CN105004462A - Fault-identification-based fan energy consumption monitoring system - Google Patents
Fault-identification-based fan energy consumption monitoring system Download PDFInfo
- Publication number
- CN105004462A CN105004462A CN201510480936.3A CN201510480936A CN105004462A CN 105004462 A CN105004462 A CN 105004462A CN 201510480936 A CN201510480936 A CN 201510480936A CN 105004462 A CN105004462 A CN 105004462A
- Authority
- CN
- China
- Prior art keywords
- energy consumption
- fault
- fan
- signal
- eddy current
- 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.)
- Granted
Links
Landscapes
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
- Control Of Positive-Displacement Air Blowers (AREA)
Abstract
Disclosed in the invention is a fault-identification-based fan energy consumption monitoring system comprising three three-shaft acceleration sensors and two eddy-current transducers. The three three-shaft acceleration sensors are respectively arranged on a shaft seat housing, a motor housing, and a ventilator housing; and the two eddy-current transducers perpendicular to each other are arranged in a vertical plane of a rotating shaft. The three-shaft acceleration sensors, the eddy-current transducers, and a signal processing and feature extraction module are connected; and the signal processing and feature extraction module and a neural-network-based classification identification module are connected. During the all-weather energy consumption monitoring process, the low-cost three-shaft acceleration sensors and two eddy-current transducers are installed on the fan and a three-dimensional vibration signal and a shaft center orbit feature vector are inputted into a multi-weight neural network; and the network output is an energy increasing classification value.
Description
The application is application number: the divisional application of 201410257423.1, the applying date: 2014.6.11, title " fan energy consumption monitoring method and system ".
Technical field
The present invention relates to a kind of fan energy consumption monitoring method and system.
Background technology
Blower fan, motor, water pump, compressor are referred to as " industrial motor system " by International Energy Agency (IEA).Point out in National Development and Reform Committee's Eleventh Five-Year Plan energy conservation plan, industrial motor system is the main electric power user of China, and account for more than 50% of whole power consumption, wherein the power consumption of blower fan accounts for 10.4% of national power consumption.Therefore, the raising of fan efficiency, very great to saves energy meaning.
Blower fan system has a large capacity and a wide range, and energy conservation potential is huge.The appearance of " ventilator energy efficiency limit value and efficiency grade " national standard, defines the efficiency grade of ventilation blower, energy efficiency market, Energy efficiency evaluation value and test method, for the research of China's air-foil fan efficiency work provides foundation with carrying out.Also the beginning of China's air-foil fan Energy Labeling work is indicated.On November 1st, 2010, blower fan will formally list the products catalogue (the 6th batch) of People's Republic of China's implementation energy efficiency label in, and had taken up to implement.
Blower fan in the industrial production long-time running time, can produce a lot of fault, the vibration caused as dynamic unbalance (comprises rotor-support-foundation system manufacture process residue uneven; Fan blade in rotary course, due to concentrated wear or corrosion, and local damage or reason such as blocking foreign matter etc.; Fan blower works at high temperature under high pressure, causes cambered axle phenomenon etc. because of thermal deformation and thermal expansion); (data shows, the equipment existence of 30% ~ 50% misaligns problem to misalign the vibration caused.Misalign and both can produce radial vibration, can axial vibration be produced again; Both can cause the vibration closing on shaft coupling supporting place, also can cause the vibration of the free end away from shaft coupling); Machinery loosens (loosening other fault that both may cause machine also may because of caused by other fault, the abrasion deformation of mechanical part, the misaligning of axle system, uneven etc. to influence each other with loosening); The vibration that oil whip causes; Gas impacts the vibration caused; Gaseous tension fluctuates the vibration caused; The vibration that Resonance Wave Composition causes; The various faults of blower fan driving motor, as the drive failure such as axle, belt chain, gear, bearing, motor dust condense, the poor heat radiation caused, lubrication that working time, long or dirt and water pollution caused are good etc. all can cause efficiency to reduce and energy consumption improves in addition.These faults, generally can cause motor and blower fan system heating, various loss increase, thus reduce system effectiveness, increase system energy consumption.Therefore, the existence of various fault reduces (power consumption values raises) with energy valid value and there is cause-effect relationship, excavates the numerical relation between various fault signature and efficiency decreasing value (energy consumption lift-off value), can be used as the foundation of energy consumption monitoring.For enterprise's energy efficiency management, in time eliminate and change high-energy equipment, to realize high-energy equipment maintenance targetedly significant.
