CN114152433A - Rotor failure detection system and rotary machine - Google Patents
Rotor failure detection system and rotary machine Download PDFInfo
- Publication number
- CN114152433A CN114152433A CN202111626797.2A CN202111626797A CN114152433A CN 114152433 A CN114152433 A CN 114152433A CN 202111626797 A CN202111626797 A CN 202111626797A CN 114152433 A CN114152433 A CN 114152433A
- Authority
- CN
- China
- Prior art keywords
- rotor
- fault detection
- strain
- signal
- fault
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 125
- 238000004364 calculation method Methods 0.000 claims abstract description 19
- 230000001133 acceleration Effects 0.000 claims description 19
- 238000013527 convolutional neural network Methods 0.000 claims description 17
- 238000004804 winding Methods 0.000 claims description 4
- 238000000034 method Methods 0.000 abstract description 20
- 238000012544 monitoring process Methods 0.000 abstract description 5
- 238000011065 in-situ storage Methods 0.000 abstract description 3
- 230000005540 biological transmission Effects 0.000 description 14
- 238000011176 pooling Methods 0.000 description 12
- 230000008569 process Effects 0.000 description 10
- 230000006870 function Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 7
- 238000012549 training Methods 0.000 description 7
- 239000011888 foil Substances 0.000 description 6
- 238000002955 isolation Methods 0.000 description 4
- 239000000463 material Substances 0.000 description 4
- 239000000758 substrate Substances 0.000 description 4
- 238000001914 filtration Methods 0.000 description 3
- 230000006698 induction Effects 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 239000002184 metal Substances 0.000 description 3
- 229910052751 metal Inorganic materials 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 2
- 239000003795 chemical substances by application Substances 0.000 description 2
- 229910052802 copper Inorganic materials 0.000 description 2
- 239000010949 copper Substances 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 229910000831 Steel Inorganic materials 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
- G01M13/02—Gearings; Transmission mechanisms
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The present application relates to a rotor fault detection system and a rotary machine, wherein, the rotor fault detection system includes a wireless power supply unit, a detection circuit and a calculation unit, wherein: the wireless power supply unit is used for supplying power to the detection circuit; the detection circuit is fixed on the rotor and used for acquiring working condition signals of the rotor when the rotor rotates and sending the working condition signals to the calculation unit in a wireless mode; and the calculating unit is used for judging whether the rotor has faults or not according to the working condition signals. Through the method and the device, the technical problem that the accuracy of rotor fault detection is not high in the prior art is solved, in-situ monitoring of the rotor is achieved, and the precision of rotor fault detection is improved.
Description
Technical Field
The present application relates to the field of rotary machines, and more particularly, to a rotor fault detection system and a rotary machine.
Background
With the continuous development of industrialization, rotary machines become more and more important in the production fields of chemical industry, electric power, steel and the like. The rotary machine generally comprises basic components such as a rotor, a bearing, a coil and the like, wherein the rotor is used as an important part of the rotary machine and is easily damaged on the surface and the structure when being in a high-speed rotation and cross-load operation environment for a long time, and further great potential safety hazard is brought to the rotary machine.
In order to reduce the potential safety hazard brought by the rotor, the working condition of the rotor is generally detected by a sensor in the prior art, the sensor is installed on bearing blocks at two ends of a rotor system, and vibration signals of the bearing blocks are collected and processed and analyzed so as to judge the working condition of the rotor. However, the rotor is often in a high-speed rotation state, the working condition signal of the rotor itself cannot be directly collected in the prior art, only the signal on the fixed bearing seat can be obtained, and the accuracy of rotor fault detection is not high due to signal attenuation of the rotor in the process of transmitting the signal to the bearing seat.
Aiming at the technical problem that the accuracy of rotor fault detection is not high in the related technology, no effective solution is provided at present.
Disclosure of Invention
In the present embodiment, a rotor fault detection system and a rotary machine are provided to solve the problem of low accuracy of rotor fault detection in the related art.
In a first aspect, in the present embodiment, there is provided a rotor fault detection system applied to a rotary machine, the rotor fault detection system including a wireless power supply unit, a detection circuit, and a calculation unit, wherein:
the wireless power supply unit is used for supplying power to the detection circuit;
the detection circuit is fixed on the rotor and used for acquiring working condition signals of the rotor when the rotor rotates and sending the working condition signals to the calculation unit in a wireless mode;
and the calculating unit is used for judging whether the rotor has faults or not according to the working condition signals.
In some of these embodiments, the detection circuit comprises a coil, a strain gage, and a carrier circuit, wherein:
the coil is used for acquiring the electric energy of the wireless power supply unit so as to supply power to the detection circuit;
the strain gauge is connected with the rotor and used for acquiring a strain signal of the rotor when the rotor rotates and sending the strain signal to the carrier circuit;
the carrier circuit is used for receiving the strain signal and sending the strain signal to the computing unit in a wireless mode, so that the computing unit can judge whether the rotor has faults or not according to the strain signal.
In some of these embodiments, the strain gauge is connected to a rotor shaft for acquiring a first strain signal on the rotor shaft when the rotor is rotating, and/or connected to a blade root of the rotor for acquiring a second strain signal on the blade root when the rotor is rotating, the blade being connected to the rotor shaft for increasing an air intake of the rotary machine.
In some of these embodiments, the detection circuit includes two strain gauges, one of which is parallel to the direction of the rotation axis, and the other of which is perpendicular to the direction of the rotation axis.
In some of these embodiments, the carrier circuit is a flex circuit and is disposed along a tooling inner wall surface of the rotor.
