CN114739666A - Bearing wear manufacturing and detecting integrated device - Google Patents

Bearing wear manufacturing and detecting integrated device Download PDF

Info

Publication number
CN114739666A
CN114739666A CN202210218131.1A CN202210218131A CN114739666A CN 114739666 A CN114739666 A CN 114739666A CN 202210218131 A CN202210218131 A CN 202210218131A CN 114739666 A CN114739666 A CN 114739666A
Authority
CN
China
Prior art keywords
bearing
phase
radar
wear
servo motor
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
Application number
CN202210218131.1A
Other languages
Chinese (zh)
Other versions
CN114739666B (en
Inventor
张留洋
柯志武
周洪宽
陈朝旭
田***
连光辉
王蓉
郝慧博
王星雨
王中兴
郑伟
林原胜
赵振兴
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xian Jiaotong University
719th Research Institute of CSIC
Original Assignee
Xian Jiaotong University
719th Research Institute of CSIC
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Xian Jiaotong University, 719th Research Institute of CSIC filed Critical Xian Jiaotong University
Priority to CN202210218131.1A priority Critical patent/CN114739666B/en
Publication of CN114739666A publication Critical patent/CN114739666A/en
Application granted granted Critical
Publication of CN114739666B publication Critical patent/CN114739666B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B24—GRINDING; POLISHING
    • B24B—MACHINES, DEVICES, OR PROCESSES FOR GRINDING OR POLISHING; DRESSING OR CONDITIONING OF ABRADING SURFACES; FEEDING OF GRINDING, POLISHING, OR LAPPING AGENTS
    • B24B5/00—Machines or devices designed for grinding surfaces of revolution on work, including those which also grind adjacent plane surfaces; Accessories therefor
    • B24B5/36—Single-purpose machines or devices
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B24—GRINDING; POLISHING
    • B24B—MACHINES, DEVICES, OR PROCESSES FOR GRINDING OR POLISHING; DRESSING OR CONDITIONING OF ABRADING SURFACES; FEEDING OF GRINDING, POLISHING, OR LAPPING AGENTS
    • B24B41/00—Component parts such as frames, beds, carriages, headstocks
    • B24B41/06—Work supports, e.g. adjustable steadies
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B24—GRINDING; POLISHING
    • B24B—MACHINES, DEVICES, OR PROCESSES FOR GRINDING OR POLISHING; DRESSING OR CONDITIONING OF ABRADING SURFACES; FEEDING OF GRINDING, POLISHING, OR LAPPING AGENTS
    • B24B49/00—Measuring or gauging equipment for controlling the feed movement of the grinding tool or work; Arrangements of indicating or measuring equipment, e.g. for indicating the start of the grinding operation
    • B24B49/12—Measuring or gauging equipment for controlling the feed movement of the grinding tool or work; Arrangements of indicating or measuring equipment, e.g. for indicating the start of the grinding operation involving optical means
    • 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
    • G01M13/04—Bearings
    • G01M13/045—Acoustic or vibration analysis
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/02—Systems using the reflection of electromagnetic waves other than radio waves
    • G01S17/06—Systems determining position data of a target
    • G01S17/08—Systems determining position data of a target for measuring distance only
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/88—Lidar systems specially adapted for specific applications
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P70/00—Climate change mitigation technologies in the production process for final industrial or consumer products
    • Y02P70/10—Greenhouse gas [GHG] capture, material saving, heat recovery or other energy efficient measures, e.g. motor control, characterised by manufacturing processes, e.g. for rolling metal or metal working

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Mechanical Engineering (AREA)
  • Electromagnetism (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Acoustics & Sound (AREA)
  • Length Measuring Devices By Optical Means (AREA)

Abstract

The bearing wear manufacturing and detecting integrated device is characterized in that a grinding tool is used for grinding a bearing to generate wear; the grinding tool clamping mechanism can detachably clamp the grinding tool; the motor is connected with the grinding tool to rotate the grinding tool; the clamping structure clamps the bearing to be polished; the alternating current servo motor is connected with the clamping mechanism to control the rotation angle of the bearing so as to adjust the plane to be polished; detecting the relative distance from the plane to be polished to the grinding tool by using a laser radar; the terahertz radar faces a plane to be polished to detect the wear state in real time; and a control device which connects the laser radar, the terahertz radar, the alternating current servo motor and the motor, controls the alternating current servo motor based on the relative distance, and controls the motor to drive the grinding tool based on the wear state.

