (1), solid state power amplifier data collecting card (2), klystron (3), filament supply (4), filament supply data collecting card (5), beam power supply (6), beam current Source Data Acquisition card (7), cooling system (8), cooling system temperature data acquisition card (9), klystron data collecting card (10), high-power circulator (11), high-power circulator data collecting card (12), computer server (13) and processes and displays unit (14); It is characterized in that: said solid state power amplifier (1) output terminal is connected with klystron (3) input end with solid state power amplifier data collecting card (2) input end; Said klystron (3) input end is connected with filament supply (4) output terminal, beam power supply (6) output terminal, cooling system (8) output terminal; Filament supply (4) output terminal is connected with filament supply data collecting card (5) input end; Beam power supply (6) output terminal is connected with beam current Source Data Acquisition card (7) input end; Cooling system (8) output terminal is connected with cooling system temperature data acquisition card (9) input end; Klystron (3) output terminal is connected with klystron data collecting card (10) input end, high-power circulator (11) input end; High-power circulator (11) output terminal is connected with high-power circulator data collecting card (12) input end; Solid state power amplifier data collecting card (2) output terminal, filament supply data collecting card (5) output terminal, beam current Source Data Acquisition card (7) output terminal, cooling system temperature data acquisition card (9) output terminal, klystron data collecting card (10) output terminal, high-power circulator data collecting card (12) output terminal are connected with computer server (13) input end respectively, and computer server (13) output terminal is connected with processes and displays unit (14) input end.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011204761003U CN202339410U (en) | 2011-11-25 | 2011-11-25 | Radar fault diagnosis system based on back propagation (BP) neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011204761003U CN202339410U (en) | 2011-11-25 | 2011-11-25 | Radar fault diagnosis system based on back propagation (BP) neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN202339410U true CN202339410U (en) | 2012-07-18 |
Family
ID=46488101
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011204761003U Expired - Fee Related CN202339410U (en) | 2011-11-25 | 2011-11-25 | Radar fault diagnosis system based on back propagation (BP) neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN202339410U (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103913728A (en) * | 2014-04-01 | 2014-07-09 | 中国人民解放军总装备部军械技术研究所 | Portable radar general-purpose tester and testing method |
| CN103941240A (en) * | 2014-04-01 | 2014-07-23 | 中国人民解放军总装备部军械技术研究所 | Radar system communication extension detection device and detection methods |
| CN104569934A (en) * | 2014-12-31 | 2015-04-29 | 中国气象局气象探测中心 | Radar fault-handling system |
| CN109856969A (en) * | 2018-11-06 | 2019-06-07 | 皖西学院 | A kind of failure prediction method and forecasting system based on BP neural network model |
-
2011
- 2011-11-25 CN CN2011204761003U patent/CN202339410U/en not_active Expired - Fee Related
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103913728A (en) * | 2014-04-01 | 2014-07-09 | 中国人民解放军总装备部军械技术研究所 | Portable radar general-purpose tester and testing method |
| CN103941240A (en) * | 2014-04-01 | 2014-07-23 | 中国人民解放军总装备部军械技术研究所 | Radar system communication extension detection device and detection methods |
| CN104569934A (en) * | 2014-12-31 | 2015-04-29 | 中国气象局气象探测中心 | Radar fault-handling system |
| CN109856969A (en) * | 2018-11-06 | 2019-06-07 | 皖西学院 | A kind of failure prediction method and forecasting system based on BP neural network model |
| CN109856969B (en) * | 2018-11-06 | 2023-10-03 | 皖西学院 | Fault prediction method and prediction system based on BP neural network model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Serikul et al. | Smart farm monitoring via the Blynk IoT platform: case study: humidity monitoring and data recording | |
| CN202339410U (en) | Radar fault diagnosis system based on back propagation (BP) neural network | |
| CN103454564A (en) | Partial discharge detecting system and method for high voltage switch cabinet | |
| CN111650501A (en) | Testing device for nondestructive online evaluation of aging state of relay | |
| CN103200423A (en) | Delayed detection device of video picture processing system | |
| CN104568327A (en) | Novel ring main unit SF6 gas leakage on-line monitoring device | |
| CN203551679U (en) | Transformer fault diagnosis system based on wavelet transform | |
| CN104359689A (en) | Method and device for testing brake performance of motor train units | |
| CN204269770U (en) | A kind of chip security detection system | |
| CN104485991A (en) | Optical module fault automatic alarm method and system | |
| CN104297595B (en) | The method of electronic equipment radiated immunity test repeatability is improved under the continuous stir mode of reverberation chamber | |
| CN204228199U (en) | A kind of remote monitoring microwave power device long-term reliability test macro | |
| CN204214944U (en) | A kind of general radio frequency condition monitoring and fault diagnosis warning device | |
| CN104374424A (en) | Test system for remotely monitoring long-term reliability of microwave power device | |
| CN201429683Y (en) | Surge protector detection device based on temperature sensor | |
| CN207297240U (en) | A kind of braking resistor resistance value and temperature on-line monitoring device | |
| CN103983372A (en) | Method for measuring operating temperature of power cable connector based on surface acoustic waves | |
| CN105306311A (en) | Electric energy data acquisition local communication reliability test system and method | |
| CN204719127U (en) | A kind of device for detecting power of radio frequency | |
| Aralikatti et al. | IoT-based distribution transformer health monitoring system using node-MCU & Blynk | |
| CN207336645U (en) | A kind of target ship BIT monitorings and acoustooptic alarm system | |
| CN203644200U (en) | Wireless data transmitting system of outdoor operation safety monitoring directing device | |
| CN204346491U (en) | Based on the cable data monitoring system of LabVIEW | |
| CN201546941U (en) | Small flow weak signal test device | |
| CN204313814U (en) | A kind of cable sag detection system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C17 | Cessation of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20120718 Termination date: 20121125 |