A bearing monitoring method, device and system

Abstract

The present invention provides a bearing monitoring method, device and system, which relate to the field of bearing monitoring technology, in order to solve the problems of long vibration transmission path and severe signal attenuation of vibration signals. The bearing monitoring method comprises: obtaining a bearing image collected from a sensing component during the operation of the bearing, the sensing component is arranged in the bearing, and edge feature detection is performed on the bearing image using the edge feature of the image to obtain an edge detection result. If the edge detection result meets the characteristic mutation condition, it is determined that the bearing has a defect. The electronic device and the non-transient computer-readable storage medium storing computer instructions are used to execute the bearing monitoring method. The bearing monitoring method, device and system provided by the present invention are used in bearing monitoring.

Description

Technical Field

[0001] The present invention relates to the technical field of bearing monitoring, and in particular to a bearing monitoring method, device and system. Background Art

[0002] Compared with ordinary bearings, spindle bearings have the characteristics of high speed, large load, severe cage impact, high friction heat generation and high working environment temperature during operation. It is difficult to lubricate the spindle bearings well, which leads to large-scale changes in operating conditions, slipping and other faults in the spindle bearings in a short period of time. When the spindle bearings produce fatigue, wear and other faults, abnormal vibrations will occur.

[0003] At present, the vibration monitoring method is to install a vibration sensor at an appropriate position of the bearing seat or housing, and the vibration sensor collects signals and analyzes them to determine the bearing fault. Since the installation position of the vibration sensor is limited by the engine structure, usually only one vibration sensor is installed in the casing of the aircraft engine, and the vibration signal emitted by the vibration sensor in the aircraft engine system has problems such as long vibration transmission path and severe signal attenuation. At the same time, conventional image recognition methods have certain limitations in the recognition of bearing images. Summary of the invention

[0004] The object of the present invention is to provide a bearing monitoring method, device and system to solve the problems of long vibration transmission path and severe signal attenuation of vibration signals.

[0005] In a first aspect, the present invention provides a bearing monitoring method, comprising:

[0006] Acquiring a bearing image collected by a sensing component during the operation of the bearing, wherein the sensing component is disposed in the bearing;

[0007] Performing edge feature detection on the bearing image using the image edge feature to obtain an edge detection result;

[0008] If the edge detection result meets the characteristic mutation condition, it is determined that the bearing has defects.

[0009] Compared with the prior art, in the bearing monitoring method provided by the present invention, when the bearing is in operation, the sensing component arranged in the bearing can collect the bearing image, and on this basis, the edge feature of the bearing image is detected by using the edge feature of the image to obtain the edge detection result, and based on this, the edge detection result of the bearing image is compared with the characteristic mutation condition of the bearing image, if the edge detection result of the bearing image meets the characteristic mutation condition of the bearing image, then the bearing has a defect, and if the edge detection result of the bearing image does not meet the characteristic mutation condition of the bearing image, then the bearing has no defect, thereby determining the bearing defect, thereby improving the effect of identifying the defect of the bearing image.

[0010] At the same time, the bearing includes a bearing outer ring, a bearing inner ring, balls, and a cage for fixing the balls, the cage is located between the bearing outer ring and the bearing inner ring, and each sensing component is arranged on the cage. Therefore, the sensing component is arranged in the bearing, and the sensing component can not only collect the bearing image but also collect the vibration signal of the bearing, and the sensing component can wirelessly transmit the collected bearing image and the vibration signal of the bearing to the bearing monitoring device. It can be seen that the exemplary embodiment of the present invention can not only improve the identification of bearing image defects by arranging the sensing component in the bearing, but also shorten the transmission path of the bearing vibration signal and reduce signal attenuation, thereby effectively solving the problems of the long vibration transmission path, complex frequency components, and severe signal attenuation of the bearing vibration signal.

[0011] In a second aspect, the present invention provides a bearing monitoring device, comprising:

[0012] An acquisition module, used to acquire a bearing image collected by a sensing component during the operation of the bearing, wherein the sensing component is disposed in the bearing;

[0013] A detection module, used to perform edge feature detection on the bearing image using image edge features to obtain edge detection results;

[0014] The determination module is used to determine whether the bearing has defects if the edge detection result meets the characteristic mutation condition.

[0015] Compared with the prior art, the beneficial effects of the bearing monitoring device provided by the present invention are the same as the beneficial effects of the bearing monitoring method described in the present invention, which will not be elaborated here.

[0016] In a third aspect, the present invention provides a bearing monitoring system, comprising:

[0017] A bearing monitoring device, a bearing and at least one induction component, each induction component is wirelessly connected to the bearing monitoring device, the bearing comprises a bearing outer ring, a bearing inner ring, balls and a retaining frame for fixing the balls, the balls have permanent magnets, the retaining frame has a coil, the retaining frame is located between the bearing outer ring and the bearing inner ring, and each induction component is arranged on the retaining frame.