The total efficiency of ventilation blower is defined as the ratio that blower fan passes to the energy that the kinetic energy of gas and static energy sum are transmitted with motor.Be used in now the fan energy consumption detection system of other mechanisms such as quality testing department, adopt the test method measuring system constructing about ventilation blower in GB/T 1236-2000 " industrial ventilation machine standardization air channel makes a service test " and GB-19761-2009 " ventilator energy efficiency limit value and efficiency grade " GB, need measure multiparameters such as rotating speed, pressure reduction, flow, power, temperature, torques, the system price of structure is expensive.And existing fan energy consumption checkout equipment is for dissimilar blower fan, additionally to installs the structures such as air duct additional to facilitate flow and wind pressure measurement, and the multiple sensors such as differential pressure pick-up, torque sensor, speed probe need be installed.After blower fan long-time running, various fault can cause energy consumption to increase, and therefore fan energy consumption monitoring is conducive to enterprise's energy efficiency management, eliminates and change high-energy equipment in time, realizes high-energy equipment maintenance targetedly.And above energy consumption detecting method causes existing equipment to be not suitable for blower fan application enterprise to carry out energy consumption monitoring, existing expensive device is more unsuitable for as every Fans coupling realizes round-the-clock energy efficiency monitoring.
Along with the propelling of energy-saving and emission-reduction fundamental state policy, the efficiency that the various faults of blower fan cause reduces and energy consumption improves the attention that each blower fan need be caused to apply enterprise, in addition the efficiency that external electrical network Parameters variation causes reduces and energy consumption increases, also can by fan vibration signal analysis out.Under there is at equipment the prerequisite of high performance-price ratio, for every platform high-power blower is equipped with energy-consumption monitoring device, realize the long-term Real-Time Monitoring of blower fan efficiency, accurately find that the efficiency caused due to various mechanical fault, electric fault or power supply grid Parameters variation reduces phenomenon, for enterprise's energy efficiency management, eliminate and change high-energy equipment in time, to realize high-energy equipment maintenance targetedly significant.
Summary of the invention
The object of the present invention is to provide and be a kind ofly beneficial to enterprise's energy efficiency management, in time eliminate and change high-energy equipment, the fan energy consumption monitoring method realizing high-energy equipment trouble hunting targetedly and system.
Technical solution of the present invention is:
A kind of fan energy consumption monitoring method, is characterized in that: comprise the following steps:
(1) first off-line training sample collection is carried out:
(1) off-line training sample acquisition system builds
Build energy consumption testing system, adopt the multiple sensors comprising torque sensor, differential pressure pick-up, speed probe, detect compressor flow, total pressure of fan, static pressure of fan, volume flow, fan shaft power, final fan efficiency, thus learn ventilation blower energy consumption size;
Adopt three 3-axis acceleration sensors, be placed on bearing seat shell, motor housing, ventilator housing respectively, obtain X, Y, Z tri-axle orthogonal vibration signal of three test points; By gathering vibration signal with the orthogonal eddy current sensor of two in rotating shaft vertical plane simultaneously, and respectively using the figure that gathered data fit to as horizontal, ordinate, be orbit of shaft center;
(2) during blower fan non-fault, training sample off-line obtains
Adopt " signal transacting and characteristic extracting module " to carry out feature extraction, through repetitive measurement, obtain feature samples during many group non-fault; Efficiency value corresponding for feature samples during non-fault is orientated as " energy consumption is low ";
(3) when blower fan has a fault, training sample off-line obtains
The combination of artificial manufacture various faults and various faults, three 3-axis acceleration sensors are adopted to detect the three-dimensional vibrating signal of bearing fan shell, motor housing, ventilator housing 3, two eddy current sensor is adopted to detect axle center trajectory signal, " signal transacting and characteristic extracting module " is adopted to carry out feature extraction, each fault is taken multiple measurements, obtains the feature samples under each fault; The efficiency value when efficiency value in different faults situation and non-fault is compared, according to difference from big to small, is divided into Four types, be defined as " energy consumption is high ", " energy consumption is higher ", " energy consumption is medium ", " energy consumption is on the low side " respectively;
(2) online energy consumption monitoring
Three 3-axis acceleration sensors are adopted to detect the three-dimensional vibrating signal of bearing fan shell, motor housing, ventilator housing 3, two eddy current sensor is adopted to detect axle center trajectory signal, adopt " signal transacting and characteristic extracting module " to carry out feature extraction to signal, obtain tested sample; Adopt multiple weighing value neural network as the core algorithm of " the Classification and Identification module based on neural network ", multiple degrees of freedom neural network in the training sample structure higher dimensional space adopting " energy consumption detection training sample off-line acquisition module " to obtain, after the structure completing multiple weighing value neuroid, obtain the multiple weighing value neuron areal coverage of " energy consumption is high ", " energy consumption is higher ", " energy consumption is medium ", " energy consumption is on the low side ", the different energy consumption rank of " energy consumption is low " five sign; Euclidean distance between the multiple weighing value neuroid areal coverage calculating sample to be identified and characterize every class energy consumption rank, by that class energy consumption rank the shortest with the Euclidean distance of sample to be identified, be used as the affiliated energy consumption rank of sample to be identified, and fan energy consumption grade classification is exported as multiple weighing value neural network.