Description

Bearing wear manufacturing and detecting integrated device
Technical Field
The invention relates to the field of bearing wear monitoring, in particular to a bearing wear manufacturing and detecting integrated device.
Background
The bearing is an important part in the modern mechanical equipment, and has the main functions of supporting a mechanical rotating body, reducing the friction coefficient in the motion process of the mechanical rotating body and ensuring the rotation precision of the mechanical rotating body. The rolling bearing generally comprises four parts, namely an outer ring, an inner ring, a rolling body and a retainer, and strictly speaking comprises six parts, namely the outer ring, the inner ring, the rolling body, the retainer, a seal and lubricating oil. In short, the rolling bearing can be defined as a rolling bearing as long as the rolling bearing includes an outer ring, an inner ring, and rolling elements. Rolling bearings are classified into ball bearings and roller bearings according to the shape of the rolling elements.
As defective products can appear in the bearing production process, and the degree of bearing abrasion cannot be estimated, the performance of the bearing needs to be detected after the bearing survives. In a plurality of detection items, the outer surface abrasion detection of the bearing is an important technical index, and in the prior art, the detection effect of the abrasion detection outside the bearing is poor, and the abrasion detection is very inconvenient for bearings with different specifications, so that a device for manufacturing the outer surface abrasion degree of the bearing and the detection device are provided.
The above information disclosed in this background section is only for enhancement of understanding of the background of the invention and therefore it may contain information that does not form the prior art that is already known in this country to a person of ordinary skill in the art.
Disclosure of Invention
In view of the above-mentioned deficiencies or drawbacks of the prior art, an integrated bearing wear manufacturing and detecting device is provided that automatically manufactures a desired wear state of a bearing.
The purpose of the invention is realized by the following technical scheme.
The bearing wear manufacturing and detecting integrated device comprises:
grinding device, it includes:
a grinder that grinds the bearing to generate wear;
a grinder holding mechanism detachably holding the grinder;
a motor connected to the grinder to rotate the grinder;
a workpiece holding device, comprising:
the clamping structure clamps the bearing to be polished;
the alternating current servo motor is connected with the clamping mechanism to control the rotation angle of the bearing so as to adjust the plane to be polished;
a detection tool, comprising:
the laser radar is used for detecting the relative distance from the plane to be polished to the grinding tool;
a terahertz radar facing the plane to be polished to detect a wear state in real time;
and a control device which connects the laser radar, the terahertz radar, the alternating current servo motor and the motor, controls the alternating current servo motor based on the relative distance, and controls the motor to drive the grinding tool based on the wear state.
In the bearing wear manufacturing and detecting integrated device, the bearing wear manufacturing and detecting integrated device is supported on a horizontal bottom plate.
In the bearing wear manufacturing and detecting integrated device, the grinding device is arranged on a guide rail which moves up and down and is driven by an alternating current servo motor for moving up and down through a grinding tool, and the guide rail is vertically supported on the bottom plate.
In the bearing wear manufacturing and detecting integrated device, the grinding tool comprises a cutter.
In the bearing wear manufacturing and detecting integrated device, the workpiece clamping device is supported by a ball screw for left-right movement and a ball screw for front-back movement through ball screw coupling, the ball screw for left-right movement is connected with an alternating current servo motor for left-right movement in a driving manner, and the ball screw for front-back movement is connected with an alternating current servo motor for front-back movement in a driving manner.
In the bearing wear manufacturing and detecting integrated device, a terahertz radar transmits linear frequency modulation continuous waves to a surface to be polished and receives reflected echo signals; the echo signals and the transmitting signals are mixed to obtain intermediate frequency signals, the obtained intermediate frequency signals are preprocessed, phase vibration signals are extracted, and a wear state is generated based on the phase vibration signals.
The bearing abrasion manufacturing and detecting integrated device is characterized in that a bearing abrasion detecting device is arranged on the bearing abrasion manufacturing and detecting integrated device;
in the preprocessing of the phase vibration signal, the object displacement distance is Δ R, the wavelength of the center frequency of the transmission frequency of the terahertz radar is λ, and the phase variation between continuous measurements is:
Figure BDA0003535118970000031
the terahertz radar obtains an intermediate frequency signal as ADC original data by mixing the transmitted wave and the echo; performing fast Fourier transform on ADC (analog to digital converter) original data obtained by the terahertz radar to obtain distance data; determining the distance range of the target according to the position relation between the terahertz radar and the rolling bearing, and searching the distance data in the distance range；
According to the formula
Figure BDA0003535118970000032
To obtain