[0018] Compared with the prior art, the beneficial effects of the bearing monitoring system provided by the present invention are the same as the beneficial effects of the bearing monitoring method described in the present invention, which will not be described in detail here. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Further details, features and advantages of the invention are disclosed in the following description of exemplary embodiments in conjunction with the accompanying drawings, in which:

[0020] Figure 1 A structural diagram of a bearing according to an embodiment of the present invention is shown;

[0021] Figure 2 The structure diagram of the sensing component and the bayonet of the embodiment of the present invention is shown;

[0022] Figure 3 A structural diagram of an infrared thermal imager module according to an embodiment of the present invention is shown;

[0023] Figure 4 A structural diagram of a rotation speed sensor according to an embodiment of the present invention is shown;

[0024] Figure 5 A structural diagram of an acceleration sensor according to an embodiment of the present invention is shown;

[0025] Figure 6 A flow chart showing a bearing monitoring method according to an embodiment of the present invention is shown;

[0026] Figure 7 A flow chart of obtaining a foreground image according to an embodiment of the present invention is shown;

[0027] Figure 8 A flow chart of edge feature detection of a foreground image according to an embodiment of the present invention is shown;

[0028] Fig. 9 A block diagram of a bearing monitoring device according to an embodiment of the present invention is shown;

[0029] Fig.10 A schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present invention is shown;

[0030] Fig.11 A schematic diagram of the structure of a chip provided by an embodiment of the present invention is shown.

[0031] Reference numerals:

[0032] 101-bearing inner ring, 102-bearing inner ring, 103-ball, 104-sensing component, 105-cage, 106-bayonet, 300-infrared thermal imager module, 301-lens, 302-grating, 303-infrared shell, 304-detector, 400-speed sensor, 401-light source, 402-photoelectric tube, 403-semi-transparent diaphragm, 404-lens, 405-shell, 500-acceleration sensor, 501-elastic part, 5 02-mass block, 503-connecting part, 504-piezoelectric element, 505-base, 900-bearing monitoring device, 901-acquisition module, 902-detection module, 903-determination module, 1010-processor, 1020-memory, 1030-communication interface, 1040-communication route, 1050-processor, 1100-chip, 1110-processor, 1120-memory, 1130-communication interface, 1140-communication route. DETAILED DESCRIPTION

[0033] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0034] It should be noted that when an element is referred to as being "fixed to" or "disposed on" another element, it can be directly on the other element or indirectly on the other element. When an element is referred to as being "connected to" another element, it can be directly connected to the other element or indirectly connected to the other element.

[0035] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined. The meaning of "several" is one or more, unless otherwise clearly and specifically defined.

[0036] In the description of the present invention, it is necessary to understand that the directions or positional relationships indicated by the terms "up", "down", "front", "back", "left", "right", etc. are based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as a limitation on the present invention.

[0037] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0038] Compared with ordinary bearings, spindle bearings have the characteristics of high speed, large load, severe cage impact, high friction heat generation and high working environment temperature during operation. It is difficult to lubricate the spindle bearings well, which leads to large-scale changes in operating conditions, slipping and other faults in the spindle bearings in a short period of time. When the spindle bearings produce fatigue, wear and other faults, abnormal vibrations will occur.

[0039] At present, the vibration monitoring method is to install a vibration sensor at an appropriate position of the bearing seat or housing, and the vibration sensor collects signals and analyzes them to determine the bearing fault. Since the installation position of the vibration sensor is limited by the engine structure, usually only one vibration sensor is installed in the casing of the aircraft engine, and the vibration signal emitted by the vibration sensor in the aircraft engine system has problems such as long vibration transmission path and severe signal attenuation. At the same time, conventional image recognition methods have certain limitations in the recognition of bearing images.

[0040] Based on the above problems, the present invention provides a bearing monitoring method, device and system to solve the problems of long vibration transmission path and severe signal attenuation of vibration signals, thereby improving the identification of defects in bearing images.

[0041] Figure 1 The structural diagram of the bearing of the embodiment of the present invention is shown as follows: Figure 1 As shown, the bearing monitoring system of the embodiment of the present invention includes a bearing monitoring device, a bearing and at least one sensing component 104. It should be understood that the bearing here can be a cylindrical roller bearing, a double-flap outer ring bearing, etc., which are not listed here one by one. The bearing includes a bearing outer ring 101, a bearing inner ring 102, balls 103 and a retaining frame 105 for fixing the balls. The retaining frame is located between the bearing outer ring 101 and the bearing inner ring 102. The balls 103 are fixed on the retaining frame 105. The retaining frame 105 is used to connect the bearing inner ring 102 and the bearing outer ring 101. The bearing inner ring 102 and the bearing outer ring 101 slide relative to each other under the action of the balls 103.