The concrete grammar that during blower fan non-fault, training sample off-line obtains is:
By the time-domain signal that three 3-axis acceleration sensors during non-fault export, carry out denoising, and adopt hypercomplex number PCA to carry out pivot analysis, under the prerequisite of maintenance three axle output signal correlativity, obtain vibration performance vector during non-fault;
During fan rotor failure free operation, two eddy current sensor is adopted to extract orbit of shaft center, during non-fault, the time domain waveform of its vibration signal of eddy current sensor is sinusoidal curve, two orthogonal sinusoidal signals are synthesized, just circle or oval is obtained, extract the geometries characteristic of orbit of shaft center image or grey level histogram feature or textural characteristics as characteristic parameter, and the vibration performance obtained with acceleration transducer is vectorial combines, sample when obtaining non-fault; Adopt said method, repeatedly test, obtain sample time many groups " energy consumption is low ".
A kind of fan energy consumption monitoring system, it is characterized in that: comprise three and be placed in the 3-axis acceleration sensor on bearing seat shell, motor housing, ventilator housing and two orthogonal eddy current sensors in rotating shaft vertical plane respectively, 3-axis acceleration sensor, eddy current sensor are connected with signal transacting and characteristic extracting module, signal transacting and characteristic extracting module and the Classification and Identification model calling based on neural network.
The present invention proposes the fan energy consumption monitoring method based on vibration signal and orbit of shaft center signal analysis.The method does not need to install the structures such as air duct additional in the application, three 3-axis acceleration sensors are adopted to detect ventilation blower multiple spot three-dimensional vibrating signal (detecting the vibration signal of motor housing, bearing seat shell, ventilator housing), adopt the displacement that two eddy current sensors detection ventilation blower spindle eccentricities cause, and obtain orbit of shaft center.By on great many of experiments basis, obtain the dissimilar fault of blower fan and fan energy consumption increase between relation, and by multiple weighing value neural network, rank is increased to the energy consumption that different faults causes and carries out Classification and Identification.
Make a general survey of domestic existing fan energy consumption monitoring method and system, the design object that the present invention carries there is no unit and realizes.
The invention reside in and a kind of novel energy-consumption monitoring system is provided, only adopt 3-axis acceleration sensor, eddy current sensor, ONLINE RECOGNITION and monitoring that fan energy consumption increases degree can be realized, the cost avoiding existing energy consumption detection system is high, install the problems such as difficulty, be conducive to enterprise and realize the daily energy consumption monitoring of blower fan, thus be beneficial to enterprise's energy efficiency management, in time eliminate and change high-energy equipment, realize high-energy equipment trouble hunting targetedly.
Accompanying drawing explanation
Below in conjunction with drawings and Examples, the invention will be further described.
Fig. 1 is energy-consumption monitoring system structural drawing of the present invention.Wherein there are 3-axis acceleration sensor, eddy current sensor, energy consumption detection training sample off-line acquisition module, signal transacting and characteristic extracting module, Classification and Identification module based on neural network." signal transacting and characteristic extracting module ", by software simulating, comprises denoising, hypercomplex number PCA feature extraction, orbit of shaft center feature extraction (geometries characteristic, or grey level histogram feature, or textural characteristics)." the Classification and Identification module based on neural network " increases grade classification by multiple weighing value neural fusion energy consumption.
Fig. 2 is the off-line acquisition methods schematic diagram of train samples of the present invention.