Figure BDA0003535118970000033
To obtain the position of the target, fsIs the sampling frequency, nsamplesIs the number of sampling points, R is the distance between the target and the terahertz radar, B is the bandwidth of the terahertz radar, nbinIs the position of the peak of the waveform, which is the reflection of the target;
the detection frame period is T, the phase of the target is extracted once every time T, the detection frame lasts for n times to obtain the value change of the phase along with the frame number, the relation between the target phase change and the time is recorded as a vibration signal x (T), and the abrasion state is generated based on the vibration signal x (T).
In the bearing wear manufacturing and detecting integrated device, when the phase difference between continuous values is larger than or smaller than +/-pi, the phase expansion is executed by subtracting 2 pi from the phase, and Fourier transformation data obtained by Fourier transformation of a vibration signal x (t) is input into a deep neural network model to generate a wear state.
Advantageous effects
The existing bearing abrasion manufacturing device is difficult to detect in real time and design for different abrasion degrees. The invention detects the position of the bearing according to the laser radar and detects the abrasion of the bearing in real time according to the terahertz radar, thereby designing different abrasion degrees. The terahertz radar detection adopts non-contact detection, and the temperature does not interfere with terahertz echo, so that the method can be suitable for bearing surface diagnosis of different types and different wear conditions. The polishing process is fully automatic, extra manpower is not needed for supervision, the cost is reduced, and the efficiency is improved. Secondly, the polishing effect can be detected in real time through signals fed back by the laser radar, and the polishing position can be accurately controlled through controlling a motor. In addition, different degrees of grinding operations can be performed by replacing the grinding tool. The terahertz radar can realize real-time detection of bearing abrasion, so that closed-loop control is realized.
The above description is only an overview of the technical solutions of the present invention, and in order to make the technical means of the present invention more clearly apparent, and to make the implementation of the content of the description possible for those skilled in the art, and to make the above and other objects, features and advantages of the present invention more obvious, the following description is given by way of example of the specific embodiments of the present invention.
Drawings
Various other advantages and benefits of the present invention will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. It is obvious that the drawings described below are only some embodiments of the invention, and that for a person skilled in the art, other drawings can also be derived from them without inventive effort. Also, like parts are designated by like reference numerals throughout the drawings.
In the drawings:
FIG. 1 is a schematic top view of an integrated bearing wear manufacturing and testing apparatus according to one embodiment of the present invention;
FIG. 2 is a schematic structural diagram of one embodiment of an integrated bearing wear manufacturing and inspection device in accordance with one embodiment of the present invention;
FIG. 3 is a schematic control flow diagram of an integrated bearing wear manufacturing and inspection device according to one embodiment of the present invention;
FIG. 4 is a schematic view of a terahertz radar detection flow of an integrated bearing wear manufacturing and detection device according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a deep neural network of an integrated bearing wear manufacturing and testing device, according to one embodiment of the present invention;
FIG. 6 is a schematic diagram of a neural network architecture of an integrated bearing wear manufacturing and inspection device, according to one embodiment of the present invention.
The invention is further explained below with reference to the figures and examples.
Detailed Description
Specific embodiments of the present invention will be described in more detail below with reference to fig. 1 to 6. While specific embodiments of the invention are shown in the drawings, it should be understood that the invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
It should be noted that certain terms are used throughout the description and claims to refer to particular components. As one skilled in the art will appreciate, various names may be used to refer to a component. The description and claims do not intend to distinguish between components that differ in name but not function. In the following description and in the claims, the terms "include" and "comprise" are used in an open-ended fashion, and thus should be interpreted to mean "include, but not limited to. The description which follows is a preferred embodiment of the invention, but is made for the purpose of illustrating the general principles of the invention and not for the purpose of limiting the scope of the invention. The scope of the present invention is defined by the appended claims.
For the understanding of the embodiments of the present invention, the following detailed description will be given by way of example with reference to the accompanying drawings, and the drawings are not intended to limit the embodiments of the present invention.
As shown in fig. 1 to 6, the integrated bearing wear manufacturing and detecting apparatus includes,
grinding device, it includes:
a grinder 15 that grinds the bearing to generate wear;
a grinder holding mechanism 16 that detachably holds the grinder 15;
a motor 8 connected to the grinder 15 to rotate the grinder 15;