In some of these embodiments, the rotor fault detection system further comprises an acceleration sensor connected to a bearing housing of the rotor, wherein:
the acceleration sensor is used for collecting vibration signals on the bearing seat when the rotor rotates and sending the vibration signals to the computing unit;
and the calculating unit is used for judging whether the rotor has a fault or not according to the vibration signal.
In some embodiments, the calculation unit is further configured to input the operating condition signal to a rotor fault detection model to determine whether a fault exists in the rotor, where the rotor fault detection model includes a trained convolutional neural network.
In some embodiments, the calculation unit is further configured to train the convolutional neural network according to the fault sample data and the corresponding fault result, so as to obtain the rotor fault detection model.
In a second aspect, a rotary machine is provided in the present embodiment, where the rotary machine includes a rotating shaft, a wheel disc, a tool, and the rotor fault detection system of any one of the first aspect, where:
the rotating shaft is used for supporting the rotor to rotate and transmitting torque;
the wheel disc is fixed on the rotating shaft, connected with the tool through a bolt and used for fixing the tool;
the tool is used for winding a coil and fixing the detection circuit;
and the rotor fault detection system is used for acquiring working condition signals of the rotor when the rotor rotates and analyzing the working condition signals so as to judge whether the rotor has faults or not.
In some embodiments, the coil of the rotor is wound outside the tool, the carrier circuit is fixed on the inner wall of the tool, the tool is provided with a threading hole, and a lead is led into the threading hole so as to connect the coil with the carrier circuit.
Compared with the related art, the rotor fault detection system and the rotary machine provided in the present embodiment include a wireless power supply unit, a detection circuit, and a calculation unit, wherein: the wireless power supply unit is used for supplying power to the detection circuit; the detection circuit is fixed on the rotor and used for acquiring working condition signals of the rotor when the rotor rotates and sending the working condition signals to the calculation unit in a wireless mode; and the calculating unit is used for judging whether the rotor has faults or not according to the working condition signals. The working condition signal of the rotor is directly collected by the detection circuit arranged on the rotor, the detection circuit is powered in a wireless power supply mode, the working condition signal is transmitted in a wireless mode, the condition signal which is transmitted by the rotor and can only be acquired through fixed structures such as a bearing seat in the prior art is avoided, the technical problem that the accuracy of rotor fault detection in the prior art is not high is solved, in-situ monitoring of the rotor is realized, and the precision of rotor fault detection is improved.
The details of one or more embodiments of the application are set forth in the accompanying drawings and the description below to provide a more thorough understanding of the application.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
FIG. 1 is a block diagram of a rotor fault detection system in accordance with an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a convolutional neural network according to an embodiment of the present invention;
FIG. 3 is a comparison of rotor fault detection results for one embodiment of the present invention;
FIG. 4 is a schematic diagram of a rotary machine according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a tooling structure according to an embodiment of the present invention;
fig. 6 is a schematic view of a wheel disc structure according to an embodiment of the present invention.
Detailed Description
For a clearer understanding of the objects, aspects and advantages of the present application, reference is made to the following description and accompanying drawings.
Unless defined otherwise, technical or scientific terms used herein shall have the same general meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The use of the terms "a" and "an" and "the" and similar referents in the context of this application do not denote a limitation of quantity, either in the singular or the plural. The terms "comprises," "comprising," "has," "having," and any variations thereof, as referred to in this application, are intended to cover non-exclusive inclusions; for example, a process, method, and system, article, or apparatus that comprises a list of steps or modules (elements) is not limited to the listed steps or modules, but may include other steps or modules (elements) not listed or inherent to such process, method, article, or apparatus. Reference throughout this application to "connected," "coupled," and the like is not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. Reference to "a plurality" in this application means two or more. "and/or" describes an association relationship of associated objects, meaning that three relationships may exist, for example, "A and/or B" may mean: a exists alone, A and B exist simultaneously, and B exists alone. In general, the character "/" indicates a relationship in which the objects associated before and after are an "or". The terms "first," "second," "third," and the like in this application are used for distinguishing between similar items and not necessarily for describing a particular sequential or chronological order.
The rotary machine is a key device in the industrial manufacturing field, and is widely applied to devices such as motors, gear boxes, water pumps, engines and the like. The rotating machine consists of a rotor, a bearing, a coil and other parts and is used for realizing the conversion of energy such as electric energy, kinetic energy and the like. The rotor is the most important component of a rotating machine and needs to be monitored in operation.
In the prior art, the operating condition of the rotor is generally monitored by a simple instrument, and maintenance is performed in time when a fault is found. However, this method requires manual experience, and has low accuracy of diagnosis results and high monitoring cost. On the other hand, in the prior art, the working condition of the rotor is automatically detected through devices such as a sensor. However, the rotor is often in a high-speed rotation state, the working condition signal of the rotor itself cannot be directly collected in the prior art, and only the signal on a fixed structure such as a bearing seat can be obtained. Therefore, the invention aims to solve the key problem of monitoring the working condition of the rotor in real time at the position where the rotor fault is easy to occur.
To solve the above problems, the present invention provides a rotor failure detection system and a rotary machine for realizing the following embodiments and preferred embodiments. The terms "module," "unit," "subunit," and the like as used below may implement a combination of software and/or hardware for a predetermined function. Although the means described in the embodiments below are preferably implemented in hardware, an implementation in software, or a combination of software and hardware is also possible and contemplated.
Referring to fig. 1, fig. 1 is a block diagram of a rotor fault detection system according to an embodiment of the present invention. In the present embodiment, the rotor failure detection system is applied to a rotary machine, and includes a wireless power supply unit 10, a detection circuit 20, and a calculation unit 30, wherein: a wireless power supply unit 10 for supplying power to the detection circuit; the detection circuit 20 is fixed to the rotor and used for acquiring working condition signals of the rotor when the rotor rotates and sending the working condition signals to the calculation unit 30 in a wireless mode; and the calculating unit 30 is used for judging whether the rotor has a fault according to the working condition signal.