The experimental technique schematic diagram that the train samples that Fig. 3 is obtains.
Fig. 4 is the schematic layout pattern of sensor.Two eddy current sensor center lines are all crossing with blower fan main shaft axial line, and two eddy current sensor center lines are all perpendicular to blower fan main shaft axial line, and two eddy current sensor center lines are mutually vertical.Three acceleration transducers are fixedly mounted on motor surface, bearing seat shell, ventilator housing respectively.
Fig. 5 is multiple weighing value neural network recognization process schematic.
Embodiment
A kind of fan energy consumption monitoring system, comprise three and be placed in the 3-axis acceleration sensor 1 on bearing seat shell, motor housing, ventilator housing and two orthogonal eddy current sensors 2 in rotating shaft vertical plane respectively, 3-axis acceleration sensor, eddy current sensor are connected with signal transacting and characteristic extracting module, signal transacting and characteristic extracting module and the Classification and Identification model calling based on neural network." signal transacting and characteristic extracting module ", " the Classification and Identification module based on neural network " all rely on the hardware facility such as PC or high performance controller (as FPGA etc.), by software simulating denoising, hypercomplex number PCA feature extraction, orbit of shaft center feature extraction, pattern-recognition based on multiple weighing value neural network.
1, first carry out off-line training sample collection, specific implementation process is:
This system is only for the off-line collection of train samples, and after having gathered, this system does not re-use in daily energy efficiency monitoring.
1.1 off-line training sample acquisition system build
According to GB/T 1236-2000 " industrial ventilation machine standardization air channel makes a service test " and GB-19761-2009 " ventilator energy efficiency limit value and efficiency grade " national standard, build energy consumption testing system, adopt the multiple sensors such as torque sensor, differential pressure pick-up, speed probe, detect compressor flow, total pressure of fan, static pressure of fan, volume flow, fan shaft power, finally can obtain fan efficiency, thus learn ventilation blower energy consumption size.
According to layout type shown in Fig. 4, adopt three 3-axis acceleration sensors, be placed on bearing seat shell, motor housing, ventilator housing respectively, obtain X, Y, Z tri-axle orthogonal vibration signal of three test points.By gathering vibration signal with the orthogonal eddy current sensor of two in rotating shaft vertical plane simultaneously, and respectively using the figure that gathered data fit to as horizontal, ordinate, be orbit of shaft center.
During 1.2 blower fan non-fault, training sample off-line obtains
GB/T 1236-2000 " industrial ventilation machine standardization air channel makes a service test " and GB-19761-2009 " ventilator energy efficiency limit value and efficiency grade " national standard method is adopted to carry out fan efficiency detection, obtain efficiency value during non-fault, this state energy consumption is defined as " energy consumption is low ".By the time-domain signal that three 3-axis acceleration sensors during non-fault export, carry out denoising, and adopt hypercomplex number PCA to carry out pivot analysis, under the prerequisite of maintenance three axle output signal correlativity, obtain vibration performance vector during non-fault.
During fan rotor failure free operation, two eddy current sensor is adopted to extract orbit of shaft center, during non-fault, the time domain waveform of its vibration signal of eddy current sensor is sinusoidal curve, two orthogonal sinusoidal signals are synthesized, just circle or oval is obtained, extract the geometries characteristic of orbit of shaft center image or grey level histogram feature or textural characteristics as characteristic parameter, and the vibration performance obtained with acceleration transducer is vectorial combines, sample when obtaining non-fault.Adopt said method, repeatedly test, obtain sample time many groups " energy consumption is low ".
When 1.3 blower fans have a fault, training sample off-line obtains
Artificially arrange various faults, as poor heat radiation, lubrication is not good, rotating shaft is eccentric, line voltage reduces or frequency shakiness (especially when new energies such as wind-powered electricity generations), wheel rotation imbalance, drive failure (as faults such as belt chain, gear, bearings), motor oil whip etc.When breaking down, vibration signal frequency domain can change.Orbit of shaft center there will be the situations such as bajiao banana figure, 8-shaped, inner ring figure, irregular component.The vibration signal characteristics of extraction and orbit of shaft center Feature Combination are got up, different faults or fault combination can be characterized.During off-line training sample acquisition, efficiency is carried out repeatedly respectively to the combination of often kind of fault, various faults and detects and feature extraction, obtain the many groups sample under the combined situation of often kind of fault, various faults.