a workpiece holding device, comprising:
the clamping structure 1 clamps the bearing 2 to be polished;
the alternating current servo motor 4 is connected with the clamping mechanism to control the rotation angle of the bearing so as to adjust the plane to be polished;
a detection tool, comprising:
a laser radar that detects the relative distance from the plane to be polished to the grinding tool 15;
a terahertz radar 9 facing the plane to be polished to detect a wear state in real time;
and a control device which connects the laser radar, the terahertz radar 9, the alternating current servo motor and the motor, controls the alternating current servo motor based on the relative distance, and controls the motor to drive the grinding tool 15 based on the wear state.
In the preferred embodiment of the integrated bearing wear manufacturing and detecting device, the integrated bearing wear manufacturing and detecting device is supported on a horizontal bottom plate 13.
In the preferred embodiment of the integrated bearing wear manufacturing and detecting device, the grinding device is mounted on a guide rail 14 which moves up and down and is vertically driven by an ac servo motor via a grinding tool 15, and the guide rail is vertically supported on the bottom plate 13.
In a preferred embodiment of the integrated bearing wear manufacturing and detecting device, the grinding tool 15 comprises a cutter.
In the preferred embodiment of the integrated bearing wear manufacturing and detecting device, the workpiece holding device is supported by a ball screw 5 for left-right movement and a ball screw 7 for front-back movement via a ball screw coupling 3, the ball screw 5 for left-right movement is connected to an ac servomotor 6 for left-right movement in a driving manner, and the ball screw 7 for front-back movement is connected to an ac servomotor 11 for front-back movement in a driving manner.
In the preferred embodiment of the bearing wear manufacturing and detection integrated device, the terahertz radar 9 transmits linear frequency modulation continuous waves to the surface to be polished and receives reflected echo signals; the echo signals and the transmitting signals are mixed to obtain intermediate frequency signals, the obtained intermediate frequency signals are preprocessed, phase vibration signals are extracted, and a wear state is generated based on the phase vibration signals.
In the preferred embodiment of the integrated bearing wear manufacturing and detecting device,
in the phase vibration signal preprocessing, the object displacement distance is delta R, the wavelength of the center frequency of the transmitting frequency of the terahertz radar is lambda, and the phase variation between continuous measurements is as follows:
Figure BDA0003535118970000081
the terahertz radar performs frequency mixing on the transmitted waves and the echoes to obtain intermediate frequency signals serving as ADC original data; performing fast Fourier transform on ADC (analog to digital converter) original data obtained by the terahertz radar to obtain distance data; determining a distance range of a target according to the position relation between the terahertz radar and the rolling bearing, and searching the distance data in the distance range;
according to the formula
Figure BDA0003535118970000082
To obtain
Figure BDA0003535118970000083
To obtain the position of the target, fsIs the sampling frequency, nsamplesIs the number of sampling points, R is the distance between the target and the terahertz radar, B is the bandwidth of the terahertz radar, nbinIs the position of the peak of the waveform, which is the reflection of the target;
the detection frame period is T, the phase of the target is extracted once every time T, the detection frame is continuously detected for n times to obtain the value change of the phase along with the frame number, the relation between the target phase change and the time is recorded as a vibration signal x (T), and the abrasion state is generated based on the vibration signal x (T).
In the preferred embodiment of the integrated bearing wear manufacturing and detecting device, when the phase difference between continuous values is larger than or smaller than +/-pi, phase expansion is performed by subtracting 2 pi from the phase, and Fourier transformation data obtained by Fourier transformation of a vibration signal x (t) is input into a deep neural network model to generate a wear state.
The bearing wear manufacturing and detecting integrated device is driven by electric power, the surface of the bearing can be automatically polished, and more effects can be achieved by replacing the grinding tool 15. By clamping the workpiece, the surface of the workpiece to be polished can be changed, and the horizontal position of the grinding tool 15 can move left and right and back and up and down. The terahertz radar 9 realizes real-time detection of the bearing wear state.
In one embodiment, the grinding device includes a grinder 15, a grinder holding mechanism 16, a common ac motor; the clamping mechanism can realize different polishing effects by replacing the grinding tool 15; the common ac motor is used to drive the grinding tool 15 to rotate. The workpiece clamping device comprises a clamping structure 1 and an alternating current servo motor; the clamping structure 1 is used for clamping a workpiece to be polished; the alternating current servo motor is used for controlling the rotation angle of the workpiece so as to polish different planes. The grinder supporting mechanism 10 supports the grinder 15.