Illustratively, the rotor failure detection system includes a wireless power supply unit 10, a detection circuit 20, and a calculation unit 30, which are connected in sequence. Wherein, the detection circuit 20 is fixed on the rotor and rotates along with the rotor when the rotating machine runs; the wireless power supply unit 10 and the computing unit 30 are external devices of the rotor, and establish a connection relationship with the detection circuit 20 through a wireless transmission channel, so as to solve the problem that the wire is wound around the rotor when the rotating machine operates due to a wired transmission mode.
Illustratively, the wireless power supply unit 10 is configured to transmit power to the detection circuit by wireless transmission to supply power to the detection circuit. Specifically, the wireless power supply unit 10 is a transmitting terminal of the wireless charging device, and a receiving terminal of the wireless charging device is disposed on the detection circuit 20, and is configured to receive electric energy of the transmitting terminal and serve as a power source of the detection circuit 20.
Illustratively, the detection circuit 20 is in direct contact with the rotor, so as to directly acquire the operating condition signal of the rotor when the rotor rotates, and send the operating condition signal to the computing unit 30 by means of wireless transmission. Specifically, the operating condition signal of the rotor includes, but is not limited to, a strain signal, an acceleration signal, a temperature signal, and the like, so that various operating conditions of the rotor can be detected.
Illustratively, the calculating unit 30 is configured to receive the operating condition signal collected by the detecting circuit, and analyze and process the operating condition signal to determine whether an operation fault exists in the rotor. The computing unit 30 is an electronic device with an operation function, and includes, but is not limited to, a server, a computer terminal, a single chip, and an industrial personal computer.
Rotor fault detection system includes wireless power supply unit, detection circuitry and computational element among the embodiment, wherein: the wireless power supply unit is used for supplying power to the detection circuit; the detection circuit is fixed on the rotor and used for acquiring working condition signals of the rotor when the rotor rotates and sending the working condition signals to the calculation unit in a wireless mode; and the calculating unit is used for judging whether the rotor has faults or not according to the working condition signals. The working condition signal of the rotor is directly collected by the detection circuit arranged on the rotor, the detection circuit is powered in a wireless power supply mode, the working condition signal is transmitted in a wireless mode, the condition signal which is transmitted by the rotor and can only be acquired through fixed structures such as a bearing seat in the prior art is avoided, the technical problem that the accuracy of rotor fault detection in the prior art is not high is solved, in-situ monitoring of the rotor is realized, and the precision of rotor fault detection is improved.
In another embodiment, the detection circuit includes a coil, a strain gage, and a carrier circuit, wherein: the coil is used for acquiring the electric energy of the wireless power supply unit so as to supply power to the detection circuit; the strain gauge is connected with the rotor and used for acquiring a strain signal of the rotor when the rotor rotates and sending the strain signal to the carrier circuit; and the carrier circuit is used for receiving the strain signal and sending the strain signal to the computing unit in a wireless mode so that the computing unit can judge whether the rotor has faults or not according to the strain signal.
Illustratively, the detection circuit is composed of a coil, a strain gauge and a carrier circuit to realize functions of wireless charging, signal acquisition and wireless signal transmission.
Illustratively, the coil cuts a magnetic induction line generated by the wireless power supply unit when the rotor rotates, thereby generating an induction current and supplying power to the detection circuit. Specifically, the coil is generally made of copper metal and is wound on a fixture of the rotor.
Illustratively, the strain gauge is in direct contact with the rotor, gathers the strain signal of rotor when the rotor rotates, and transmits to the carrier circuit through wireless mode. Specifically, the strain gauge is an element for measuring strain, which is composed of a sensitive grid and the like, and is deformed under the action of an external force, and electrical parameters such as a resistance value and the like of the strain gauge are changed based on the deformation. Based on the characteristics of the strain gauge, it can be used to generate a strain signal according to the stress of the rotor when the rotor rotates. The strain signal contains information such as variance, frequency, amplitude and form factor of strain gauge resistance change, and can be used for analyzing the strain signal to obtain the stress condition of the strain gauge, and further judging whether the rotor has a fault.
Specifically, in the prior art, an acceleration sensor is generally used to obtain a vibration signal when the rotor rotates, but the acceleration sensor has a large volume and can only be fixed to a fixed structure such as a bearing seat and cannot be fixed to the rotor rotating at a high speed. While rotor faults generally occur in rotating parts such as blades, and the attenuation of vibration signals of the rotor acquired by a fixed structure is serious. Although the vibration signals can be processed by a filtering algorithm, the filtered vibration signals are often distorted and cannot achieve the accuracy when the rotor vibration signals are directly acquired. The strain gauge adopted in the embodiment has the characteristics of small volume and light weight, can be directly fixed on the rotor and rotate together with the rotor, directly acquires the strain signal of the rotor when the rotor rotates, and avoids the loss of the signal in the transmission process.
Illustratively, the carrier circuit receives the strain signal transmitted by the strain gauge and transmits the strain signal to the computing unit in a wireless transmission mode. Specifically, the carrier circuit is a circuit that transmits an analog signal or a digital signal by using a carrier method, and the transmission method may be a wired method or a wireless method.
Specifically, in the prior art, signals are generally transmitted through wireless transmission modules such as a Wi-Fi module and a bluetooth module, but the wireless transmission modules are often large in size and cannot be fixed to the rotor. And when the rotating speed of the rotor is high, the structural characteristics of the Wi-Fi module and the Bluetooth module can cause serious packet loss of transmitted data or abnormal work.