To the combination of often kind of fault, various faults, adopt the method establishment fan efficiency detection system of 1.2 joints, the efficiency value when efficiency value in different faults situation and non-fault is compared, according to difference from big to small, be divided into Four types, be defined as " energy consumption is high ", " energy consumption is higher ", " energy consumption is medium ", " energy consumption is on the low side " respectively.
2, online energy consumption monitoring, concrete methods of realizing is:
During online energy consumption monitoring, 1.2 and 1.3 joints " energy consumption detection training sample off-line acquisition module " used do not re-use.Only adopt three 3-axis acceleration sensors, two eddy current sensors.Acceleration transducer and eddy current sensor are still installed according to method shown in Fig. 4.
Multiple degrees of freedom neural network in the training sample structure higher dimensional space adopting off-line in 1.2 and 1.3 to gather.After the structure completing multiple weighing value neuroid, " energy consumption is high ", " energy consumption is higher " can be obtained, " energy consumption is medium ", " energy consumption is on the low side ", " energy consumption are low " five multiple weighing value neuron areal coverage characterizing different energy consumption rank.When after fan operation, adopt the recognizer based on multiple weighing value neural network shown in Fig. 5, with the signal that 3-axis acceleration sensor and eddy current sensor gather, sample after feature extraction is as input, Euclidean distance between the multiple weighing value neuroid areal coverage calculating sample to be identified and characterize every class energy consumption rank, by that class energy consumption rank the shortest with the Euclidean distance of sample to be identified, be used as the affiliated energy consumption rank of sample to be identified.And fan energy consumption grade classification is exported as multiple weighing value neural network.
Claims (2)
1. the fan energy consumption monitoring system based on Fault Identification, it is characterized in that: comprise three and be placed in the 3-axis acceleration sensor on bearing seat shell, motor housing, ventilator housing and two orthogonal eddy current sensors in rotating shaft vertical plane respectively, 3-axis acceleration sensor, eddy current sensor are connected with signal transacting and characteristic extracting module, signal transacting and characteristic extracting module and the Classification and Identification model calling based on neural network;
Monitoring method comprises the following steps:
(1) first off-line training sample collection is carried out:
(1) off-line training sample acquisition system builds
Build energy consumption testing system, adopt the multiple sensors comprising torque sensor, differential pressure pick-up, speed probe, detect compressor flow, blower press, fan static pressure, volume flow, fan shaft power, final fan efficiency, thus learn fan energy consumption size;
Adopt three 3-axis acceleration sensors, be placed on bearing seat shell, motor housing, blower housing respectively, obtain X, Y, Z tri-axle orthogonal vibration signal of three test points; By gathering vibration signal with the orthogonal eddy current sensor of two in rotating shaft vertical plane simultaneously, and respectively using the figure that gathered data fit to as horizontal, ordinate, be orbit of shaft center;
(2) during blower fan non-fault, training sample off-line obtains
Adopt " signal transacting and characteristic extracting module " to carry out feature extraction, through repetitive measurement, obtain feature samples during many group non-fault; Efficiency value corresponding for feature samples during non-fault is orientated as " energy consumption is low ";
(3) when blower fan has a fault, training sample off-line obtains
The combination of artificial manufacture various faults and various faults, three 3-axis acceleration sensors are adopted to detect the three-dimensional vibrating signal of bearing fan shell, motor housing, blower housing 3, two eddy current sensor is adopted to detect axle center trajectory signal, " signal transacting and characteristic extracting module " is adopted to carry out feature extraction, each fault is taken multiple measurements, obtains the feature samples under each fault; The efficiency value when efficiency value in different faults situation and non-fault is compared, according to difference from big to small, is divided into Four types, be defined as " energy consumption is high ", " energy consumption is higher ", " energy consumption is medium ", " energy consumption is on the low side " respectively;
(2) online energy consumption monitoring
Three 3-axis acceleration sensors are adopted to detect the three-dimensional vibrating signal of bearing fan shell, motor housing, blower housing 3, two eddy current sensor is adopted to detect axle center trajectory signal, adopt " signal transacting and characteristic extracting module " to carry out feature extraction to signal, obtain tested sample; Adopt multiple weighing value neural network as the core algorithm of " the Classification and Identification module based on neural network ", multiple degrees of freedom neural network in the training sample structure higher dimensional space adopting " energy consumption detection training sample off-line acquisition module " to obtain, after the structure completing multiple weighing value neuroid, obtain the multiple weighing value neuron areal coverage of " energy consumption is high ", " energy consumption is higher ", " energy consumption is medium ", " energy consumption is on the low side ", the different energy consumption rank of " energy consumption is low " five sign; Euclidean distance between the multiple weighing value neuroid areal coverage calculating sample to be identified and characterize every class energy consumption rank, by that class energy consumption rank the shortest with the Euclidean distance of sample to be identified, be used as the affiliated energy consumption rank of sample to be identified, and fan energy consumption grade classification is exported as multiple weighing value neural network.