The detection means comprises a lidar; the laser radar is used for detecting the relative distance from a plane to be polished to a polishing tool and adjusting the spatial position of the polishing device, wherein the spatial position comprises the horizontal distance and the vertical distance from the surface of a workpiece to be polished, so that the automatic polishing effect is realized. The terahertz radar 9 is used for detecting the polishing degree of the surface of the bearing and detecting the polishing progress in real time.
The control device comprises an alternating current servo motor, a 32-bit singlechip, a control switch and an encoder; the alternating current servo motor is used for controlling the left-and-right movement of the clamping structure 1, controlling the front-and-back movement of the clamping structure 1 and controlling the up-and-down movement of the polishing device so as to realize decentralized control; the single chip microcomputer acquires information by processing signals of the laser radar, outputs signals to excite the encoder, controls the rotation of the alternating current servo motor, judges whether the grinding tool is positioned right above the grinding surface through feedback signals of the laser radar, and controls the grinding tool 15 and the relative spatial position of a workpiece; the control switch controls the starting and the closing of the common alternating current motor and the rotating speed; the encoder is used to assist the ac servo motor to rotate accurately.
As one of the preferable schemes, the horizontality of the plane of the workpiece to be polished can be judged in real time polishing through the laser radar, even if interference factors such as mistaken touch vibration and the like occur in the machining process, the final polishing effect cannot be influenced, and the robustness of the polishing system is greatly enhanced.
Preferably, each ac servo motor is provided with an independent encoder, which works independently of each other without interfering with each other, but is linked by a control system. The control system accurately controls the rotation angle of the alternating current servo motor through the encoder and accurately controls the polishing position; the servo motor is directly driven, the use of a transmission mechanism is reduced, and the structure is simplified.
As one of the preferred solutions, both the grinding and perforating functions can be combined into the same device by replacing the grinding tool 15. Meanwhile, different polishing tools 15 can be selected for different woods or different furniture, so that the polishing effect is optimal.
As shown in fig. 1, the workpiece holding device is connected with a ball screw, and a servo motor drives the ball screw to control the position of the workpiece holding device; the terahertz radar 9, the laser radar detection device and the polishing device are fixed together, have a fixed relative spatial relationship, and the position of the polishing device can be judged through the laser radar; the servo motor direct drive reduces drive mechanism's use, simplifies the structure, and different motion forms are controlled by the servo motor that does not use, and a plurality of power supplies work simultaneously, each other noninterference.
As shown in fig. 2, the grinding device is mounted on a guide rail which can move up and down, the position of the guide rail is independent of the moving area of the workpiece, and the upper space extends into the working area, so that the movement of the clamping device is not interfered; the grinding tool 15 is connected with the supporting device through a clamping device and can be replaced; the grinding tool 15 is directly driven by a motor, simplifying the mechanism. In one embodiment, the grinder 15 is connected to the up and down movement ac servo motor 12 and supported via the grinder support mechanism 10.
As shown in fig. 3, after a workpiece to be polished is clamped, a main switch is turned on, the laser radar can judge the relative spatial positions of the polishing device and the clamping device, signals are transmitted to a single chip microcomputer, then signals are output to excite an encoder, the rotation of an alternating current servo motor is controlled, the clamping device moves, the polishing device is adjusted to a proper polishing position based on the feedback of the laser radar, then the polishing device is controlled to move up and down to be adjusted to a proper position based on the information processing of the single chip microcomputer, and whether the polishing tool is positioned right above the surface to be polished is judged through the feedback signals of the laser radar; and ending the whole system after the system judges whether the wear degree meets the requirement.
In one embodiment, as shown in fig. 4, a linear frequency-modulated continuous wave is first transmitted by the terahertz radar 9 to the bearing being operated; next, the terahertz radar 9 receives echo signals reflected by the bearing to be detected and the surrounding environment object; the echo signals and the transmitting signals are subjected to frequency mixing to obtain intermediate frequency signals, the obtained intermediate frequency signals are preprocessed, phase vibration signals are extracted, noise reduction and filtering processing are carried out, and the influence of signals reflected by the surrounding environment and objects is reduced; the preprocessed signals are input into a deep learning neural network which is trained in advance, so that the defect that the fault categories cannot be distinguished by the traditional method is overcome, and the fault degree can be effectively and accurately identified; and finally, outputting the fault diagnosis result.
The terahertz radar 9 receives an echo signal, transmits the signal to a PC terminal for preprocessing, and then inputs the preprocessed signal to a deep neural network trained in advance, as shown in fig. 5, the deep neural network is described by taking Resnet as an example, but is not limited to the network model.