[0042] When the bearing monitoring system of the embodiment of the present invention includes a plurality of sensing components, each sensing component is arranged on a retaining frame. Each sensing component is wirelessly connected to the bearing monitoring device. The bearing monitoring device here can be an external computing platform or other equipment with computing functions.

[0043] In practical applications, Figure 2 The structure diagram of the sensing component and the bayonet of the embodiment of the present invention is shown as follows: Figure 2 As shown, each sensing component 104 is fixed to the retaining frame through a bayonet 106. The sensing component 104 is at least used to collect the bearing image. Since each sensing component is wirelessly connected to the bearing monitoring device, the sensing component 104 can also transmit the bearing image to the bearing monitoring device. The bearing monitoring device provided by the exemplary embodiment of the present invention can improve the recognition of bearing image defects by executing the bearing monitoring method after receiving the bearing image.

[0044] Each sensing component of the exemplary embodiment of the present invention can also collect the vibration signal of the bearing and send it to the bearing monitoring device. The bearing monitoring device can determine the operating status of the bearing by analyzing the vibration signal of the bearing.

[0045] Exemplarily, as shown in the figure, each sensing component has an infrared thermal imager module, an acceleration sensor, a rotation speed sensor, a controller and a wireless communicator, all of which are arranged on a retaining frame. The controller is electrically connected to the infrared thermal imager module, the acceleration sensor, the rotation speed sensor and the wireless communicator through a signal circuit, respectively. The infrared thermal imager module is arranged on the end face away from the bayonet and higher than the surface of the retaining frame, and the vibration acceleration sensor is arranged on the end face close to the bayonet and connected to the bayonet.

[0046] When the bearing is in operation, the rotation of the bearing will generate a lot of heat. The infrared thermal imager module receives the infrared radiation energy distribution diagram in the bearing, and the detector in the infrared thermal imager module determines the bearing image based on the infrared radiation energy distribution diagram. At the same time, during the operation of the bearing, the bearing may vibrate. The acceleration sensor connected to the bayonet at the end face close to the bayonet can collect the vibration signal when the bearing vibrates. The speed sensor located between the thermal imager module and the acceleration sensor can also collect the vibration signal of the bearing. The acceleration sensor and the speed sensor both transmit the vibration signal to the controller through the signal circuit. The controller transmits the vibration signal to the wireless communicator through the signal circuit, and the wireless communicator then transmits the vibration signal to the bearing monitoring device.

[0047] It can be seen that the defects of the bearing image can be determined through the above-mentioned infrared thermal imager module, and the operating status of the bearing can be determined through the acceleration sensor and the speed sensor, thereby realizing real-time monitoring of the bearing operation process.

[0048] In an alternative approach, Figure 3 FIG. 4 shows a structural diagram of an infrared thermal imager module according to an embodiment of the present invention. Figure 3 As shown, the infrared thermal imager module 300 provided by the exemplary embodiment of the present invention includes an infrared shell 303, and a lens 301, a grating 302 and a detector 304 arranged in the infrared shell 303, the lens 301 and the grating 302 are arranged on the incident light path of the detector 304 along the incident direction of the light of the detector 304, and the detector 304 is electrically connected to the controller.

[0049] When the bearing is in operation, a large amount of heat is generated when the bearing rotates. The large amount of heat generates thermal radiation waves that are transmitted to the lens in the infrared shell 303. The lens 301 focuses the thermal radiation waves. The focused thermal radiation waves form light that is irradiated along the infrared shell to the grating 302, so that the light formed by different thermal radiation waves shines on the detector 304 respectively. The detector 304 receives the light formed by different thermal radiation waves to form an infrared radiation energy distribution graph. The detector 304 determines the bearing image based on the infrared radiation energy distribution graph.

[0050] In an alternative approach, Figure 4 The structure diagram of the rotation speed sensor according to the embodiment of the present invention is shown as follows: Figure 4 As shown, the rotation speed sensor 400 provided by the exemplary embodiment of the present invention includes a shell 405, and a light source 401, a lens 404, a semi-transparent membrane 403 and a phototube 402 arranged in the shell 405, the lens 404 and the semi-transparent membrane 403 are arranged on the incident light path of the light source 401 along the incident direction of the light source and the incident direction of the phototube 402, respectively, and the phototube 402 is electrically connected to the controller.