2. the fan energy consumption monitoring system based on Fault Identification according to claim 1, is characterized in that: the concrete grammar that during blower fan non-fault, training sample off-line obtains is:
By the time-domain signal that three 3-axis acceleration sensors during non-fault export, carry out denoising, and adopt hypercomplex number PCA to carry out pivot analysis, under the prerequisite of maintenance three axle output signal correlativity, obtain vibration performance vector during non-fault;
During fan rotor failure free operation, two eddy current sensor is adopted to extract orbit of shaft center, during non-fault, the time domain waveform of its vibration signal of eddy current sensor is sinusoidal curve, two orthogonal sinusoidal signals are synthesized, just circle or oval is obtained, extract the geometries characteristic of orbit of shaft center image or grey level histogram feature or textural characteristics as characteristic parameter, and the vibration performance obtained with acceleration transducer is vectorial combines, sample when obtaining non-fault; Adopt said method, repeatedly test, obtain sample time many groups " energy consumption is low ".
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510480936.3A CN105004462B (en) | 2014-06-11 | 2014-06-11 | Fan energy consumption monitoring system based on fault identification |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510480936.3A CN105004462B (en) | 2014-06-11 | 2014-06-11 | Fan energy consumption monitoring system based on fault identification |
| CN201410257423.1A CN104006908B (en) | 2014-06-11 | 2014-06-11 | fan energy consumption monitoring method and system |
Related Parent Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410257423.1A Division CN104006908B (en) | 2014-06-11 | 2014-06-11 | fan energy consumption monitoring method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105004462A true CN105004462A (en) | 2015-10-28 |
| CN105004462B CN105004462B (en) | 2017-07-04 |
Family
ID=51367671
Family Applications (3)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410257423.1A Active CN104006908B (en) | 2014-06-11 | 2014-06-11 | fan energy consumption monitoring method and system |
| CN201510480936.3A Active CN105004462B (en) | 2014-06-11 | 2014-06-11 | Fan energy consumption monitoring system based on fault identification |
| CN201510480910.9A Active CN105021334B (en) | 2014-06-11 | 2014-06-11 | Fan energy consumption monitoring recognition methods based on multiple weighing value neutral net |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410257423.1A Active CN104006908B (en) | 2014-06-11 | 2014-06-11 | fan energy consumption monitoring method and system |
Family Applications After (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510480910.9A Active CN105021334B (en) | 2014-06-11 | 2014-06-11 | Fan energy consumption monitoring recognition methods based on multiple weighing value neutral net |
Country Status (1)
| Country | Link |
|---|---|
| CN (3) | CN104006908B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106017802A (en) * | 2016-06-24 | 2016-10-12 | 南京南瑞继保电气有限公司 | Method for dynamically monitoring axis locus |
| CN106322686A (en) * | 2016-09-26 | 2017-01-11 | 中铁第四勘察设计院集团有限公司 | Anti-vibration anti-loosening ventilating system and ventilating method |
| CN107178514A (en) * | 2017-05-04 | 2017-09-19 | 山东大学 | Blower fan unit non-intrusion type efficiency diagnostic method and system |
| CN109614981A (en) * | 2018-10-17 | 2019-04-12 | 东北大学 | The Power System Intelligent fault detection method and system of convolutional neural networks based on Spearman rank correlation |
| CN110119789A (en) * | 2019-05-28 | 2019-08-13 | 湃方科技(北京)有限责任公司 | A kind of rotary-type mechanical equipment start and stop judgment method and system |
| CN112803369A (en) * | 2020-12-31 | 2021-05-14 | 南通威尔电机有限公司 | Intelligent operation method and device of efficient motor |
| US11486710B2 (en) * | 2020-04-06 | 2022-11-01 | The Boeing Company | System and method for determining a three-dimensional travel path for a vehicle |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105258892B (en) * | 2015-09-28 | 2018-12-11 | 沈阳鼓风机集团安装检修配件有限公司 | A kind of centrifugal compressor vibration fault detection method and device |