The method includes the following steps that the terahertz radar 9 is used for collecting operation data of a certain number of bearings in advance to train the model for follow-up real-time monitoring:
s1: collecting spool and valve rod vibration signals of an electromagnetic directional valve which are prone to faults by using a terahertz radar 9, and collecting normal bearings and three bearing fault parts which only have surface wear and are effectively worn 1/4, 2/1 and 3/4 as data sets under five working conditions of 500rpm, 800rpm, 1000rpm, 1500rpm and 2000rpm of rotation speed respectively;
s2: carrying out proper pretreatment on the acquired vibration signal, dividing the signal into a training set, a verification set and a test set, then training and testing the neural network model, and storing the predicted optimal model parameters in the test result as a pre-training model for subsequent use;
s21: inputting signals collected aiming at different types of fault pieces described in S1 into a deep neural network model to be trained, and extracting the characteristics of the deep neural network model; the adopted ResNet network model aiming at the one-dimensional signal is firstly a one-dimensional convolution layer, a Batch Normalization layer and a Max-firing layer; followed by four residual blocks and 3 identical network structures; the residual block is followed by an Average capacitance layer, an FC layer and a Softmax function. Not specifically stated, the activation functions are all ReLU functions; in the training process, the batch size is 64, each 1024 points is used as a sample, the learning rate is 0.001, and the iteration round is 40.
S22: the Batch Normalization layer is a Batch Normalization layer, and can prevent gradient disappearance and gradient explosion and accelerate convergence speed; the Max-posing layer is a maximum pooling layer; the Average pond layer is an Average pond layer; the FC layer is a full connection layer; the Softmax function is used to classify the output results.
The working principle of the terahertz radar 9 is as follows:
s1: the target is detected by using a terahertz wave band Frequency Modulated Continuous Wave (FMCW) radar.
S2: the intermediate frequency signal is obtained by continuously transmitting linear frequency-modulated continuous waves and mixing the echo waves with fundamental waves. The signals emitted by the radar are:
Figure BDA0003535118970000131
wherein f iscIs the center frequency of radar transmission, the range is the terahertz wave band, B is the bandwidth of radar, T is the period of linear frequency modulation, a0Is the amplitude of the transmitted signal.
S3: the radar receives signals reflected by an object as follows:
Figure BDA0003535118970000132
where R is the distance of the target from the radar, c is the speed of light in vacuum, tdK is the attenuation coefficient of the received signal for the time delay of the received signal.
Figure BDA0003535118970000133
After mixing and filtering, the radar receives object signals from the range of R as follows:
Figure BDA0003535118970000134
i.e. for a single object, the received signal b (t) is of frequency fbPhase of phibThe sinusoidal signal of (a), wherein:
Figure BDA0003535118970000141
the steps of preprocessing the signal received by the terahertz radar 9 are as follows:
s1: in order to be able to measure the vibration at a small scale of the bearing, the phase change of the LFMCW signal according to the measurement is required. If the object displacement distance is Δ R, the phase variation between consecutive measurements is:
Figure BDA0003535118970000142
s2: distance dimension fourier transform: firstly, performing fast Fourier transform on ADC (analog to digital converter) original data obtained by a radar to obtain distance data;
s3: the distance range of the target can be determined through the approximate position relation between the radar and the bearing, and corresponding distance data are obtained through searching in the range;
according to the formula:
Figure BDA0003535118970000143
deforming it can yield:
Figure BDA0003535118970000144
wherein f issIs the sampling frequency, nsamplesIs the number of sampling points, nbinThe position of the target can be obtained by the formula, where the peak of the waveform is the position of the peak and the peak is the reflection of the target.
S4: the detection (frame) period is T, i.e. the phase of the object is extracted once every time T. If the radial distance between the target and the radar is changed, the Range bin distance data at the moment needs to be obtained according to the algorithm (3), and then the phase is extracted. The detection lasts for n times (frames), so that the value change of the phase along with the frame number (cycle number) can be obtained, and the relation between the target phase change and the time can also be recorded as a vibration signal x (t).
S5: phase unwrapping: since the phase values are between [ -pi, pi ], we need to expand to obtain the actual displacement curve. Therefore, every time the phase difference between the continuous values is larger/smaller than + -pi, phase unwrapping is performed by subtracting 2 pi from the phase, the phase information obtained after the phase unwrapping is Fourier-transformed, and the obtained Fourier-transformed data is used as the input of the neural network.
Although the embodiments of the present invention have been described above with reference to the accompanying drawings, the present invention is not limited to the above-described embodiments and application fields, and the above-described embodiments are illustrative, instructive, and not restrictive. Those skilled in the art, having the benefit of this disclosure, may effect numerous modifications to the disclosed embodiments without departing from the scope of the invention as defined by the appended claims.