The detection circuit in this embodiment includes a coil, a strain gauge and a carrier circuit, wherein: the coil is used for acquiring the electric energy of the wireless power supply unit so as to supply power to the detection circuit; the strain gauge is connected with the rotor and used for acquiring a strain signal of the rotor when the rotor rotates and sending the strain signal to the carrier circuit; and the carrier circuit is used for receiving the strain signal and sending the strain signal to the computing unit in a wireless mode so that the computing unit can judge whether the rotor has faults or not according to the strain signal. Realize detection circuitry's power supply and information transmission through wireless mode to direct and rotor contact through the foil gage, make detection circuitry can directly gather the signal of meeting an emergency of rotor, avoided the loss of signal of meeting an emergency in the transmission course, improved the accuracy that rotor fault detected.
In another embodiment, the strain gauge is connected with a rotating shaft of the rotor for acquiring a first strain signal on the rotating shaft when the rotor rotates, and/or is connected with a blade root of the rotor for acquiring a second strain signal of the blade root when the rotor rotates, and the blade is connected with the rotating shaft for increasing the air intake of the rotating machine.
Illustratively, the strain gauge is fixed with a rotating shaft of the rotor, and a first strain signal of the position of the rotating shaft is acquired when the rotor rotates. Specifically, a first strain signal acquired by a strain gauge fixed on the rotating shaft can be used for judging whether faults such as unbalance, eccentricity and friction exist in the rotor during rotation. It can be understood that, because the rotating shaft is located at the center of the rotation of the rotor, the first strain signal collected on the rotating shaft is most sensitive to the faults of unbalance, eccentricity, friction and the like of the rotor, and whether the faults exist in the rotor can be more accurately identified based on the first strain signal.
Illustratively, the rotary machine is further provided with a blade, and the blade is fixed on a rotating shaft of the rotor and used for increasing the air intake of the rotary machine when the rotor rotates. The strain gauge is fixed on the root of the blade and used for acquiring a second strain signal of the root of the blade when the rotor rotates. Specifically, since the blade root is subjected to a large stress during rotation of the rotor, and cracks or fractures may occur, it is necessary to provide a strain gauge at the blade root. It can be understood that the blade root is closest to the occurrence part of the fault such as the crack or the fracture of the blade, so that the second strain signal acquired at the blade root is most sensitive to the fault, and the blade fault of the rotor in the rotating process can be more accurately identified based on the second strain signal.
Specifically, the above-mentioned strain signal collecting portion is only a preferred embodiment, and the collecting portion of the strain signal in the present invention may be set based on the type and occurrence position of the rotor fault. The characteristics of the acquired strain signals are different under different fault types and acquisition parts. It can be understood that in this embodiment, the strain signal of the rotating shaft that can be collected at the root of the blade, and the strain signal of the root of the blade that can also be collected at the rotating shaft, but the strain signal often has attenuation in the process of being transmitted to the rotating shaft or the root of the blade, so the best collection position of the strain signal needs to be selected according to the type of the fault and the occurrence position.
The foil gage is connected with the pivot of rotor in this embodiment for gather the epaxial first strain signal of commentaries on classics when the rotor rotates, and/or be connected with the blade root of rotor, be used for gathering the second strain signal of blade root when the rotor rotates, the blade is connected with the pivot, is used for increasing rotary machine's air input. Through gathering first strain signal in pivot department to directly monitor the trouble of rotor rotation in-process, and through gathering the second strain signal at the blade root, detect with the trouble of direct rotation in-process blade, avoided strain signal's loss in transmission process, improved strain signal's quality, and then improved rotor fault detection's accuracy.
In another embodiment, the detection circuit comprises two strain gauges, wherein one strain gauge is parallel to the direction of the rotating shaft, and the other strain gauge is perpendicular to the direction of the rotating shaft.
Illustratively, the detection circuit includes two foil gauges, and two foil gauges vertical setting, one of them is on a parallel with the pivot, and another perpendicular to pivot is fixed in the rotor through foil gauge adhesion water agent. Specifically, when the rotor rotates, centrifugal force is generated, the stress direction of the strain gauge perpendicular to the direction of the rotating shaft is in the direction of the centrifugal force, the grid direction of the strain gauge is the same as the direction of the centrifugal force, at the moment, the strain signal is most sensitive to the centrifugal force, and the amplitude of the signal is the largest. The grid direction of the strain gauge parallel to the rotating shaft is tangent to the direction of the centrifugal force, the grid expands to a certain degree after being influenced by the centrifugal force, and the acquired strain signal can be used as a reference.
It can be understood that the rotor fault can be more conveniently analyzed based on the strain signal perpendicular to the rotating shaft direction and the strain signal parallel to the rotating shaft direction. When only one strain gauge is arranged in the detection circuit and an included angle is formed between the direction of the strain gauge and the direction of the rotating shaft, the acquired strain signals simultaneously contain strain signal components in the vertical direction and strain signal components in the parallel direction, and the strain signals in the two directions need to be distinguished, so that the complexity of the system is increased.
For example, the present embodiment is merely a preferred embodiment, and the strain gauges in the present invention are not limited to the number and the position layout of the strain gauges in the present embodiment. In most cases, because the force of the rotor is not analyzed in advance, strain gauges in multiple directions need to be arranged to judge the direction of the force applied to the rotor, so that the fault analysis and maintenance of the rotor are performed.