[0051] The light source 401 emits light through the lens 404. The light is focused by the lens 404 and then shines on the translucent membrane 403. The light is reflected by the translucent membrane 403 and then shines on the lens 404. The light is focused by the lens 404 and then shines on the bearing to set a reflection mark. When the bearing is running, the reflection mark will change, and the reflectivity of the reflected light will change. The reflected light shines on the translucent membrane through the lens 404 and then shines on the photoelectric tube. The photoelectric tube 402 converts the change in the position of the reflected signal of the light into an electrical signal. The photoelectric tube 402 finally transmits the electrical signal to the controller. The controller transmits the electrical signal to the wireless communicator through the signal circuit. The wireless communicator then transmits the electrical signal to the bearing monitoring device. The speed information of the bearing can be obtained through the electrical signal.

[0052] In an alternative approach, Figure 5 FIG. 4 shows a structural diagram of an acceleration sensor according to an embodiment of the present invention. Figure 5 As shown, an acceleration sensor 500 provided by an exemplary embodiment of the present invention includes an elastic member 501 , a mass block 502 , a piezoelectric element 504 , a base 505 , and a connecting member 503 , wherein one end of the mass block 502 away from the base 505 is connected to the elastic member 501 .

[0053] like Figure 5 As shown, when the bearing is a double-petal outer ring type spindle bearing, there is relative movement between the two halves of the outer ring. When the bearing is running, the elastic member 501 starts to move with the vibration of the bearing, and the elastic member 501 drives the mass block 502 to move at the same time. At the same time, since the piezoelectric element 504 is located between the base 505 and the mass block 502, the connector 503 connects the elastic member 501, the mass block 502, the piezoelectric element 504 and the base 505 in sequence. Therefore, when the mass block 502 moves, pressure is generated on the piezoelectric element 504. When the piezoelectric element 504 is subjected to the pressure of the mass block 502, it will convert the pressure into a vibration signal in the form of an electrical signal, and transmit the vibration signal to the controller through the signal circuit. The controller then transmits the vibration signal to the bearing monitoring device through the wireless communication device.

[0054] For example, Figure 2As shown, the induction component 104 is connected to the holder through the bayonet 106, which can facilitate the disassembly and reuse of the induction component. At the same time, since the ball has a permanent magnet and the holder has a coil, when the bearing rotates, the permanent magnet in the ball cuts the coil to generate electricity, and the generated electric energy is stored in the power module. It should be understood that the power module here has a battery, and the power module then transmits electricity to the infrared thermal imager module, the acceleration sensor and the rotation speed sensor through the power supply circuit.

[0055] Exemplarily, one end of the acceleration sensor is fixedly connected to the bayonet, and the sensing component also has a cavity for accommodating a controller and a wireless communicator. The cavity is arranged on the base of the vibration acceleration sensor, and the sensing component is connected as a whole. The infrared thermal imager module, the acceleration sensor and the rotation speed sensor are powered by a battery. Each sensor transmits the collected vibration signal to the controller in the sensing component in the form of signal transmission. The controller receives the bearing vibration signal collected by each sensor, and finally transmits the received bearing vibration signal to the bearing monitoring device in a wireless transmission manner. On this basis, when each sensor transmits the collected vibration signal to the controller, there is no need for long-path signal transmission, and at the same time, signal attenuation is reduced, effectively solving the problems of long vibration transmission path, complex frequency components and severe signal attenuation of the vibration signal.

[0056] Figure 6 A flow chart of a bearing monitoring method according to an embodiment of the present invention is shown. The bearing monitoring method provided by an exemplary embodiment of the present invention includes:

[0057] Step 601: during the operation of the bearing, a bearing image collected by a sensing component is obtained, and the sensing component is disposed in the bearing. The manner in which the sensing component is disposed in the bearing can be referred to in the previous text, and will not be described in detail here. The bearing vibration signal collected by the sensing component can be transmitted to the external computing platform described above through wireless communication.

[0058] Step 602: Use the image edge feature to perform edge feature detection on the bearing image to obtain an edge detection result. The edge feature detection here is actually to perform binarization processing on the bearing image to obtain a foreground image.

[0059] Step 603: If the edge detection result meets the characteristic mutation condition, it is determined that the bearing has defects. The characteristic mutation condition here determines the gradient modulus of the binary image based on the wavelet transform components in different directions, and whether the gradient modulus of the binary image meets the maximum condition.

[0060] Exemplarily, an embodiment of the present invention performs binarization processing on the bearing image. When obtaining the foreground image, the bearing image is first converted into grayscale to obtain a grayscale image. For example: in order to reduce the error, according to the radiation distance x, which can also be understood as the distance from the radiation point to the lens of the external thermal imaging camera module, the relative temperature ambient temperature t, which can also be understood as the temperature at the radiation point, the grayscale image is calculated according to the formula F=F1(,x). When the foreground image is obtained, the wavelet transform method is used to detect edge features of the foreground image to obtain an edge detection result.