| CN106840282A (en) * | 2015-12-03 | 2017-06-13 | 李建锋 | Compressor flow and Efficiency test method based on gas temperature rise |
| CN106369834A (en) * | 2016-09-02 | 2017-02-01 | 南通大学 | Directly-heated type heat pump system constant-temperature flow control method based on neural network |
| CN108615018A (en) * | 2018-04-28 | 2018-10-02 | 宋浏阳 | Object state identification method based on the extraction of time domain histogram feature |
| CN109030998B (en) * | 2018-07-19 | 2023-01-20 | 浙江浙能常山天然气发电有限公司 | Intelligent transformer monitoring system based on triaxial vibration technology |
| CN110161330B (en) * | 2019-05-10 | 2021-06-11 | 广东石油化工学院 | Method and device for detecting vibration sound of transformer running state based on gray scale theory |
| CN117419646B (en) * | 2023-12-19 | 2024-03-15 | 南京牧镭激光科技股份有限公司 | Method and system for monitoring displacement of fan spindle based on laser sensor |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH09281179A (en) * | 1996-04-17 | 1997-10-31 | Shinko Electric Co Ltd | Method for sensing current of ac generator system and ac generator system controller using this method |
| CN102735968A (en) * | 2012-06-13 | 2012-10-17 | 江苏省电力公司南京供电公司 | GIS (Geographic Information System) fault diagnosis system and method based on vibration signal spectrum analysis |
| CN103743964A (en) * | 2013-10-28 | 2014-04-23 | 无锡优电科技有限公司 | Electric energy quality real-time monitoring device and method of monitoring electric energy data |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5050092A (en) * | 1990-02-26 | 1991-09-17 | Perry Robert E | Fan efficiency measuring apparatus |
| CA2123619A1 (en) * | 1994-05-16 | 1995-11-17 | Cameron Sterling | Apparatus for demonstrating relative drive efficiency |
| JP4031986B2 (en) * | 2000-11-22 | 2008-01-09 | アーファウエル リスト ゲゼルシャフト ミット ベシュレンクテル ハフツング | Method for supplying conditioned combustion gas to an internal combustion engine, apparatus for carrying out the method, method for measuring the amount of harmful substances in the exhaust gas of an internal combustion engine, and apparatus for carrying out the method |
| EP2204712A1 (en) * | 2008-12-17 | 2010-07-07 | Bayer MaterialScience AG | Method and system for monitoring and analysing energy consumption in operated chemical plants |
| RU2496100C1 (en) * | 2012-03-12 | 2013-10-20 | Федеральное государственное бюджетное образовательное учреждение высшего профессионального образования "Брянский государственный технический университет" | Bench for simulation of dynamic processes in traction drive locomotive with power transmission |
| CN203441798U (en) * | 2013-07-24 | 2014-02-19 | 国家电网公司 | Fan efficiency on-line measuring device based on wireless communication |
-
2014
- 2014-06-11 CN CN201410257423.1A patent/CN104006908B/en active Active
- 2014-06-11 CN CN201510480936.3A patent/CN105004462B/en active Active
- 2014-06-11 CN CN201510480910.9A patent/CN105021334B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH09281179A (en) * | 1996-04-17 | 1997-10-31 | Shinko Electric Co Ltd | Method for sensing current of ac generator system and ac generator system controller using this method |
| CN102735968A (en) * | 2012-06-13 | 2012-10-17 | 江苏省电力公司南京供电公司 | GIS (Geographic Information System) fault diagnosis system and method based on vibration signal spectrum analysis |
| CN103743964A (en) * | 2013-10-28 | 2014-04-23 | 无锡优电科技有限公司 | Electric energy quality real-time monitoring device and method of monitoring electric energy data |
Non-Patent Citations (1)
| Title |
|---|
| 羌予践: "基于虚拟仪器的风电机组状态监测与故障诊断平台设计", 《2010电工测试技术学术交流会论文集》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106017802A (en) * | 2016-06-24 | 2016-10-12 | 南京南瑞继保电气有限公司 | Method for dynamically monitoring axis locus |
| CN106322686A (en) * | 2016-09-26 | 2017-01-11 | 中铁第四勘察设计院集团有限公司 | Anti-vibration anti-loosening ventilating system and ventilating method |
| CN107178514A (en) * | 2017-05-04 | 2017-09-19 | 山东大学 | Blower fan unit non-intrusion type efficiency diagnostic method and system |