The detection circuit in the embodiment comprises two strain gauges, wherein one strain gauge is parallel to the rotating shaft direction, and the other strain gauge is perpendicular to the rotating shaft direction. Based on the strain signals in the directions vertical to the rotating shaft and the strain signals parallel to the rotating shaft, the rotor fault is more conveniently analyzed, and the calculation cost of the rotor fault detection system is reduced.
In another embodiment, the carrier circuit is a flexible circuit and is disposed along a tooling inner wall surface of the rotor.
Illustratively, the carrier circuit may be a flexible circuit, so that the layout shape of the carrier circuit can be set according to an actual scene. Specifically, the carrier circuit has a flexible substrate, and the flexible substrate is laid along the frock inner wall surface of rotor, is equipped with carrier circuit's electronic components on the flexible substrate to make carrier circuit can laminate the frock inner wall of rotor completely.
The carrier circuit in this embodiment is a flexible circuit and is disposed along the tool inner wall surface of the rotor. It can be understood that the hard substrate circuit cannot be attached to the inner wall of the rotor due to its fixed shape, and thus is likely to cause a failure such as collision or falling off when the rotor rotates at a high speed. And based on flexible carrier circuit, can laminate the frock inner wall of rotor completely with the circuit, reduced the potential safety hazard of rotor.
In another embodiment, the rotor fault detection system further comprises an acceleration sensor connected to a bearing housing of the rotor, wherein: the acceleration sensor is used for collecting vibration signals on the bearing seat when the rotor rotates and sending the vibration signals to the computing unit; and the calculating unit is used for judging whether the rotor has a fault or not according to the vibration signal.
The rotor fault detection system is further provided with an acceleration sensor, the acceleration sensor is arranged on a bearing seat of the rotor and connected with the computing unit, and the acceleration sensor is used for collecting vibration signals transmitted to the bearing seat by the rotor when the rotor rotates and sending the vibration signals to the computing unit through a connecting channel. And after receiving the vibration signal, the computing unit analyzes the vibration signal to judge whether the rotor has a fault in the operation process. The acceleration sensor is a sensor for measuring acceleration signals, comprises a mass block, a damper, an elastic element, a sensitive element, an adjusting circuit and the like, and comprises a capacitance sensor, an inductance sensor, a strain sensor, a piezoelectric sensor and the like.
It is understood that the position of the acceleration sensor in the present embodiment is merely an example, and the acceleration sensor in the present invention may be disposed on other fixed structures besides the bearing seat. However, since the bearing seat is in direct contact with the rotor, the loss of the vibration signal of the rotor collected on the bearing seat in the transmission process is small, and the collected vibration signal is closer to the vibration signal directly collected on the rotor itself, which can be taken as a preferred embodiment.
Optionally, after receiving the vibration signal, the computing unit performs filtering processing on the vibration signal to filter noise interference, so as to reduce the influence of signal attenuation in the transmission process on the vibration signal and improve the quality of the vibration signal.
In the embodiment, the vibration signal acquired on the bearing seat has loss on the signal, so that the final fault detection precision is lower than that of the scheme of directly acquiring the strain signal at the rotor. However, the solution of providing the acceleration sensor on the fixed structure such as the bearing seat is lower in cost, and can be used as a supplement solution. And the computing unit can be combined with the strain signal and the vibration signal to analyze the running state of the rotor, so that the accuracy of rotor fault detection is improved.
In another embodiment, the calculation unit is further configured to input the operating condition signal into a rotor fault detection model to determine whether a fault exists in the rotor, where the rotor fault detection model includes a trained convolutional neural network.
Illustratively, the calculation unit inputs the working condition signals into the trained convolutional neural network, and the working condition signals are subjected to feature extraction and classification through the convolutional neural network, so as to finally judge whether the rotor has faults.
Specifically, the convolutional neural network comprises at least two convolutional layers, two pooling layers and an output layer. The convolutional layer is used for carrying out convolution operation, local features input by the convolutional layer are extracted every time convolution operation is carried out, and finally all partial features are summarized to obtain global features; the pooling layer is used for carrying out down-sampling, and the data volume is compressed by carrying out characteristic dimension reduction on the input of the pooling layer, so that the overfitting is reduced, and the pooling layer mainly comprises an average pooling layer and a maximum pooling layer; and the output layer is a full connection layer and is used for outputting a final detection result.
Referring to fig. 2, fig. 2 is a schematic flow chart of a convolutional neural network according to an embodiment of the present invention. In one specific embodiment, the convolutional neural network further comprises a Relu layer and a Softmax layer. The Relu layer is arranged between the convolution layer and the pooling layer and used for carrying out nonlinear mapping on an output result of the convolution layer through a Relu function and filtering characteristic data with low correlation degree, so that the dependency relationship among parameters is reduced, the over-fitting problem is alleviated, the computation speed of back propagation is improved, and the iteration speed of the Relu function is higher compared with other excitation functions such as Sigmoid and ELU; the Softmax layer is arranged in front of the output layer and is used for carrying out normalization operation through a Softmax function, the input of the Softmax layer is mapped between 0 and 1, and the mapping result can be used as the probability of each category in the classification result. Preferably, the pooling layer in this embodiment is a maximum pooling layer, and the output layer includes a first full-link layer and a second full-link layer, so as to perform pooling operation through the maximum value of the local region and map the features to vectors of preset dimensions, thereby improving the detection effect.
In one embodiment, the initial network parameters of the convolutional neural network are set as follows: the convolution kernel parameter is set to 5, the first convolution layer parameter is set to 64, the second convolution layer parameter is set to 32, the first pooling layer parameter is set to 4, the second pooling layer parameter is set to 2, the activation function is set to the Relu function, the convolution step is set to 1, Dropout is set to 0.4, the learning rate is set to 0.0001, and the optimizer is set to Adam.