Claims (8)

1. The utility model provides a bearing wear makes and detects integrated device which characterized in that: which comprises the steps of preparing a mixture of a plurality of raw materials,
a polishing device comprising;
a grinder that grinds the bearing to generate wear;
a grinder holding mechanism detachably holding the grinder;
a motor connected to the grinder to rotate the grinder;
a workpiece holding device comprising;
the clamping structure clamps the bearing to be polished;
the alternating current servo motor is connected with the clamping mechanism to control the rotation angle of the bearing so as to adjust the plane to be polished;
a detection tool comprising;
the laser radar is used for detecting the relative distance from the plane to be polished to the grinding tool;
a terahertz radar facing the plane to be polished to detect a wear state in real time;
and a control device which connects the laser radar, the terahertz radar, the alternating current servo motor and the motor, controls the alternating current servo motor based on the relative distance, and controls the motor to drive the grinding tool based on the wear state.
2. The integrated bearing wear manufacturing and detecting device of claim 1, wherein: preferably, the bearing wear manufacturing and detection integrated device is supported on a horizontal base plate.
3. The integrated bearing wear manufacturing and detecting device of claim 2, wherein: the grinding device is installed on a guide rail which moves up and down and is driven up and down by an alternating current servo motor for moving up and down through a grinding tool, and the guide rail is vertically supported on the bottom plate.
4. The integrated bearing wear manufacturing and detecting device of claim 1, wherein: the abrasive article comprises a cutter.
5. The integrated bearing wear manufacturing and detecting device of claim 2, wherein: the workpiece clamping device is supported by a ball screw for left-right movement and a ball screw for front-back movement through a ball screw coupling, the ball screw for left-right movement is in driving connection with an alternating current servo motor for left-right movement, and the ball screw for front-back movement is in driving connection with an alternating current servo motor for front-back movement.
6. The integrated bearing wear manufacturing and detecting device of claim 1, wherein: the method comprises the following steps that a terahertz radar transmits linear frequency modulation continuous waves to a surface to be polished and receives reflected echo signals; the echo signals and the transmitting signals are subjected to frequency mixing to obtain intermediate frequency signals, the obtained intermediate frequency signals are preprocessed, phase vibration signals are extracted, and a wear state is generated based on the phase vibration signals.
7. The integrated bearing wear manufacturing and detecting device of claim 6, wherein: in the preprocessing of the phase vibration signal, the object displacement distance is Δ R, the wavelength of the center frequency of the transmission frequency of the terahertz radar is λ, and the phase variation between continuous measurements is:
Figure FDA0003535118960000021
the terahertz radar obtains an intermediate frequency signal as ADC original data by mixing the transmitted wave and the echo; performing fast Fourier transform on ADC (analog to digital converter) original data obtained by the terahertz radar to obtain distance data; determining a distance range of a target according to the position relation between the terahertz radar and the rolling bearing, and searching the distance data in the distance range;
according to the formula
Figure FDA0003535118960000022
To obtain
Figure FDA0003535118960000023
To obtain the position of the target, fsIs the sampling frequency, nsamplesIs the number of sampling points, R is the distance between the target and the terahertz radar, and B is that of the terahertz radarBandwidth, nbinIs the position of the peak of the waveform, which is the reflection of the target;
the detection frame period is T, the phase of the target is extracted once every time T, the detection frame is continuously detected for n times to obtain the value change of the phase along with the frame number, the relation between the target phase change and the time is recorded as a vibration signal x (T), and the abrasion state is generated based on the vibration signal x (T).
8. The integrated bearing wear manufacturing and detecting device of claim 7, wherein: whenever the phase difference between successive values is greater/less than + -pi, phase unwrapping is performed by subtracting 2 pi from the phase, and Fourier transform data from Fourier transform of the vibration signal x (t) is input to a deep neural network model to generate a wear state.
CN202210218131.1A 2022-03-07 2022-03-07 Bearing wear manufacturing and detecting integrated device Active CN114739666B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210218131.1A CN114739666B (en) 2022-03-07 2022-03-07 Bearing wear manufacturing and detecting integrated device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210218131.1A CN114739666B (en) 2022-03-07 2022-03-07 Bearing wear manufacturing and detecting integrated device