[0061] In an alternative approach, Figure 7 FIG. 4 shows a flow chart of obtaining a foreground image according to an embodiment of the present invention. Figure 7 As shown, the binarization processing method is a global threshold segmentation method, and the bearing image is binarized to obtain a foreground image.

[0062] Step 701: extracting a foreground estimation image and a background estimation image from a bearing image based on an estimation threshold, where the estimation threshold is a preset threshold.

[0063] Step 702: Update the estimation threshold based on the foreground estimation image and the background estimation image, determine the average value of the foreground estimation image, determine the average value of the background estimation image, and obtain the estimation threshold based on the average value of the foreground estimation image and the average value of the background estimation image.

[0064] Step 703: If the difference between the estimated thresholds before and after the update meets the segmentation termination condition, the updated estimated threshold is determined to be the target threshold. The segmentation termination condition here includes: if the difference between the estimated thresholds before and after the update is greater than or equal to 1, the updated estimated threshold is determined to be the target threshold. If the difference between the estimated thresholds before and after the update is less than 1, the updated estimated threshold is determined to be the estimated threshold.

[0065] Step 704: Binarize the bearing image based on the target threshold.

[0066] In practical applications, the background estimation image is set to G b , set the foreground estimation image to G a , T is set as the estimated threshold, and the bearing image is segmented by the global threshold segmentation method. In order to accurately identify the cracks on the bearing surface, the target threshold is obtained by the iterative method, where Eq. Iterate the foreground estimation image, formula 2 The background estimation image is iterated, and the three target thresholds are obtained by weighted averaging the foreground estimation image and the background estimation image. In the above formula, i represents the segmentation amount in the i direction, j represents the segmentation amount in the j direction, and n represents the nth time. If the grayscale value of the bearing image is greater than or equal to the target threshold, the pixel size of the bearing image is set to 1. If the grayscale value of the bearing image is less than the target threshold, the pixel size of the bearing image is set to 0. At this time, the bearing pixels appear black.

[0067] In an alternative approach, Figure 8 FIG. 4 shows a flow chart of edge feature detection of a foreground image according to an embodiment of the present invention. Figure 8 As shown, the edge feature detection of the foreground image is performed using the wavelet transform method to obtain the edge detection result, including:

[0068] Step 801: Determine the wavelet transformation components of the binary image in different directions.

[0069] Step 802: Determine the gradient modulus of the binary image based on the wavelet transform components in different directions.

[0070] Step 803: If the gradient modulus of the binary image meets the maximum condition, the feature position corresponding to the gradient modulus of the binary image is an edge feature.

[0071] Step 804: The wavelet transform component in each direction is determined by the partial derivative of the smoothing function of the binary image in the corresponding direction and the signal function of the binary image.

[0072] In practical applications, the binary image is divided into multiple wavelet transformation components in different directions through wavelet transform, and the local maximum of the wavelet is used to depict the collection point of information at the edge of the image. If the gradient modulus of the binary image meets the maximum condition, the feature position corresponding to the gradient modulus of the binary image is the edge feature.

[0073] Assume that the infrared thermal image signal function is Y(x, y), the smoothing function is U(x, y), and the partial derivative operation is performed on the direction of the smoothing function to determine the wavelet transform component in each direction to obtain Formula 1:

[0074]

[0075] The partial derivative θ of the smoothing function in the above formula 1 in the x direction 1 (x,y), the partial derivative θ of the signal function in the x direction 2 (x, y) is set as a two-dimensional wavelet function, and the infrared thermal image is transformed by wavelet to obtain formula 2:

[0076]

[0077] Among them, δ in Formula 2 1 Y(x,y) represents the wavelet transform component of the infrared thermal image in one direction, δ2 Y(x,y) represents the wavelet transform component of the infrared thermal image in another direction. The gradient vector and amplitude angle of the wavelet transform at any scale are determined based on formulas 1 and 2. The gradient vector and amplitude angle of the wavelet transform at any scale are obtained as formula 3:

[0078]

[0079] According to the above formula 3, when the gradient modulus M1Y(x,y) reaches the maximum value at point (x,y), the gradient undergoes a drastic mutation at this point. Therefore, by obtaining the position of the local maximum value, the corresponding modulus M1Y(x,y) position, and the corresponding angular position N1Y(x,y) during the change process, the collection point of the defect edge can be depicted, the defect position in the infrared thermal image can be determined, the edge feature detection can be completed, and the defect recognition on the material surface can be realized.