In this embodiment, the calculation unit is further configured to input the operating condition signal into a rotor fault detection model to determine whether the rotor has a fault, where the rotor fault detection model includes a trained convolutional neural network. The trained convolutional neural network is used for analyzing and judging the working condition signals, the characteristic expression mode of the working condition signals does not need to be designed manually, the dependence of a detection system on human experience is reduced, and the accuracy of detection results is improved.
In another embodiment, the calculation unit is further configured to train the convolutional neural network according to the fault sample data and the corresponding fault result, so as to obtain a rotor fault detection model.
Illustratively, fault data of the rotor in the operation process are collected, and fault sample data and a mapping relation between the fault sample data and a fault result are established to obtain a training set. And pre-training the convolutional neural network through a training set, so as to optimize parameters in the network and obtain a rotor fault detection model. In the detection process, working condition signals of the rotor are directly input to the rotor fault detection model, and then a rotor fault detection result is obtained.
In one specific embodiment, fault data of the rotor under 5 working conditions are acquired, and a training set is established, wherein the training set comprises an unbalance fault data 75 group at 507rpm, an unbalance fault data 75 group at 995rpm, an unbalance fault data 75 group at 1503rpm, a rub-over fault data 75 group at 1005rpm, and a rub-over fault data 75 group at 1552 rpm. And pre-training the convolutional neural network through a training set formed by the fault data to obtain a rotor fault detection model. In the subsequent detection process, 25 groups of working condition signals of the unbalance fault at the rotating speed of 507rpm, the unbalance fault at the rotating speed of 995rpm, the unbalance fault at the rotating speed of 1503rpm, the rubbing fault at the rotating speed of 1005rpm and the rubbing fault at the rotating speed of 1552rpm are respectively obtained, and the working condition signals are analyzed through a rotor fault detection model to detect whether the rotor has the corresponding fault.
Referring to fig. 3, fig. 3 is a comparison diagram of rotor fault detection results according to an embodiment of the invention. Specifically, the working condition signal in the above specific embodiment includes a strain signal and a vibration signal, the strain signal and the vibration signal of the rotor are respectively iterated for 10 times by using the rotor fault detection model, and the convergence rates of the strain signal and the vibration signal and the accuracy of fault identification are compared. As can be seen from fig. 3, the rotor fault detection model has a faster convergence rate and a higher accuracy rate when the strain signal is input.
In another embodiment, the present invention further provides a rotary machine, including a rotating shaft, a wheel disc, a tool, and the rotor fault detection system in any of the above embodiments, wherein: the rotating shaft is used for supporting the rotor to rotate and transmitting torque; the wheel disc is fixed on the rotating shaft, connected with the tool through a bolt and used for fixing the tool; the fixture is used for winding the coil and fixing the detection circuit; and the rotor fault detection system is used for acquiring working condition signals of the rotor when the rotor rotates and analyzing the working condition signals so as to judge whether the rotor has faults or not.
Illustratively, the rotary machine includes a rotor fault detection system, a shaft, a disk, and a tooling. The rotor fault detection system is fixed on the rotor and used for obtaining working condition signals of the rotor and analyzing the working condition signals so as to judge whether the rotor has faults or not. The rotating shaft is the rotating center of the rotor and is used for supporting the rotor to rotate and transmitting the torque generated when the rotor rotates. The center of the wheel disc is connected with the rotating shaft to be fixed on the rotating shaft, and is connected with the tool through the bolt structure to support the tool. The frock is the main part of rotor for the coil and the fixed detection circuitry of winding rotor.
In another embodiment, the coil of the rotor is wound outside the tool, the carrier circuit is fixed on the inner wall of the tool, the tool is provided with a threading hole, and a lead is led into the threading hole so as to connect the coil with the carrier circuit.
Exemplarily, a coil of the rotor is wound outside the tool and used for cutting the magnetic induction line to generate current when the rotor rotates, and the carrier circuit is fixed on the inner wall of the tool and used for acquiring working condition signals of the rotor. Wherein, the frock structure is equipped with the through wires hole for through the wire, with connecting coil and carrier circuit.
Referring to fig. 4, fig. 4 is a schematic structural diagram of a rotating machine according to an embodiment of the present invention. Specifically, the rotary machine in this embodiment includes a rotating shaft 1, a wheel disc 2, a tool 3, a magnetic isolation material 4, a coil 5, a threading hole 6, a conducting wire 7, an acceleration sensor 8, a strain gauge 9, a carrier circuit 10, a wheel disc threaded hole 11, an expansion sleeve 12, and an expansion sleeve threaded hole 13. Wherein, be provided with rim plate 2, frock 3, foil gage 9 on the pivot 1, rim plate 2 is fixed in on the pivot 1 for support frock 3 and drive frock 3 rotatory, frock 3 is connected with rim plate 2 through the bolt. The surface of the tool 3 is coated with a magnetic isolation material 4, the magnetic isolation material 4 is wound with a coil 5, the magnetic isolation material 4 is used for shielding electromagnetic interference caused by a metal environment, and the coil 5 is made of metal copper and used for realizing wireless power supply when the rotor rotates. The tool structure is provided with a threading hole 6, and a lead 7 is arranged in the threading hole and used for connecting the coil 5 with a carrier circuit 10 on the inner wall of the tool 3. The strain gauges 9 are perpendicular to each other and arranged on the rotating shaft 1, one of the strain gauges is parallel to the rotating shaft direction, and the other strain gauge is perpendicular to the rotating shaft direction and fixed through the strain gauge adhesion water agent and used for collecting strain signals when the rotor rotates. The acceleration sensor 8 is fixed on a bearing seat of the rotor and used for collecting vibration signals.