Publications (2)

Publication Number Publication Date
CN114739666A true CN114739666A (en) 2022-07-12
CN114739666B CN114739666B (en) 2023-05-09

Family

ID=82275792

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210218131.1A Active CN114739666B (en) 2022-03-07 2022-03-07 Bearing wear manufacturing and detecting integrated device

Country Status (1)

Country Link
CN (1) CN114739666B (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2008268162A (en) * 2007-04-18 2008-11-06 Terahertz Laboratory Co Frequency sweeping type terahertz spectrum measurement device
CN103267697A (en) * 2013-05-10 2013-08-28 哈尔滨飞机工业集团有限责任公司 Apparatus used for bearing wearing test
CN109556503A (en) * 2018-10-30 2019-04-02 西南电子技术研究所（中国电子科技集团公司第十研究所） THz clock synchronization frequency modulation continuous wave nondestructive thickness measuring detection system

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2008268162A (en) * 2007-04-18 2008-11-06 Terahertz Laboratory Co Frequency sweeping type terahertz spectrum measurement device
CN103267697A (en) * 2013-05-10 2013-08-28 哈尔滨飞机工业集团有限责任公司 Apparatus used for bearing wearing test
CN109556503A (en) * 2018-10-30 2019-04-02 西南电子技术研究所（中国电子科技集团公司第十研究所） THz clock synchronization frequency modulation continuous wave nondestructive thickness measuring detection system

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
廖晓玲: "太赫兹光谱技术在复合材料无损检测中的应用研究", 《中国优秀硕士学位论文全文数据库工程科技Ⅰ辑》 *

Also Published As

Publication number Publication date
CN114739666B (en) 2023-05-09

Similar Documents

Publication Publication Date Title
CN101261234B (en) Surface flaw detection device
CN103212540B (en) Multi-parameter on-site is measured and separation system automatically
CN202057579U (en) Optical system capable of on-line detecting internal quality of fruits
CN106342170B (en) Hollow turbine vane wall thickness method for automatic measurement
CN102248476A (en) Method and apparatus for the measurement-aided fine machining of workpiece surfaces, and measuring system
CN102141381A (en) Thickness and dimension automatic measuring instrument for insulation layer and protective sleeve of image type cable
CN103712793A (en) Ball screw pair rated dynamic load and life test device and method
CN105928479B (en) A kind of cartridge type part outer diameter on-line measuring device in spinning process
CN104280456B (en) System applied to ultrasonic detection of defects of gas cylinders
CN115561201B (en) Terahertz evaluation device for structural integrity of thermal barrier coating and application method of terahertz evaluation device
CN104931507B (en) A kind of phone housing edge quality detecting system and detection method
CN104062353B (en) Bent axle automation vortex, the compound the cannot-harm-detection device of Magnetic Memory
CN114083358A (en) Industrial robot polishing process optimization method
CN110579536A (en) Multi-probe ultrasonic flaw detection device suitable for large ring piece
CN114758176A (en) Polishing state online monitoring method based on industrial robot body information
CN114739666B (en) Bearing wear manufacturing and detecting integrated device
CN108072407A (en) Turbine case flow-paths inspection system and method
CN109226936B (en) Rotary arc type self-adaptive complex curved surface surfacing method
CN109959723A (en) A kind of turbine engine rotor internal flaw extension detection device and method
CN211696243U (en) On-line processing and detecting device for roller
CN113664053A (en) Nondestructive testing device, system and method for interface bonding rate of bimetal corrugated composite plate
CN108594212A (en) A kind of comprehensive range unit
CN105783832A (en) Method for measuring external diameter of cartridge member during spinning process through on-line detection apparatus
CN113109420B (en) Micromagnetic nondestructive testing system for revolving body part
CN205049177U (en) Super smart grinding precision of cylindrical roller and surface quality on -line monitoring device

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
CB03 Change of inventor or designer information
CB03 Change of inventor or designer information

Inventor after: Zhang Liuyang

Inventor after: Wang Zhongxing

Inventor after: Zheng Wei

Inventor after: Lin Yuansheng

Inventor after: Zhao Zhenxing

Inventor after: Ke Zhiwu

Inventor after: Zhou Hongkuan

Inventor after: Chen Chaoxu

Inventor after: Tian Fengshuo

Inventor after: Lian Guanghui

Inventor after: Wang Rong

Inventor after: Hao Huibo

Inventor after: Wang Xingyu

Inventor before: Zhang Liuyang

Inventor before: Wang Zhongxing

Inventor before: Zheng Wei

Inventor before: Lin Yuansheng

Inventor before: Zhao Zhenxing

Inventor before: Ke Zhiwu

Inventor before: Zhou Hongkuan

Inventor before: Chen Chaoxu

Inventor before: Tian Fengshuo

Inventor before: Lian Guanghui

Inventor before: Wang Rong

Inventor before: Hao Huibo

Inventor before: Wang Xingyu

GR01 Patent grant
GR01 Patent grant