[0080] The method of the exemplary embodiment of the present invention may also include: acquiring a vibration signal of the bearing collected by the sensing component during the operation of the bearing, and sending it to a bearing monitoring device, and the bearing monitoring device may determine the operating status of the bearing by analyzing the vibration signal of the bearing.

[0081] Fig. 9 FIG. 1 is a block diagram of a bearing monitoring device according to an embodiment of the present invention. An exemplary embodiment of the present invention further provides a bearing monitoring device 900 including:

[0082] An acquisition module 901 is used to acquire a bearing image collected by a sensing component during the operation of the bearing, where the sensing component is disposed in the bearing;

[0083] A detection module 902 is used to perform edge feature detection on the bearing image using the image edge feature to obtain an edge detection result;

[0084] The determination module 903 is used to determine whether the bearing has defects if the edge detection result meets the characteristic mutation condition.

[0085] As a possible implementation manner, the detection module 902 is also used to perform grayscale conversion on the bearing image to obtain a grayscale image.

[0086] As a possible implementation, the detection module 902 is used to perform binarization processing on the bearing image to obtain a foreground image, and use the wavelet transform method to perform edge feature detection on the foreground image to obtain an edge detection result. It is used to extract a foreground estimation image and a background estimation image from the bearing image based on an estimation threshold, update the estimation threshold based on the foreground estimation image and the background estimation image, and if the difference between the estimation threshold before and after the update meets the segmentation termination condition, determine the updated estimation threshold as the target threshold, and perform binarization processing on the bearing image based on the target threshold. It is used to determine the updated estimation threshold as the target threshold if the difference between the estimation threshold before and after the update is greater than or equal to 1, and determine the updated estimation threshold as the estimation threshold if the difference between the estimation threshold before and after the update is less than 1. It is used to determine the average value of the foreground estimation image, determine the average value of the background estimation image, and obtain the estimation threshold based on the average value of the foreground estimation image and the average value of the background estimation image.

[0087] As a possible implementation method, the determination module 903 is used to determine the wavelet transform components of the binary image in different directions, and determine the gradient modulus of the binary image based on the wavelet transform components in different directions. If the gradient modulus of the binary image satisfies the maximum condition, the feature position corresponding to the gradient modulus of the binary image is an edge feature, and the wavelet transform component in each direction is determined by the partial derivative of the smoothing function of the binary image in the corresponding direction and the signal function of the binary image.

[0088] Fig.10 FIG. 1 is a schematic diagram showing the hardware structure of an electronic device provided by an embodiment of the present invention. Fig.10 As shown, the electronic device includes a processor 1010 and a communication interface 1030 .

[0089] like Fig.10 As shown, the processor 1010 may be a general-purpose central processing unit 1010 (CPU), a microprocessor 1010, an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the program of the present invention.

[0090] There may be one or more communication interfaces 1030. The communication interface 1030 may use any transceiver or other device for communicating with other devices or communication networks.

[0091] like Fig.10 As shown, the electronic device may further include a communication circuit. The communication circuit may include a path to transmit information between the components.

[0092] Optional, such as Fig.10As shown, the electronic device may further include a memory 1020. The memory 1020 is used to store computer-executable instructions for executing the solution of the present invention, and is controlled to execute by the processor 1010. The processor 1010 is used to execute the computer-executable instructions stored in the memory 1020, thereby implementing the method provided by the embodiment of the present invention.

[0093] like Fig.10 As shown, the memory 1020 may be a read-only memory 1020 (ROM) or other types of static storage devices that can store static information and instructions, a random access memory 1020 (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory 1020 (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 1020 may exist independently and be connected to the processor 1010 via a communication line. The memory 1020 may also be integrated with the processor 1010.

[0094] Optionally, the computer-executable instructions in the embodiment of the present invention may also be referred to as application program codes, which is not specifically limited in the embodiment of the present invention.

[0095] In a specific implementation, as an example, Fig.10 As shown, the processor 1010 may include one or more CPUs, such as Fig.10 CPU0 and CPU1 in.

[0096] In a specific implementation, as an example, Fig.10 As shown, the terminal device may include multiple processors 1010, such as Fig.10 Each of the processors 1010 may be a single-core processor 1010 or a multi-core processor 1010.

[0097] Fig.11 1 is a schematic diagram of the structure of the chip 1100 provided in an embodiment of the present invention. Fig.11As shown, the chip 1100 includes one or more (including two) processors 1110 and a communication interface 1130 .

[0098] Optional, such as Fig.11 As shown, the chip 1100 also includes a memory 1120, which may include a read-only memory 1120 and a random access memory 1120, and provides operation instructions and data to the processor 1110. A portion of the memory 1120 may also include a non-volatile random access memory 1120 (NVRAM).