Referring to fig. 5, fig. 5 is a schematic view of a tooling structure according to an embodiment of the invention. Specifically, a carrier circuit 10 is arranged inside the tool 3 along the inner wall surface, and is used for receiving the strain signal sent by the strain gauge 9 and sending the strain signal to the computing unit. The tool 3 is provided with a threading hole 6 for connecting the carrier circuit 10 with the coil 5 through a lead 7.
Referring to fig. 6, fig. 6 is a schematic diagram of a wheel disc structure according to an embodiment of the present invention. Specifically, the outer ring of the wheel disc 2 is provided with a wheel disc threaded hole 11, and the tool 3 and the wheel disc 2 are fixed through bolts. The expansion sleeve 12 and the wheel disc are coaxial, and are structurally provided with expansion sleeve threaded holes 13, and the wheel disc 2 is locked through bolts to be axially positioned.
It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to be limiting. All other embodiments, which can be derived by a person skilled in the art from the examples provided herein without any inventive step, shall fall within the scope of protection of the present application.
It is obvious that the drawings are only examples or embodiments of the present application, and it is obvious to those skilled in the art that the present application can be applied to other similar cases according to the drawings without creative efforts. Moreover, it should be appreciated that in the development of any such actual implementation, as in any engineering or design project, numerous implementation-specific decisions must be made to achieve the developers' specific goals, such as compliance with system-related and business-related constraints, which may vary from one implementation to another.
The term "embodiment" is used herein to mean that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is to be expressly or implicitly understood by one of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the patent protection. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.
Claims (10)
1. A rotor fault detection system is applied to a rotary machine, and is characterized by comprising a wireless power supply unit, a detection circuit and a calculation unit, wherein:
the wireless power supply unit is used for supplying power to the detection circuit;
the detection circuit is fixed on the rotor and used for acquiring working condition signals of the rotor when the rotor rotates and sending the working condition signals to the calculation unit in a wireless mode;
and the calculating unit is used for judging whether the rotor has faults or not according to the working condition signals.
2. The rotor fault detection system of claim 1, wherein the detection circuit includes a coil, a strain gage, and a carrier circuit, wherein:
the coil is used for acquiring the electric energy of the wireless power supply unit so as to supply power to the detection circuit;
the strain gauge is connected with the rotor and used for acquiring a strain signal of the rotor when the rotor rotates and sending the strain signal to the carrier circuit;
the carrier circuit is used for receiving the strain signal and sending the strain signal to the computing unit in a wireless mode, so that the computing unit can judge whether the rotor has faults or not according to the strain signal.
3. The rotor fault detection system of claim 2, wherein the strain gauge is connected to a rotor shaft of the rotor for acquiring a first strain signal at the rotor shaft when the rotor is rotating and/or to a blade root of the rotor for acquiring a second strain signal at the blade root when the rotor is rotating, the blade being connected to the rotor shaft for increasing an air intake of the rotary machine.
4. The rotor fault detection system of claim 2, wherein the detection circuit includes two strain gauges, one strain gauge being parallel to the direction of the axis of rotation and the other strain gauge being perpendicular to the direction of the axis of rotation.
5. The rotor fault detection system of claim 2, wherein the carrier circuit is a flex circuit and is disposed along a tooling inner wall surface of the rotor.
6. The rotor fault detection system of claim 1, further comprising an acceleration sensor coupled to a bearing housing of the rotor, wherein:
the acceleration sensor is used for collecting vibration signals on the bearing seat when the rotor rotates and sending the vibration signals to the computing unit;
and the calculating unit is used for judging whether the rotor has a fault or not according to the vibration signal.
7. The rotor fault detection system of claim 1, wherein the computing unit is further configured to input the operating condition signal to a rotor fault detection model to determine whether a fault exists in the rotor, and the rotor fault detection model comprises a trained convolutional neural network.
8. The rotor fault detection system of claim 7, wherein the computing unit is further configured to train the convolutional neural network according to fault sample data and corresponding fault results to obtain the rotor fault detection model.
9. A rotary machine comprising a shaft, a wheel disc, a tooling, and the rotor fault detection system of any of claims 1-8, wherein:
the rotating shaft is used for supporting the rotor to rotate and transmitting torque;
the wheel disc is fixed on the rotating shaft, connected with the tool through a bolt and used for fixing the tool;
the tool is used for winding a coil and fixing the detection circuit;
and the rotor fault detection system is used for acquiring working condition signals of the rotor when the rotor rotates and analyzing the working condition signals so as to judge whether the rotor has faults or not.