| CN107178514B (en) * | 2017-05-04 | 2019-08-20 | 山东大学 | Blower unit non-intrusion type efficiency diagnostic method and system |
| CN109614981A (en) * | 2018-10-17 | 2019-04-12 | 东北大学 | The Power System Intelligent fault detection method and system of convolutional neural networks based on Spearman rank correlation |
| CN110119789A (en) * | 2019-05-28 | 2019-08-13 | 湃方科技(北京)有限责任公司 | A kind of rotary-type mechanical equipment start and stop judgment method and system |
| US11486710B2 (en) * | 2020-04-06 | 2022-11-01 | The Boeing Company | System and method for determining a three-dimensional travel path for a vehicle |
| CN112803369A (en) * | 2020-12-31 | 2021-05-14 | 南通威尔电机有限公司 | Intelligent operation method and device of efficient motor |
| CN112803369B (en) * | 2020-12-31 | 2021-11-05 | 南通威尔电机有限公司 | Intelligent operation method and device of efficient motor |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105021334A (en) | 2015-11-04 |
| CN104006908A (en) | 2014-08-27 |
| CN105021334B (en) | 2017-07-18 |
| CN104006908B (en) | 2015-12-02 |
| CN105004462B (en) | 2017-07-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104006908B (en) | fan energy consumption monitoring method and system | |
| CN101871844B (en) | Performance analysis and fault simulation experiment system of wind machine | |
| CN101592590B (en) | Fault indirect diagnosis technique of rotating blade | |
| CN103940611B (en) | Rolling bearing self adaptation method for detecting abnormality under a kind of Wind turbines variable working condition | |
| CN104792526B (en) | Wind turbine gearbox dynamic response Multi-parameter detection device | |
| CN109488630B (en) | Centrifugal fan rotor misalignment fault diagnosis method based on harmonic relative index | |
| CN101672723A (en) | Method and system for analyzing vibration and diagnosing failure for wind generating set | |
| CN107144303A (en) | A kind of fault detection system of mineral electromechanical equipment, method and device | |
| CN102798529A (en) | Method and system for diagnosing bearing faults of large-size wind turbine bearing | |
| CN108981796B (en) | Five-in-one hydraulic mechanical fault diagnosis method | |
| CN202547923U (en) | Vibration detecting device for pitch-variable bearing of wind turbine generator system | |
| CN204831532U (en) | Wind generating set pylon mode test system | |
| CN104048595A (en) | Angle misalignment fault quantitative detection system and method for rotating machine | |
| CN102589881A (en) | Intelligent detection system of special metallurgical vehicle wheel set bearings | |
| CN111474477B (en) | Method for acquiring partial time domain parameters and frequency domain parameters in motor fault diagnosis | |
| CN103925155A (en) | Self-adaptive detection method for abnormal wind turbine output power | |
| CN106762343A (en) | The diagnostic method of the hydraulic generator set thrust bearing failure based on online data | |
| CN108592812B (en) | Method for extracting load strain characteristics and monitoring cracks of optical fiber of fan blade | |
| Amano et al. | Aerodynamics of wind turbines: emerging topics | |
| CN202453182U (en) | Fault diagnosis device of gearbox of wind generation set | |
| CN109580231A (en) | A kind of pressure shell rotation failure test method of identification diesel engine matching turbocharger | |
| CN206369617U (en) | A kind of pneumatic equipment bladess damage active self-checking unit | |
| CN116465627A (en) | Mechanical equipment fault monitoring system | |
| CN103344321B (en) | Based on detection method and the device of the rotary body radial direction drift of electrostatic sensor array | |
| CN114508490B (en) | Intelligent split centrifugal pump, network fault point positioning method applied to intelligent split centrifugal pump and readable storage module |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20151028 Assignee: Jiangsu Yuanzhong Motor Co., Ltd. Assignor: Nantong University Contract record no.: 2019320000087 Denomination of invention: Fault-identification-based fan energy consumption monitoring system Granted publication date: 20170704 License type: Exclusive License Record date: 20190327 |
|
| EE01 | Entry into force of recordation of patent licensing contract |