[0099] In some embodiments, Fig.11 As shown, the memory 1120 stores the following elements, execution modules or data structures, or a subset thereof, or an extended set thereof.

[0100] In the embodiment of the present invention, Fig.11 As shown, the corresponding operation is performed by calling the operation instruction stored in the memory 1120 (the operation instruction may be stored in the operating system).

[0101] like Fig.11 As shown, the processor 1110 controls the processing operations of any one of the terminal devices, and the processor 1110 can also be called a central processing unit (CPU).

[0102] like Fig.11 As shown, the memory 1120 may include a read-only memory 1120 and a random access memory 1120, and provide instructions and data to the processor 1110. A portion of the memory 1120 may also include an NVRAM. For example, in an application, the memory 1120, the communication interface 1130, and the memory 1120 are coupled together through a bus system, wherein the bus system may include a power bus, a control bus, and a status signal bus in addition to a data bus. However, for the sake of clarity, in Fig.11 In the specification, various buses are labeled as bus systems.

[0103] like Fig.11As shown, the method disclosed in the above embodiment of the present invention can be applied to a processor 1110, or implemented by a processor 1110. The processor 1110 may be an integrated circuit chip 1100, which has the ability to process signals. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor 1110 or an instruction in the form of software. The above processor 1110 can be a general processor 1110, a digital signal processor 1110 (digital signal processing, DSP), an ASIC, a field-programmable gate array (field-programmable gate array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present invention can be implemented or executed. The general processor 1110 can be a microprocessor 1110 or the processor 1110 can also be any conventional processor 1110, etc. The steps of the method disclosed in conjunction with the embodiments of the present invention can be directly embodied as being executed by a hardware decoding processor 1110, or can be executed by a combination of hardware and software modules in the decoding processor 1110. The software module may be located in a storage medium mature in the art, such as a random access memory 1120, a flash memory, a read-only memory 1120, a programmable read-only memory 1120, or an electrically erasable programmable memory 1120, a register, etc. The storage medium is located in the memory 1120, and the processor 1110 reads the information in the memory 1120 and completes the steps of the above method in combination with its hardware.

[0104] In one possible implementation, Fig.11 As shown, the communication interface 1130 is used to execute Figure 6 to Figure 11 The processor 1110 is used to execute Figure 6 to Figure 11 The steps of the process in the illustrated embodiment.

[0105] On the one hand, a computer-readable storage medium is provided, in which instructions are stored. When the instructions are executed, the functions performed by the memory 1120 in the above embodiment are implemented.

[0106] On the one hand, a chip 1100 is provided, which is applied to a terminal device. The chip 1100 includes at least one processor 1110 and a communication interface 1130. The communication interface 1130 is coupled to at least one processor 1110. The processor 1110 is used to run instructions to implement the functions performed by the processor 1110 in the above embodiments.

[0107] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instruction is loaded and executed on a computer, the process or function described in the embodiment of the present invention is executed in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, a terminal, a user device or other programmable device. The computer program or instruction can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer program or instruction can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that integrates one or more available media. The available medium can be a magnetic medium, such as a floppy disk, a hard disk, or a tape; it can also be an optical medium, such as a digital video disc (DVD); it can also be a semiconductor medium, such as a solid state drive (SSD).

[0108] Although the present invention is described herein in conjunction with various embodiments, in the process of implementing the claimed invention, those skilled in the art may understand and implement other variations of the disclosed embodiments by viewing the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other components or steps, and "one" or "an" does not exclude multiple situations. A single processor or other unit may implement several functions listed in the claims. Certain measures are recorded in different dependent claims, but this does not mean that these measures cannot be combined to produce good results.

[0109] Although the present disclosure has been described in conjunction with specific features and embodiments thereof, it is apparent that various modifications and combinations may be made thereto without departing from the spirit and scope of the present disclosure. Accordingly, this specification and the drawings are merely exemplary illustrations of the present disclosure as defined by the appended claims, and are deemed to have covered any and all modifications, variations, combinations or equivalents within the scope of the present disclosure. Obviously, those skilled in the art may make various modifications and variations to the present disclosure without departing from the spirit and scope of the present disclosure. Thus, if these modifications and variations of the present disclosure fall within the scope of the claims of the present disclosure and their equivalents, the present disclosure is also intended to include these modifications and variations.