10. The rotating machine according to claim 9, wherein a coil of the rotor is wound around an outside of the tool, the carrier circuit is fixed to an inner wall of the tool, the tool is provided with a threading hole, and a lead is passed through the threading hole to connect the coil and the carrier circuit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111626797.2A CN114152433A (en) | 2021-12-28 | 2021-12-28 | Rotor failure detection system and rotary machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111626797.2A CN114152433A (en) | 2021-12-28 | 2021-12-28 | Rotor failure detection system and rotary machine |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114152433A true CN114152433A (en) | 2022-03-08 |
Family
ID=80449344
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111626797.2A Pending CN114152433A (en) | 2021-12-28 | 2021-12-28 | Rotor failure detection system and rotary machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114152433A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102102629A (en) * | 2011-01-17 | 2011-06-22 | 东南大学 | On-line data acquisition and analysis device of wind generating set |
| CN107179194A (en) * | 2017-06-30 | 2017-09-19 | 安徽工业大学 | Rotating machinery fault etiologic diagnosis method based on convolutional neural networks |
| CN107453581A (en) * | 2017-07-28 | 2017-12-08 | 华南理工大学 | A kind of rotor line ring type electromagnetism watertight torque transmission axle |
| CN208520574U (en) * | 2018-08-21 | 2019-02-19 | 辛迈 | General power group intelligent diagnosis system |
| CN110118152A (en) * | 2019-06-14 | 2019-08-13 | 三一重能有限公司 | Wind generator set blade air-balance monitors adjustment system and monitoring method of adjustment |
| CN209613807U (en) * | 2019-03-26 | 2019-11-12 | 马鞍山钢铁股份有限公司 | A kind of real-time torsional oscillation on-Line Monitor Device of mill main drive system |
| CN110487549A (en) * | 2019-09-10 | 2019-11-22 | 哈工大机器人（山东）智能装备研究院 | Bearing fault recognition methods, device, computer equipment and storage medium |
| CN209838604U (en) * | 2018-12-26 | 2019-12-24 | 内蒙古工业大学 | Wind turbine blade stress-strain testing device based on rotating platform |
| CN113281029A (en) * | 2021-06-09 | 2021-08-20 | 重庆大学 | Rotating machinery fault diagnosis method and system based on multi-scale network structure |
| CN113588272A (en) * | 2021-07-23 | 2021-11-02 | 上海交通大学 | Double-rotor blade composite fault simulation test bed |
-
2021
- 2021-12-28 CN CN202111626797.2A patent/CN114152433A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102102629A (en) * | 2011-01-17 | 2011-06-22 | 东南大学 | On-line data acquisition and analysis device of wind generating set |
| CN107179194A (en) * | 2017-06-30 | 2017-09-19 | 安徽工业大学 | Rotating machinery fault etiologic diagnosis method based on convolutional neural networks |
| CN107453581A (en) * | 2017-07-28 | 2017-12-08 | 华南理工大学 | A kind of rotor line ring type electromagnetism watertight torque transmission axle |
| CN208520574U (en) * | 2018-08-21 | 2019-02-19 | 辛迈 | General power group intelligent diagnosis system |
| CN209838604U (en) * | 2018-12-26 | 2019-12-24 | 内蒙古工业大学 | Wind turbine blade stress-strain testing device based on rotating platform |
| CN209613807U (en) * | 2019-03-26 | 2019-11-12 | 马鞍山钢铁股份有限公司 | A kind of real-time torsional oscillation on-Line Monitor Device of mill main drive system |
| CN110118152A (en) * | 2019-06-14 | 2019-08-13 | 三一重能有限公司 | Wind generator set blade air-balance monitors adjustment system and monitoring method of adjustment |
| CN110487549A (en) * | 2019-09-10 | 2019-11-22 | 哈工大机器人（山东）智能装备研究院 | Bearing fault recognition methods, device, computer equipment and storage medium |
| CN113281029A (en) * | 2021-06-09 | 2021-08-20 | 重庆大学 | Rotating machinery fault diagnosis method and system based on multi-scale network structure |
| CN113588272A (en) * | 2021-07-23 | 2021-11-02 | 上海交通大学 | Double-rotor blade composite fault simulation test bed |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107247230B (en) | Rotary motor state monitoring method based on support vector machine and data driving | |
| CN107345857A (en) | A kind of electro spindle condition monitoring and failure diagnosis system and its monitoring, diagnosing method | |
| CA2875071C (en) | Method and system for testing operational integrity of a drilling rig | |
| CN103620354B (en) | For monitoring the method for degaussing | |
| US5995910A (en) | Method and system for synthesizing vibration data | |
| CN104977047A (en) | Wind turbine online condition monitoring and health assessment system and method thereof based on vibration and oil | |
| EP2885646B1 (en) | System and method for monitoring an electrically-connected system having a periodic behavior | |
| CN110056640B (en) | Speed reducer wireless fault diagnosis method based on acceleration signal and edge calculation | |
| CN109724791A (en) | A kind of intelligence vibration analysis and trouble-shooter and its working method | |
| CN110134571A (en) | Rotary-type mechanical equipment health status monitoring method and device | |
| CN110462352A (en) | Vibration analyzer and mechanical part diagnostic system | |
| US9316676B2 (en) | System and method for monitoring an electrically-connected system having a periodic bahavior | |
| CN111999087A (en) | Vibration screen online state monitoring method based on LabVIEW | |
| CN114739667A (en) | Multi-mode information fusion bearing lubrication state monitoring device and method | |
| KR20210006832A (en) | Method and apparatus for machine fault diagnosis | |
| JP2015031563A (en) | Method for analyzing vibration of bearing device, apparatus for analyzing vibration of bearing device, and device for monitoring state of rolling bearing | |
| CN114152433A (en) | Rotor failure detection system and rotary machine | |
| CN105784364A (en) | Bearing fault diagnosis method based on total experience mode decomposition and fractal box dimensions | |
| Mo et al. | An FFT-based high-speed spindle monitoring system for analyzing vibrations | |
| CN106403880A (en) | Method and device for detecting clearance between rotor and stator of compressor | |
| CN117052608A (en) | Acoustic-vibration-synergistic fan blade fracture early warning device and method | |
| CN204788494U (en) | Monitoring of wind turbine generator system presence and healthy evaluation system based on vibration and fluid | |
| Tseng et al. | A Diagnostic System for Speed‐Varying Motor Rotary Faults | |
| CN206073967U (en) | A kind of gap detection device between compressor drum and stator | |
| CN111947927B (en) | Rolling bearing fault detection method based on chromaticity theory |
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: 20220308 |
|
| RJ01 | Rejection of invention patent application after publication |