Claims

1. A bearing monitoring method, characterized in that: include: Acquiring a bearing image collected by a sensing component during the operation of the bearing, wherein the sensing component is disposed in the bearing; Performing edge feature detection on the bearing image using the image edge feature to obtain an edge detection result; If the edge detection result meets the characteristic mutation condition, it is determined that the bearing has a defect; The method further comprises: performing grayscale conversion on the bearing image to obtain a grayscale image; The step of performing edge feature detection on the bearing image using the image edge feature to obtain an edge detection result includes: performing binarization processing on the bearing image to obtain a foreground image; Use wavelet transform method to detect edge features of foreground image and obtain edge detection result; The binarization process is a global threshold segmentation method, and the binarization process is performed on the bearing image to obtain a foreground image, including: extracting a foreground estimation image and a background estimation image from the bearing image based on an estimation threshold; updating the estimation threshold based on the foreground estimation image and the background estimation image; If the difference between the estimated thresholds before and after the update satisfies the segmentation termination condition, determining the updated estimated threshold as the target threshold; Performing binarization processing on the bearing image based on the target threshold; The segmentation termination conditions include: If the difference between the estimated thresholds before and after the updating is greater than or equal to 1, determining the estimated threshold after the updating as the target threshold; If the difference between the estimation thresholds before and after the updating is less than 1, the estimation threshold after the updating is determined as the estimation threshold.

2. The bearing monitoring method according to claim 1, characterized in that: The updating of the estimation threshold based on the foreground estimation image and the background estimation image comprises: determining an average value of the foreground estimation image; determining an average value of the background estimation image; An estimated threshold is obtained based on an average value of the foreground estimation image and an average value of the background estimation image.

3. The bearing monitoring method according to claim 1, characterized in that: Performing edge feature detection on the foreground image using a wavelet transform method to obtain an edge detection result, including: Determine the wavelet transform components of the binary image in different directions; Determine the gradient modulus of the binary image based on the wavelet transform components in different directions; If the gradient modulus of the binary image satisfies a maximum condition, a feature position corresponding to the gradient modulus of the binary image is an edge feature; The wavelet transformation component in each of the directions is determined by the partial derivative of the smoothing function of the binarized image in the corresponding direction and the signal function of the binarized image.

4. A bearing monitoring device, applied to the bearing monitoring method according to any one of claims 1 to 3, characterized in that: include: An acquisition module, used to acquire a bearing image collected by a sensing component during the operation of the bearing, wherein the sensing component is disposed in the bearing; A detection module, used to perform edge feature detection on the bearing image using image edge features to obtain edge detection results; The determination module is used to determine that the bearing has a defect if the edge detection result meets the characteristic mutation condition.

5. A bearing monitoring system, characterized in that: It comprises the bearing monitoring device according to claim 4, a bearing and at least one sensing component, each of the sensing components is wirelessly connected to the bearing monitoring device, the bearing comprises a bearing outer ring, a bearing inner ring, balls and a retaining frame for fixing the balls, the balls have permanent magnets, the retaining frame has a coil, the retaining frame is located between the bearing outer ring and the bearing inner ring, and each of the sensing components is arranged on the retaining frame.

6. The bearing monitoring system according to claim 5, characterized in that: Each of the sensing components comprises an infrared thermal imager module, an acceleration sensor, a rotation speed sensor, a controller, a signal circuit, a wireless communicator and a power module. When the bearing is running, the permanent magnet cuts the coil to supply power to the power module. The controller is electrically connected to the infrared thermal imager module, the acceleration sensor, the rotation speed sensor and the wireless communicator respectively through the signal circuit.

7. The bearing monitoring system according to claim 6, characterized in that: The infrared thermal imager module includes an infrared shell, and a lens, a grating and a detector arranged in the infrared shell. The lens and the grating are arranged on the incident light path of the detector along the incident direction of the light of the detector. The detector is electrically connected to the controller.

8. The bearing monitoring system according to claim 6, characterized in that: The rotation speed sensor includes a shell, and a light source, a lens, a translucent membrane and a phototube arranged in the shell. The lens and the translucent membrane are arranged on the incident light path of the light source incident direction along the incident direction of the light source and the incident direction of the light source of the phototube, respectively. The phototube is electrically connected to the controller.

9. The bearing monitoring system according to claim 6, characterized in that: The acceleration sensor comprises an elastic member, a mass block, a piezoelectric element, a base and a connecting member, wherein one end of the mass block away from the base is connected to the elastic member, and the piezoelectric element is located between the base and the mass block; The connecting member connects the elastic member, the mass block, the piezoelectric element and the base in sequence, one end of the connecting member away from the base is connected to the shell, and the piezoelectric element is electrically connected to the controller.

10. The bearing monitoring system according to claim 6, characterized in that: The sensing component also has a cavity for accommodating the controller and the wireless communicator, and the cavity is arranged on the base of the vibration acceleration sensor.

Images